Many cities in low- and medium-income countries (LMICs) are facing rapid unplanned growth of built-up areas, while detailed information on these deprived urban areas (DUAs) is lacking. There exist visible differences in housing conditions and urban spaces, and these differences are linked to urban deprivation. However, the appropriate geospatial information for unravelling urban deprivation is typically not available for DUAs in LMICs, constituting an urgent knowledge gap. The objective of this study is to apply deep learning techniques and morphological analysis to identify degrees of deprivation in DUAs. To this end, we first generate a reference dataset of building footprints using a participatory community-based crowd-sourcing approach. Secondly, we adapt a deep learning model based on the U-Net architecture for the semantic segmentation of satellite imagery (WorldView 3) to generate building footprints. Lastly, we compute multi-level morphological features from building footprints for identifying the deprivation variation within DUAs. Our results show that deep learning techniques perform satisfactorily for predicting building footprints in DUAs, yielding an accuracy of F1 score = 0.84 and Jaccard Index = 0.73. The resulting building footprints (predicted buildings) are useful for the computation of morphology metrics at the grid cell level, as, in high-density areas, buildings cannot be detected individually but in clumps. Morphological features capture physical differences of deprivation within DUAs. Four indicators are used to define the morphology in DUAs, i.e., two related to building form (building size and inner irregularity) and two covering the form of open spaces (proximity and directionality). The degree of deprivation can be evaluated from the analysis of morphological features extracted from the predicted buildings, resulting in three categories: high, medium, and low deprivation. The outcome of this study contributes to the advancement of methods for producing up-to-date and disaggregated morphological spatial data on urban DUAs (often referred to as 'slums') which are essential for understanding the physical dimensions of deprivation, and hence planning targeted interventions accordingly.

Background: As dynamic systems rivers and cities have been in interaction under changing relations over time, and the morphology of many cities has risen through a long and steady struggle between the city functions and the river system flowing inside. This makes river cities an interesting case to study how the presence of geographical features interacts with spatial morphology in the formation of cities.

Methods: The basis of this research is enabled by utilizing a novel model for cross-city comparison presented by Hillier in his Santiago keynote in 2012 called a “star model”. This is done on large samples of cities investigating concurrent configurations, as well as how the properties in this star model react to specific forms of disturbance.

Results: Results illustrate that the foreground network as identified through maximum choice values in cities are more vital to the structure of cities than the bridges. The overall syntactic structure tends to retain its character (degree of distributedness) and the location of its foreground network (which street segments constitute the foreground network) even when bridges are targeted. Furthermore, counter to the initial hypothesis, river cities tend to change less than non-river cities after targeted disturbance of the systems. Finally, the results show that while there is a statistical morphological difference between river cities and non-river cities, this difference is not directly explained through the bridges.

Conclusion: Integrating space syntax with statistical and geospatial analysis can throw light on the way in which the properties of city networks and urban structure reflect the relative effect of rivers on the morphology of river cities. The paper, finally, contributes through offering one piece of a better perception of the structure of river-cities that can support strategies of river-cities interaction as well as enhance our knowledge on the constraints and limits to that interaction.

In the wake of climate change and its impact on increasing the number and intensity of floods, adaptability of cities to and resistance against the flood hazard is critical to retain functionality of the cities. Vulnerability of urban infrastructure and its resilience to flooding from different points of view have been important and worth investigating for experts in different fields of science. Flood hazards as physical phenomena are influenced by form of the cities and thus the magnitude of their impacts can be intensified by urban infrastructures such as street networks and buildings (Bacchin et. al, 2011). In this paper, we aim to develop a method to assess the resilience of a river city (the city of Gothenburg in Sweden), which is prone to flood events, against such disturbances and find out how the city reacts to river floods and to what extent the city retains its accessibility to essential amenities after a flood occurs. To do so, collecting required data; we, firstly, simulate flood inundation with two different return periods (50 and 1000 years) and then the impact areas overlay on the street networks. Evaluating the resilience of the city, syntactic properties of the street networks before and after flooding are measured at different scales. Additionally, accessibility and the minimum distance of the street networks to essential amenities such as healthcare centers, schools and commercial centers, at a medium distance (3 Km) is examined. The results show that flooding influences the city configuration at global scale more than the local scale based on comparison of syntactic properties before and after flooding. However, the results of accessibility and the minimum distance show that the impact of flooding on the functionality of the city is more limited to the riparian areas and the city is not affected globally.

Flooding is one of the most destructive natural disasters which have rapidly been growing in frequency and intensity all over the world. In this view, assessment of the resilience of the city against such disturbances is of high necessity in order to significantly mitigate the disaster effects of flooding on the city structures and the human lives. The aim of this paper is to develop a method to assess the resilience of a river city (the city of Gothenburg in Sweden), which is prone to flood Hazard, against such disturbances. By simulating flood inundation with different return periods, in the first step, the areas of impact are determined. To assess the resilience, two different methods are followed. One is a syntactic method grounded in the foreground network in space syntax theory and the other is based on measuring accessibility to the essential amenities in the city. In the first method, similarity and sameness parameters are defined to quantitatively measure the syntactic resilience in the city. In the next step, accessibility to amenities and the minimum distance to amenities before and after each disturbance is measured. The results, in general, show that such disturbances affect the city structure and the resilience of the city differently. For instance, the city is more resilient after flooding ac- cording to accessibility measures. This clearly means that the answer to the question of resilience is mainly dependent on “resilience of what and for what.”

Disasters, whether natural or man-made have become an issue of mounting concern all over the world. Natural disasters such as floods, earthquakes, landslides, cyclones, tsunamis and volcanic eruptions are yearly phenomena that have devastating effect on infrastructure and property and in most cases, results in the loss of human life. Floods are amongst the most prevalent natural disasters. The frequency with which floods occur, their magnitude, extent and the cost of damage are escalating all around the globe. Accra, the capital city of Ghana experiences the occurrence of flooding events annually with dire consequences. Past studies demonstrated that remote sensing and geographic information system (GIS) are very useful and effective tools in flood risk assessment and management.  This thesis research seeks to demarcate flood risk areas and create a flood risk map for the Greater Accra Metropolitan Area using remote sensing and Geographic information system. Multi Criteria Analysis (MCA) is used to carry out the flood risk assessment and Sentinel-1A SAR images are used to map flood extend and to ascertain whether the resulting map from the MCA process is a close representation of the flood prone areas in the study area.  The results show that the multi-criteria analysis approach could effectively combine several criteria including elevation, slope, rainfall, drainage, land cover and soil geology to produce a flood risk map. The resulting map indicates that over 50 percent of the study area is likely to experience a high level of flood.  For SAR-based flood extent mapping, the results show that SAR data acquired immediately after the flooding event could better map flooding extent than the SAR data acquired 9 days after.  This highlights the importance of near real-time acquisition of SAR data for mapping flooding extent and damages.  All parts under the study area experience some level of flooding. The urban land cover experiences very high, and high levels of flooding and the MCA process produces a risk map that is a close depiction of flooding in the study area.  Real time flood disaster monitoring, early warning and rapid damage appraisal have greatly improved due to ameliorations in the remote sensing technology and the Geographic Information Systems.

Today, people are used to having technology as a constant aid. This also sets expectations that information should always be available. This, together with ongoing climate change that has led to more natural disasters, has laid the foundation for the need to change the methodology for how geographical data is collected, compiled and visualized when used for crisis communication. This study explores how authorities, at present, communicate with the public during a crisis and how this can be done in an easier and more comprehensible way, with the help of Geographical Information Systems (GIS). The goal is to present a new way of collecting, compiling and visualizing geographical data in order to communicate, as an authority, with the public during a crisis. This has been done using a case study with focus on wildfires. Therefore, most of the work consisted of the creation of a prototype, CMAP – Crisis Management and Planning, that visualizes fire-related data. The basic work of the prototype consisted of determining what data that exists and is necessary for the information to be complete and easily understood together with how the data is best implemented. The existing data was retrieved online or via a scheduled API request. Eventrelated data, which is often created in connection with the event itself, was given a common structure and an automatic implementation into the prototype using Google Fusion Tables. In the prototype, data was visualized in two interactive map-based sections. These sections focused on providing the user with the information that might be needed if one fears that they are within an affected location or providing the user with general preparatory information in different counties. Finally, a non-map-based section was created that allowed the public to help authorities and each other via crowdsource data. This was collected in a digital form which was then directly visualized in the prototype’s map-based sections. The result of this showed, among other things, that automatic data flows are a good alternative for avoiding manual data handling and thus enabling a more frequent update of the data. Furthermore, it also showed the importance of having a common structure for which data to be included and collected in order to create a communication platform. Finally, by visualizing of dynamic polygon data in an interactive environment a development in crisis communication that can benefit the public’s understanding of the situation is achieved. This thesis is limited to the functionality and layout provided by the Google platform, including Google Earth Engine, Google Forms, Google Fusion Tables etc

KNAS (Continuous Habitat Mapping of Protected Areas) is a Metria AB project that produces vegetation and habitat mapping in protected areas in Sweden. Vegetation and habitat mapping is challenging due to its heterogeneity, spatial variability and complex vertical and horizontal structure. Traditionally, multispectral data is used due to its ability to give information about horizontal structure of vegetation. LiDAR data contains information about vertical structure of vegetation, and therefore contributes to improve classification accuracy when used together with spectral data. The objectives of this study are to integrate LiDAR and multispectral data for KNAS and to determine the contribution of LiDAR data to the classification accuracy. To achieve these goals, two object-based classification schemes are proposed and compared: a spectral classification scheme and a spectral-LiDAR classification scheme. Spectral data consists of four SPOT-5 bands acquired in 2005 and 2006. Spectral-LiDAR includes the same four spectral bands from SPOT-5 and nine LiDAR-derived layers produced from NH point cloud data from airborne laser scanning acquired in 2011 and 2012 from The Swedish Mapping, Cadastral and Land Registration Authority. Processing of point cloud data includes: filtering, buffer and tiles creation, height normalization and rasterization. Due to the complexity of KNAS production, classification schemes are based on a simplified KNAS workflow and a selection of KNAS forest classes. Classification schemes include: segmentation, database creation, training and validation areas collection, SVM classification and accuracy assessment. Spectral-LiDAR data fusion is performed during segmentation in eCognition. Results from segmentation are used to build a database with segmented objects, and mean values of spectral or spectral-LiDAR data. Databases are used in Matlab to perform SVM classification with cross validation. Cross validation accuracy, overall accuracy, kappa coefficient, producer’s and user’s accuracy are computed. Training and validation areas are common to both classification schemes. Results show an improvement in overall classification accuracy for spectral-LiDAR classification scheme, compared to spectral classification scheme. Improvements of 21.9 %, 11.0 % and 21.1 % are obtained for the study areas of Linköping, Örnsköldsvik and Vilhelmina respectively. 

The Public Transport Network of Stockholm has been a part of the national debate for many years. The network is geographically spread across a large region that connects countryside areas with densely populated areas. The discussion ranges from how to increase the number of passengers due to traffic congestions on our roads to how to increase the capacity within the metro and railway system. Even though the range of topics is large the major discussion has been on the issue of disruptions and cancellation in the network and its impacts on the trustworthiness of the network.The ability to handle vulnerabilities and how to handle the passenger flows of a public transport network can be measured by calculating the redundancy and the robustness of the network. The aim of the thesis is to measure and analyze the redundancy and robustness of crucial nodes within the public network of Stockholm, and to analyze and present effects of evaluated extensions. From the changes in redundancy and robustness of the extensions it is possible to calculate the impact on the passenger welfare of the improvement. It is also possible to compare the impact on passenger welfare of disruptions between the existing and extended networks. The chosen crucial nodes for the analysis in the thesis are Märsta Station and Ekerö Centrum.The results of the thesis shows that the redundancy and robustness of the sub- networks surrounding Märsta Station and Ekerö Centrum were affected by the evaluated extensions.The existing subnetwork of Märsta Station already had the highest possible of the effective graph conductance CG, i.e. was already considered fully connected. The unchanged CG for the extended subnetwork therefore was not suprising. The subnetwork of Ekerö Centrum showed an increase for CG, which was according to the alternative connection via Fittja to Stockholm Central. For the meshedness α, the robustness indicator rT , and the natural connectivity λ both subnetwork extensions shows changes in the same direction, i.e. increase of redundancy and robustness.The difference in output between Märsta Station and Ekerö Centrum is most likely depending on the difference of structure of their existing subnetworks. Ekerö Centrum has a transfer node, Brommaplan, connecting Ekerö Centrum to Stockholm City. Märsta Station on the other hand is directly connected to Stockholm City, without transfer.

Building Information Modelling (BIM) and Virtual Reality (VR) are two of the main directions in the BIM-strategy of the Swedish Transport Administration. Starting from the year 2015 it is a requirement to use BIM even in tenders.

In order to meet these requirements WSP developed their own product Open VR - a data platform for visualization, communication, planning, designing as well as a tool for documentation of new and existing environments.

Geotechnical analysis is an important part in most of the projects and affects the economy, the projects timeframes and further projects design greatly. Availability of good quality basic data is a requirement to succeed in a project.  Inaccurate and late delivered rock and soil 3D models cause the problems at the design stage. A completely or partially automated process for creating 3D soil models using geotechnical database and models presentation in Open VR would provide both economic benefits and reduce the amount of repetitive work in the CAD environment.

One of the biggest issues is to combine data coming from different sources and therefore clear standards on how different fields of technology should prepare their information are needed. The goal of this master thesis is to develop a guideline how to prepare geotechnical objects for Open-VR.

Firstly software that could be used for preparing geotechnical data for Open VR were identified and described. Three products were chosen: NovaPoint, Civil3D, Power Civil. After that data were processed using the software chosen for comparison. Geotechnical objects (3D models of soil layers and 3D boreholes) were prepared for Open VR using these three products. The results were evaluated. Finally a guideline for preparing geotechnical data for Open VR was written. This guideline can be used not only for preparing the geotechnical data for Open VR but for any other product which can be used for the model coordination (for example, NavisWorks etc). This guideline can be used in any geotechnical project where geotechnical data of Swedish standard are used. This guideline can be used as it is in order to create 3D models of soil layers and rock surfaces with help of Civil3D. In case that another kind of software should be used, this guideline can be used as a basis, because the workflow is the same, but some correction can be done concerning what “button should be pressed”.

Recommendations were given depending on the project requirements and application area. Taking into account that WSP decided to not continue with NovaPoint and use Civil 3D and Power Civil instead, then it is recommended to use Civil 3D when it is necessary to create soil layers using field investigations. Results of 3D modelling can be used in NovaPoint, loaded to Open VR and, if necessary, even be imported into Power Civil.

Power Civil can be used in large-scale projects where advanced 3D modelling is required or when all other area of technology use Power Civil for project design.

Even though NovaPoint does not have priority at WSP it should not be out of the game, it can be very useful in projects where the usage of BIM is a requirement. Considering that NovaPoint has good communication with GeoSuite and can produce smart 3D models it is recommended to have a license of NovaPoint at WSP in order being able to follow software development.

The objective of this research was to evaluate the synergistic effects of multitemporal European remote sensing satellite 1 (ERS-1) synthetic aperture radar (SAR) and Landsat thematic mapper (TM) data for crop classification using a per-field artificial neural network (ANN) approach. Eight crop types and conditions were identified: winter wheat, corn (good growth), corn (poor growth), soybeans (good growth), soybeans (poor growth), barley/oats, alfalfa, and pasture. With the per-field approach using a feed-forward ANN, the overall classification accuracy of three-date early- to mid-season SAR data improved almost 20%, and the best classification of a single-date (5 August) SAR image improved the overall accuracy by about 26%, in comparison to a per-pixel maximum-likelihood classifier (MLC). Both single-date and multitemporal SAR data demonstrated their abilities to discriminate certain crops in the early and mid-season; however, these overall classification accuracies (<60%) were not sufficiently high for operational crop inventory and analysis, as the single-parameter, high-incidence-angle ERS-1 SAR system does not provide sufficient differences for eight crop types and conditions. The synergy of TM3, TM4, and TM5 images acquired on 6 August and SAR data acquired on 5 August yielded the best per-field ANN classification of 96.8% (kappa coefficient = 0.96). It represents an 8.3% improvement over TM3, TM4, and TM5 classification alone and a 5% improvement over the per-pixel classification of TM and 5 August SAR data. These results clearly demonstrated that the synergy of TM and SAR data is superior to that of a single sensor and the ANN is more robust than MLC for per-field classification. The second-best classification accuracy of 95.9% was achieved using the combination of TM3, TM4, TM5, and 24 July SAR data. The combination of TM3, TM4, and TM5 images and three-date SAR data, however, only yielded an overall classification accuracy of 93.89% (kappa = 0.93), and the combination of TM3, TM4, TM5, and 15 June SAR data decreased the classification accuracy slightly (88.08%; kappa = 0.86) from that of TM alone. These results indicate that the synergy of satellite SAR and Landsat TM data can produce much better classification accuracy than that of Landsat TM alone only when careful consideration is given to the temporal compatibility of SAR and visible and infrared data.

Our planet is facing unprecedented environmental challenges including rapid urbanization, deforestation, pollution, loss of biodiversity, sea-level rising, melting polar ice-caps and climate change. With its synoptic view and the repeatability, remote sensing offers a powerful and effective means to observe and monitor our changing planet at local, regional and global scale. Since the launch of Landsat-1 in 1972, numerous Earth Observation satellites have been launched providing large volumes of multitemporal data acquired by multispectral, hyperspectral, passive microwave, synthetic aperture radar (SAR), and LiDAR sensors. This chapter first presents an overview of the Earth Observation sensors and trends in multitemporal observation capacity. Then the current status, challenges and opportunities of multitemporal remote sensing are discussed. Finally the synopsis of the book is provided covering a wide array of methods and techniques in processing and analysis of multitemporal remotely sensed images as well as a variety of application examples in both land and aquatic environments.

The overall objective of this research is to evaluate multitemporal Sentinel-1A SAR and Sentinel-2A MSI data for global urban services using innovative methods and algorithms, namely KTH-Pavia Urban Extractor, a robust algorithm for urban extent extraction and KTHSEG, a novel object-based classification method for detailed urban land cover mapping. Ten cities around the world in different geographical and environmental conditions were selected as study areas. Large volume of Sentinel-1A SAR and Sentinel-2A MSI data were acquired during vegetation season in 2015 and 2016. The preliminary urban extraction results showed that urban areas and small towns could be well extracted using multitemporal Sentinel-1A SAR data with the KTH-Pavia Urban Extractor. For urban land cover mapping, multitemporal Sentinel-1A SAR data alone yielded an overall classification accuracy of 60% for Stockholm. Sentinel-2A MSI data as well as the fusion of Sentinel-1A SAR and Sentinel-2A MSI data, however, produced much higher classification accuracies, both reached 80%.

The overall objectives of this research are to investigate spaceborne SAR data, optical data and fusion of SAR and optical data for urbanization monitoring in China, and to assess the impact of urbanization on the environment for sustainable development. Effective segmentation and classification methods for urban extent extraction and land cover mapping were developed. Several change detection algorithms and approaches using SAR and optical data were evaluated. Further, synergistic effects of multisensor SAR data as well as ASAR and HJ-1B data are examined. The results show that the developed methods were effective for urban extent extraction, land cover mapping and change detection. The fusion of multisensor spaceborne SAR as well as fusion of ASAR and HJ-1 data were beneficial for urban land cover mapping. The spatiotemporal patterns of urbanization in China were analyzed. The results show that rapid urbanization in Yangtze River Delta, Jingjinji and Pearl River Delta has a significant impact on the environment in terms of landscape fragmentation and ecosystem services.

Based on photo-interpretation procedures, the technique of sequential masking can be used to differentiate image features using a series of multitemporal images. In this study, a set of nine ERS-1 SAR images is analyzed using this technique to determine the earliest dates for identifying different crop types in an agricultural area of southern Ontario, Canada. SAR temporal backscatter profiles of crops were generated from calibrated radar imagery. Based on these temporal backscatter profiles, per-field classifications using the sequential-masking technique were performed on the early- and mid-season multitemporal SAR data. It was found that using only three images, acquired on May 31, June 16 and July 5, it is possible to differentiate winter wheat, alfalfa/hay, barley/oats, soybeans and corn with an overall validation accuracy of 88.5% and a Kappa coefficient of 0.85.

Multi-temporal radar backscatter characteristics of crops and their underlying soils were analysed for an agricultural area in south-western Ontario, Canada using nine dates of ERS-1 SAR imagery acquired during the 1993 growing season. From the calibrated data, SAR temporal backscatter profiles were generated for each crop type. The results indicate that small changes in incidence-angle can have strong impacts on radar backscatter. Thus, attention must be given to local incidence-angle effects when using ERS-1 SAR data,especially when comparing backscatter coefficients of the same area from different scenes or different areas within the same scene.

The overall objective of this research is to evaluate multitemporal spaceborne SAR and optical data for urban land cover mapping and urbanization monitoring. Multitemporal Sentinel-1A SAR and historical ERS SAR and ENVISAT ASAR data as well as HJ-1B multispectral data were acquired in Beijing, Chendgdu and Nanchang, China where rapid urbanization has taken place. KTHSEG, a novel object-based classification method is adopted for urban land cover mapping while KTH-Pavia Urban Extractor, a robust algorithm is improved for urban extent extraction and urbanization monitoring. The research demonstrates that, for urban land cover classification, the fusion of multitemporal SAR and optical data is superior to SAR or optical data alone. The second best classification result is achieved using fusion of 4-date SAR and one HJ-1B image. The results indicate that carefully selected multitemporal SAR dataset and its fusion with optical data could produce nearly as good classification accuracy as the whole multitemporal dataset. The results also show that KTH-SEG, the edge-aware region growing and merging segmentation algorithm, is effective for classification of SAR, optical and their fusion. KTH-SEG outperforms eCognition, the commonly used commercial software, for image segmentation and classification of linear features. For Urban extent extraction, single-date and multitemporal SAR data including ERS SAR, ENVISAT ASAR and Sentinel-1A SAR achieved very promising results in all study areas using the improved KTH-Pavia Urban Extractor. The results showed that urban areas as well as small towns and villages could be well extracted using multitemporal Sentinel-1A SAR data while major urban areas could be well extracted using a single-date single-polarization SAR image. The results clearly demonstrate that multitemporal SAR data are cost- and time-effective way for monitoring spatiotemporal patterns of urbanization.

The overall objective of this research is to evaluate multitemporal Sentinel-1A SAR and Sentinel-2A MSI data for global urban services using innovative methods and algorithms, namely KTH-Pavia Urban Extractor, a robust algorithm for urban extent extraction and KTH-SEG, a novel object-based classification method for detailed urban land cover mapping. Ten cities around the world in different geographical and environmental conditions were selected as study areas. Large volumes of Sentinel-1A SAR and Sentinel-2A MSI data were acquired during the vegetation season in 2015 and 2016. The urban extraction results showed that urban areas and small towns could be well extracted using multitemporal Sentinel-1 SAR, Sentinel-2A MSI data and their fusion using the Urban Extractors developed within the project. For urban land cover mapping, multitemporal Sentinel-1A SAR data alone yielded an overall classification accuracy of 60% for Stockholm. Sentinel-2A MSI data as well as the fusion of Sentinel-1A SAR and Sentinel-2A MSI data, however, produced much higher classification accuracies, both reached 80%.

With its synoptic view and the repeatability, satellite remote sensing can provide timely, accurate and consistent information about earth’s surface for costeffective monitoring of environmental changes. In this chapter, recent development in change detection techniques using multitemporal remotely sensed images were reviewed. The chapter covers change detection methods for both optical and SAR images. Various aspects of change detection processes were presented including data preprocessing, change image generation and change detection algorithms such as unsupervised and supervised change detection as well as pixel-based and objectbased change detection. The review shows that significant progress has been made in the field of change detection and innovative methods have been developed for change detection using both multitemporal SAR and optical data. Attempts have been made for change detection using multitemporal multisensor/cross-sensor images. The review also identified a number of challenges and opportunities in change detection.

In recent years, the world witnessed many devastating wildfires that resulted in destructive human and environmental impacts across the globe. Emergency response and rapid response for mitigation calls for effective approaches for near real-time wildfire monitoring. Capable of penetrating clouds and smoke, and imaging day and night, Synthetic Aperture Radar (SAR) can play a critical role in wildfire monitoring. In this communication, we investigated and demonstrated the potential of Sentinel-1 SAR time series with a deep learning framework for near real-time wildfire progression monitoring. The deep learning framework, based on a Convolutional Neural Network (CNN), is developed to detect burnt areas automatically using every new SAR image acquired during the wildfires and by exploiting all available pre-fire SAR time series to characterize the temporal backscatter variations. The results show that Sentinel-1 SAR backscatter can detect wildfires and capture their temporal progression as demonstrated for three large and impactful wildfires: the 2017 Elephant Hill Fire in British Columbia, Canada, the 2018 Camp Fire in California, USA, and the 2019 Chuckegg Creek Fire in northern Alberta, Canada. Compared to the traditional log-ratio operator, CNN-based deep learning framework can better distinguish burnt areas with higher accuracy. These findings demonstrate that spaceborne SAR time series with deep learning can play a significant role for near real-time wildfire monitoring when the data becomes available at daily and hourly intervals with the launches of RADARSAT Constellation Missions in 2019, and SAR CubeSat constellations.

In the last few decades, there has been a growing interest in studying non-contact methods for full-field displacement and strain measurement. Among such techniques, Digital Image Correlation (DIC) has received particular attention, thanks to its ability to provide these information by comparing digital images of a sample surface before and after deformation. The method is now commonly adopted in the field of civil, mechanical and aerospace engineering and different companies and some research groups implemented 2D and 3D DIC software. In this work a review on DIC software status is given at first. Moreover, a free and open source 2D DIC software is presented, named py2DIC and developed in Python at the Geodesy and Geomatics Division of DICEA of the University of Rome "La Sapienza"; its potentialities were evaluated by processing the images captured during tensile tests performed in the Structural Engineering Lab of the University of Rome "La Sapienza" and comparing them to those obtained using the commercial software Vic-2D developed by Correlated Solutions Inc, USA. The agreement of these results at one hundredth of millimetre level demonstrate the possibility to use this open source software as a valuable 2D DIC tool to measure full-field displacements on the investigated sample surface.

Synthetic Aperture Radar (SAR) satellite data are widely used to monitor deformation phenomena impacting the Earth's surface (e.g. landslides, glacier motions, subsidence, and volcano deformations) and infrastructures (e.g. bridges, dams, buildings). The analysis is generally performed using the Differential SAR Interferometry (DInSAR) technique that exploits the phase information of SAR data. However, this technique suffers for lack of coherence among the considered stack of images, and it can only be adopted to monitor slow deformation phenomena. In the field of geohazards monitoring and glacier melting, the Offset Tracking technique has been also widely investigated. This approach is based on the amplitude information only but it reaches worse accuracy compared to DInSAR. To overcome the limitations of DInSAR and Offset Tracking, in the last decade, a new technique called Imaging Geodesy has been investigated exploiting the amplitude information and the precise orbit of the modern SAR platforms (i.e. TerraSAR-X, COSMO-SkyMed). In this study, an investigation of using COSMO-SkyMed data for Earth surface monitoring was performed. The developed approach was applied to a set of imagery acquired over the Corvara (Northern Italy) area, which is affected by a fast landslide with yearly displacements up to meters. Specifically, two well identifiable and stable human-made Amplitude Persistent Scatterers (APSs) were considered to estimate the residual errors of COSMO-SkyMed sensor during the acquisition period between 2010 and 2015. Then, the same methodology was applied to estimate the displacement of a Corner Reflector (CR) located in the landslide area. Finally, the results were compared to the available GPS reference trend showing a good agreement.

Thanks to the advances in computer power, memory storage and the availability of low-cost and high resolution digital cameras, Digital Image Correlation (DIC) is currently one of the most used optical and non-contact techniques for measuring material deformations. A free and open source 2D DIC software, named py2DIC, was developed at the Geodesy and Geomatics Division of the Sapienza University of Rome. Implemented in Python, the software is based on the template matching method and computes the 2D displacements and strains of samples subjected to mechanical loading. In this work, the potentialities of py2DIC were evaluated by processing two different sets of experimental data and comparing the results with other three well known DIC software packages Ncorr, Vic-2D and DICe. Moreover, an accuracy assessment was performed comparing the results with the values independently measured by a strain gauge fixed on one of the samples. The results demonstrate the possibility of successfully characterizing the deformation mechanism of the investigated materials, highlighting the pros and cons of each software package.

The assessment of cracks in civil infrastructures commonly relies on visual inspections carried out at night, resulting in limited inspection time and an increased risk of crack oversight. The Digital Image Correlation (DIC) technique, employed in structural monitoring, requires stationary cameras for image collection, which proves challenging for long-term monitoring. This paper describes the Crack Monitoring from Motion (CMfM) methodology for automatically detecting and measuring cracks using non-fixed cameras, combining Convolutional Neural Networks and photogrammetry. Through evaluation using images obtained from laboratory tests on concrete beams and subsequent comparison with DIC and a pointwise sensor, CMfM demonstrates accurate crack width computation within a few hundredths of a millimetre when compared to the sensor. This method exhibits potential for effectively monitoring temporal crack evolution using non-fixed cameras.

Civil infrastructures, such as tunnels and bridges, are directly related to the overall economic and demographic growth of countries. The aging of these infrastructures increases the probability of catastrophic failures that results in loss of lives and high repair costs; all over the world, these factors drive the need for advanced infrastructure monitoring systems. For these reasons, in the last years, different types of devices and innovative infrastructure monitoring techniques have been investigated to automate the process and overcome the main limitation of standard visual inspections that are used nowadays. This paper presents some preliminary findings of an ongoing research project, named TACK, that combines advanced deep learning techniques and innovative photogrammetric algorithms to develop a monitoring system. Specifically, the project focuses on the development of an automatic procedure for crack detection and measurement using images of tunnels and bridges acquired with a mobile mapping system. In this paper, some preliminary results are shown to investigate the potential of a deep learning algorithm in detecting cracks occurred in concrete material. The model is a CNN (Convolutional Neural Network) based on the U-Net architecture; in this study, we tested the transferability of the model that has been trained on a small available labeled dataset and tested on a large set of images acquired using a customized mobile mapping system. The results have shown that it is possible to effectively detect cracks in unseen imagery and that the primary source of errors is the false positive detection of crack-like objects (i.e., contact wires, cables and tile borders).

With new directives from Swedish authorities imposing municipalities to digitize sections of their plan archives, the question of digital detailed plans is becoming more relevant than ever in Sweden. Digitizing already existing detailed plans is time consuming, so effective automated digitizing methods will be valuable to save time in this process. However, in order to know if a method is effective it first has to be evaluated. This study aims at evaluating a recently introduced method for automated digitizing of detailed plans, and it is the first one evaluating this method in a quantitative manner. The questions to be answered within the study is whether the implemented method is effective and if it has any weaknesses. Additionally, whether a number of defining characteristics of the detailed plan maps influence the quality of the result. As the quality of digitized detailed plans have not been subjected to systematic evaluation before, a novel contribution of this study is also suggesting a framework for how this can be measured and evaluated.

The method consists of 3 steps and the first 2 steps, namely automated georeferencing and automated vectorization, have been performed on a set of 75 detailed plans. Using manually digitized versions of the same detailed plans as ground truth, the results of these two steps have been compared and evaluated using a set of quantitative measures. 

Findings from this study have shown that about 70% of the detailed plans tested can be georeferenced, and 44% of relevant areas in the plan maps can be vectorized using the method. However, the results have displayed a significant disparity of quality, with error values for georeferencing ranging between under 5 meter for the best results and over 100 meters for the worst.

The weaknesses that have been identified for the method are mainly that the georeferencing procedure requires extensive manual supervision, that the vectorization produces polygons of ambiguous belonging, and that the method is limited to multicolor detailed plans. Furthermore, a small plan area has been identified as the most influential factor for a low quality result. Main conclusions of this study have been that the method can be considered effective for digitizing detailed plans to some extent. Additionally, the method for evaluating the quality of digitizing could be expanded by reviewing more factors such as shape and gaps between polygons in future work.

Maintaining infrastructure of high standard is important for all countries. Failing this means severe logistical and economic consequences. Power line inspection is an important part of this. This thesis has searched for an answer to what the advantages and disadvantages are of inspecting power lines by using satellites, as well as an answer to if the technology of satellite surveillance of power lines is sufficient to estimate forest volume. The methodology of the thesis has been to turn to companies and experts in the field and to use relevant literature. Examining what the advantages and disadvantages of satellite inspection of power lines are was important since satellite surveillance is a growing field, but not very well researched. To analyze whether technology of satellite surveillance of power lines is enough to estimate forest volume was thought to be valuable since forest volume today is estimated by airborne LiDAR, while airborne LiDAR was claimed to be significantly more expensive in general than 3 satellite measurements. Thus, there was a potential economic advantage to estimate forest volume with satellites instead of airborne measurements. The expected result was that the technology of satellite surveillance of power lines is sufficient to estimate forest volume. The biggest disadvantages of satellite surveillance of power lines involve the problems of achieving high enough accuracy in the processes of tree identification, as well as developing effective formulas to evaluate this when the research material of proposed methods is sparse. Another disadvantage turned out to be that the satellite methods are hard to compete with, in comparison to the established airborne LiDAR methods and in regard to cost. The reason is that the high-resolution satellite images that often are demanded still are expensive, even though an advantage that also was identified in this thesis is that new and cheaper satellite technology is being developed at a quick rate. The biggest advantage of satellite surveillance of power lines turned out to be the quick development of new satellites with higher resolution, which enables the possibility to catch up with the conventional methods. The expected result in regard to whether satellite surveillance has economic advantages compared to airborne surveillance is contradicted in the result of this thesis, in regard to power line inspection. However, the result indicates that the technology of satellite surveillance of power lines is sufficient to estimate forest volume, which concurs with the expected result.

For several years, the occurrence of more severe and uncontrolled wildfires has been increasing. There is a need to detect wildfires with a higher spatial and temporal resolution than the ones currently provided by operational satellites. In this thesis, an imager study and orbital design of a microsatellite constellation using near infrared (NIR) and shortwave infrared (SWIR) imagers for wildfire monitoring, with enhanced spatial and temporal resolution, was conducted. After a state of the art review, different alternatives of imaging systems were discerned: two commercial sensors with spectral range of 0.7 to 1.7 μm and spatial resolution of 140 m and 112 m, respectively; one commercial sensor with spectral range up to 2.2 μm and spatial resolution of 168 m; and one sensor proposal with higher spatial resolution of 20 m or 50 m, achieved by increasing the focal length. Several conclusions were reached with regards to the imagers: the appropriateness of lenses found for each sensor was confirmed, the Earth rotation distortion was found to increase as the exposure time is extended, as did the signal-to noise ratio. A proposal for a circular sun-synchronous polar orbit with a daily repeating pattern was made. Applying a simplified method to calculate the semi-major axis, an altitude of 561 km and inclination of 97.64° were determined. Accordingly, the number of satellites for both global and regional (Sweden) coverage was estimated for all imager alternatives. For global coverage, the necessary number of satellites to achieve a spatial resolution of 140.25 m was calculated to be 15 satellites, whereas for a spatial resolution of 50 m the number of satellites increased to 84. On the other hand, for regional coverage (Sweden), the number of satellites to achieve a spatial resolution of 140.25 m were 6, and for a spatial resolution of 50 m the number of satellites was 32. This thesis shows how many satellites are required for either global or regional coverage, considering different imager configurations, to detect wildfires with a higher spatial and temporal resolution.

When companies are expanding, they are searching for optimal locations according to parameters which are important for the company. Companies for which the geographic location is important needs to rely on geographic aspects to find the optimal site for their service. The geographic tool of using Suitability Analysis can make the planning of expansions more efficient. Is it possible to give a reliable Suitability Analysis and will it differ between different choices of weighting techniques in the analysis?

The focus of the study is on the reliability of Suitability Analysis for expanding companies depending on geographic data. It will, through a study on a start-up company, be checked if the Suitability Analysis is different between two frequently used weighting ideas; Analytic Hierarchy Process and Swing Weight Technique, in this type of analysis. The Suitability Analysis will be done using Geographical Information Systems and the result will be two suitability maps.

The study results in two different suitability maps, one for each weighting technique, with differences. The different techniques are dissimilar in their subjectivity of the weighting, which is reflected in the result.

Suitability Analysis is useful for companies which expansions are depending on geographic aspect. The key to a reliable and useful suitability analysis is depending on a credible source of data for respectively parameter of interest. It decreases the risk of error sources and gives the result a higher reliability. 

Along with the increasing rate of urbanization takes place in the world, the population keeps shifting from rural to urban areas. China, as the country of the largest population, has the highest urban population growth in Asia, as well as the world. However, the urbanization in China, in turn, is leading to a lot of social issues which reshape the living environment and cultural fabric. A variety of these kinds of social issues emphasize the challenges regarding a healthy and sustainable urban growth particularly in the reasonable planning of urban land use and land cover features. Therefore, it is significant to establish a set of comprehensive urban sustainable development strategies to avoid detours in the urbanization process.

Nowadays, faced with such as a series of the social phenomenon, the spatial and temporal technological means including Remote Sensing and Geographic Information System (GIS) can be used to help the city decision maker to make the right choices. The knowledge of land use and land cover changes in the rural and urban area assists in identifying urban growth rate and trend in both qualitative and quantitatively ways, which provides more basis for planning and designing a city in a more scientific and environmentally friendly way. This paper focuses on the urban sprawl analysis in Nanjing, Jiangsu, China that being analyzed by urban growth pattern monitoring during a study period.

From 2001 to 2016, Nanjing Municipality has experienced a substantial increase in the urban area because of the growing population. In this paper, one optimal supervised classification with high accuracy which is Support Vector Machine (SVM) classifier was used to extract thematic features from multitemporal satellite data including Landsat 7 ETM+, Landsat 8, and Sentinel-2A MSI. It was interpreted to identify the existence of urban sprawl pattern based on the land use and land cover features in 2001, 2006, 2011, and 2016. Two different types of change detection analysis including post-classification comparison and change vector analysis (CVA) were performed to explore the detailed extent information of urban growth within the study region. A comparison study on these two change detection analysis methods was carried out by accuracy assessment. Based on the exploration of the change detection analysis combined with the current urban development actuality, some constructive recommendations and future research directions were given at last.

By implementing the proposed methods, the urban land use and land cover changes were successfully captured. The results show there is a notable change in the urban or built-up land feature. Also, the urban area is increased by 610.98 km² while the agricultural land area is decreased by 766.96 km2, which proved a land conversion among these land cover features in the study period. The urban area keeps growing in each particular study period while the growth rate value has a decreasing trend in the period of 2001 to 2016. Besides, both change detection techniques obtained the similar result of the distribution of urban expansion in the study area. According to the result images from two change detection methods, the expanded urban or built-up land in Nanjing distributes mainly in the surrounding area of the central city area, both side of Yangtze River, and Southwest area.

The results of change detection accuracy assessment indicated the post-classification comparison has a higher overall accuracy 86.11% and a higher Kappa Coefficient 0.72 than CVA. The overall accuracy and Kappa Coefficient for CVA is 75.43% and 0.51 respectively. These results proved the strength of agreement between predicted and truth data is at ‘good’ level for post-classification comparison and ‘moderate’ for CVA. Also, the results further confirmed the expectation from previous studies that the empirical threshold determination of CVA always leads to relatively poor change detection accuracy. In general, the two change detection techniques are found to be effective and efficient in monitoring surface changes in the different class of land cover features within the study period. Nevertheless, they have their advantages and disadvantages on processing change detection analysis particularly for the topic of urban expansion.

Gender equality is a fundamental human right and is part of one of the goals of the 2030 Agenda (Goal 5), which promotes a more equitable and sustainable way of life. A gender imbalance still exists in the transport sector. Over the years, the reasons why women travel have changed, as have their modal preferences, thanks to the introduction of concessions (pink parking, pregnant seats) but also thanks to the introduction of new forms of mobility and multimodality. However, several works in the literature point out that women's journeys are in many cases more difficult than those of men because there are several factors that influence this imbalance. The recent COVID-19 pandemic has contributed to a widening this gap. Through the administration of an online questionnaire, it was possible to find data regarding socio-demographic characteristics, travel habits and finally to analyze the main problems and feelings (feeling of safety on board, perception of a possible contagion and overall evaluation of gender equity both as passengers and as drivers of vehicles) related to the different modes of transport present in the Sicilian context. A statistical comparison of the results was defined considering the different pandemic phases from January 2020 to December 2021. The results show the basis for a better mobility planning starting from the resolution of the COVID-19 crisis that represents an opportunity to change the status quo.

Mobility since 2000 has undergone enormous changes due to new modes of transport and related technologies as well as catastrophic and pandemic events. Several strategies have been implemented by European states to mitigate impacts and assess possible risks in a preventive way. Today, mobility pursues the objectives of sustainability and resilience through a series of short-, medium- and long-term strategies that encourage the collaboration of the population to the choices of urban planning and design. Among the different modes of transport that have had a rise in recent years are scooters. Such modes are well suited to connecting spaces within the first and last mile. Similar to other modes of transportation, scooters are also characterized to date by reduced gender equity. The present work investigates through the administration of an online survey the participants' perceptions concerning the factors that most affect this gender balance considering the metropolitan areas of Catania and Palermo in Sicily. The development of an ordinal regression model revealed the most influential factors of the gender equality variable. Specifically, age, job occupation and perceived safety level of micromobility modes play the most important role. The present findings can be effectively utilized in the planning stage of e-scooter services towards the bridging of the gender gap.

Dragon is a cooperation Programme between the European Space Agency (ESA) and the Ministry of Science and Technology (MOST) of the P.R. China. The Programme, initiated in 2004, focuses on the exploitation of ESA, Third Party Missions (TPM) and Chinese Earth Observation (EO) data for geo-science and applications development in land, ocean and atmospheric applications. In particular, the Programme brings together joint Sino- European teams to investigate 50 thematic projects. In this paper, the results of the research projects1 in the thematic field "Land and Environment" will be briefly presented, whereas emphasis will be given in the assessment of the usefulness of the results for an integrated assessment of the state of the environment in the respective study areas. Furthermore new knowledge gained in such fields as desertification assessment, drought and epidemics' monitoring, forest modeling, cropwatch monitoring, climate change vulnerability (including climate change adaptation and mitigation plans), urbanization monitoring and land use/cover change assessment and monitoring, will be presented. Such knowledge will be also linked to the capacities of Earth Observation systems (and of the respective EO data) to support the temporal, spatial and spectral requirements of the research studies. The potential of DRAGON to support such targets as "technology and knowledge transfer at the bilateral level", "common EO database for exploitation" and "data sharing and open access data policy" will be also presented. Finally special consideration will be given in highlighting the replication potential of the techniques as developed in the course of the projects, as well as on the importance of the scientific results for environmental policy drafting and decision making.

30-m Global Land Cover (GLC) data products permit the detection of land cover changes at the scale of most human land activities, and are therefore used as fundamental information for sustainable development, environmental change studies, and many other societal benefit areas. In the past few years, increasing efforts have been devoted to the accuracy assessment of GlobeLand30 and other finer-resolution GLC data products. However, most of them were conducted either within a limited percentage of map sheets selected from a global scale or in some individual countries (areas), and there are still many areas where the uncertainty of 30-m resolution GLC data products remains to be validated and documented. In order to promote a comprehensive and collaborative validation of 30-m GLC data products, the GEO Global Land Cover Community Activity had organized a project from 2015 to 2017, to examine and explore its major problems, including the lack of international agreed validation guidelines and on-line tools for facilitating collaborative validation activities. With the joint effort of experts and users from 30 GEO member countries or participating organizations, a technical specification for 30-m GLC validation was developed based on the findings and experiences. An on-line validation tool, GLCVal, was developed by integrating land cover validation procedures with the service computing technologies. About 20 countries (regions) have completed the accuracy assessment of GlobeLand30 for their territories with the guidance of the technical specification and the support of GLCVal.

Background: The use of an automated external defibrillator (AED) prior to EMS arrival can increase 30-day survival in out-of-hospital cardiac arrest (OHCA) significantly. Drones or unmanned aerial vehicles (UAV) can fly with high velocity and potentially transport devices such as AEDs to the site of OHCAs. The aim of this explorative study was to investigate the feasibility of a drone system in decreasing response time and delivering an AED. Methods: Data of Global Positioning System (GPS) coordinates from historical OHCA in Stockholm County was used in a model using a Geographic Information System (GIS) to find suitable placements and visualize response times for the use of an AED equipped drone. Two different geographical models, urban and rural, were calculated using a multi-criteria evaluation (MCE) model. Test-flights with an AED were performed on these locations in rural areas. Results: In total, based on 3,165 retrospective OHCAs in Stockholm County between 2006-2013, twenty locations were identified for the potential placement of a drone. In a GIS-simulated model of urban OHCA, the drone arrived before EMS in 32 % of cases, and the mean amount of time saved was 1.5 min. In rural OHCA the drone arrived before EMS in 93 % of cases with a mean amount of time saved of 19 min. In these rural locations during (n = 13) test flights, latch-release of the AED from low altitude (3-4 m) or landing the drone on flat ground were the safest ways to deliver an AED to the bystander and were superior to parachute release. Discussion: The difference in response time for EMS between urban and rural areas is substantial, as is the possible amount of time saved using this UAV-system. However, yet another technical device needs to fit into the chain of survival. We know nothing of how productive or even counterproductive this system might be in clinical reality. Conclusions: To use drones in rural areas to deliver an AED in OHCA may be safe and feasible. Suitable placement of drone systems can be designed by using GIS models. The use of an AED equipped drone may have the potential to reduce time to defibrillation in OHCA.

Natural disasters result in devastating losses in human life, environmental assets, and personal, regional, and national economies. The availability of different big data such as satellite images, Global Positioning System (GPS) traces, mobile Call Detail Records (CDR), social media posts, etc., in conjunction with advances in data analytic techniques (e.g., data mining and big data processing, machine learning and deep learning), can facilitate the extraction of geospatial information that is critical for rapid and effective disaster response. However, disaster response system development usually requires the integration of data from different sources (streaming data sources and data sources at rest) with different characteristics and types, which consequently have different processing needs. Deciding which processing framework to use for a specific big data to perform a given task is usually a challenge for researchers from the disaster management field. While many tasks can be accomplished with population and movement data, for disaster management, a key and arguably most important task is to analyze the displacement of the population during and after a disaster. Therefore, in this thesis, the knowledge and framework resulted from a literature review. These were used to select tools and processing strategies to perform population displacement (the forced movement or relocation of people from their original homes) analysis after a disaster. This is a use case of the framework as well as an illustration of the value and challenges (e.g., gaps in data due to power outages) of using CDR data analysis to support disaster management.

Displaced populations were inferred by analyzing the variation of home cell-tower for each anonymized mobile phone subscriber before and after a disaster using CDR data. The effectiveness of the proposed method is evaluated using remote sensing-based building damage assessment data and Displacement Tracking Matrix (DTM) from individuals’ survey responses at shelters after a severe cyclone in Beira city, central Mozambique, in March 2019. The results show an encouraging correlation coefficient (over 70%) between the number of arrivals in each neighborhood estimated using CDR data and from DTM. In addition to this, CDR-based analysis derives the spatial distribution of displaced populations with high coverage of people, i.e., including not only people in shelters but everyone who used a mobile phone before and after disaster. Moreover, results suggest that if CDR data are available after a disaster, population displacement can be estimated. These details can be used for response activities and for example to contribute to reducing waterborne diseases (e.g., diarrheal disease) and diseases associated with crowding (e.g., acute respiratory infections) in shelters and host communities.

Although COVID-19 is not a post-disaster disease, it is an acute respiratory illness that can be severe. By assuming that its characteristics can be similar to an acute respiratory infection following a disaster, a deep learning approach was tested to predict the spread of COVID-19. The tested deep learning approach consists of multilayer BiLSTM. In order to train the model to predict daily COVID-19 cases in low-income countries, mobility trend data from Google, temperature, and relative humidity were used. The performance of the proposed multilayer BiLSTM is evaluated by comparing its RMSE with the one from multilayer LSTM (with the same settings as BiLSTM) in four developing countries namely Mozambique, Rwanda, Nepal, and Myanmar. The proposed multilayer BiLSTM outperformed the multilayer LSTM in all four countries. The proposed multilayer BiLSTM was also evaluated by comparing its root mean squared error (RMSE) with multilayer LSTM models, ARIMA- and stacked LSTM-based models in 8 countries, namely Italy, Turkey, Australia, Brazil, Canada, Egypt, Japan, and the UK. Finally, the proposed multilayer BiLSTM model was evaluated at the city level by comparing its average relative error (ARE) with the other four models, namely the LSTM-based model considering multilayer architecture, Google Cloud Forecasting, the LSTM-based model with mobility data only, and the LSTM-based model with mobility, temperature, and relative humidity data for 7 periods (of 28 days each) in six highly populated regions in Japan, namely Tokyo, Aichi, Osaka, Hyogo, Kyoto, and Fukuoka. The proposed multilayer BiLSTM model outperformed the multilayer LSTM model and other previous models by up to 1.6 and 0.6 times in terms of RMSE and ARE, respectively. Therefore, the proposed model enables more accurate forecasting of COVID-19 cases. This can support governments and health authorities in their decisions, mainly in developing countries with limited resources.

In addition to understanding the disease spread dynamics, rapid implementation of control measures is critical in the case of a post-disaster outbreak. This is crucial to stopping the spread of the disease. However, its implementation is based on informed decisions. Therefore, in order to support the decision-makers, a data-driven approach for estimating spatio-temporal exposure risk of locations using mobile phone data was tested. The approach used anonymized CDR from one of the biggest mobile network operators in Mozambique to estimate the daily origin-destination (OD) matrices. The daily OD matrices are estimated at province level since the available daily COVID-19 cases (validation data) are at that level. COVID-19 was used as a proxy of a post-disaster disease due to the unavailability of daily real-world data of a disease following a natural disaster in Mozambique. The estimated daily OD matrices are then used to construct the daily directed-weighted networks, in which the nodes represent provinces and the edges, the people flowing between each pair of provinces. Then, three centrality measures, namely weighted in-degree centrality, improved in-degree centrality, and weighted PageRank were used to estimate the daily exposure risk of each province. The results were evaluated by computing the Spearman’s rank correlation between risk score estimated using the daily COVID-19 reported cases and the exposure risk estimated using the three measures. The comparison results revealed that the overall weighted PageRank algorithm is the best measure at estimating exposure risk compared to the other two measures. Accordingly, three Poisson regression models were implemented to model the relationship between the COVID-19 cases in each province and the corresponding exposure risk estimated using the three centrality measures. The results showed that the coefficients of the models estimated using the maximum likelihood method are statistically significant (p-value <0.05). This means that the exposure risk does in fact influence the number of COVID-19 cases. Since the sign of the coefficients of the models is positive, we conclude that the number of COVID-19 cases in each province increases with an increase in the spatial exposure risk. The analysis was also conducted at district level, i.e., in Greater Maputo Area (GMA), which is located in the southern part of Mozambique and consists of all Maputo city districts (except Kanyaka), Matola city, Matola-Rio, Boane, and Marracuene districts. However, due to the unavailability of daily COVID-19 cases at district level, the evaluation was done by comparing the daily exposure risk estimated using the three centrality measures and the distribution of different types of points of interest, namely commercial, education, financial, government, healthcare, public, sport, and transport. The results revealed a good Spearman’s rank correlation between education, financial, and transport related points of interest and the three centrality measures. Government related points of interest presented the lowest correlation results compared to the three centrality measures. The remainder of points of interest showed medium-low to medium-high Spearman’s correlation coefficient compared to the three centrality measures. Therefore, anonymized CDR in conjunction with weighted PageRank algorithm can help decision-makers estimate the exposure risk in case of an outbreak and hence reduce the impact of a disease on human lives by imposing several informed interventions to contain and delay its spread. 

Natural disasters result in devastating losses in human life, environmental assets, and personal-, regional-, and national economies. The availability of different big data such as satellite images, Global Positioning System (GPS)traces, mobile Call Detail Records (CDR), social media posts, etc., in conjunction with advances in data analytic techniques (e.g., data mining and big data processing, machine learning and deep learning) can facilitate the extraction of geospatial information that is critical for rapid and effective disaster response. However, disaster response system development usually requires the integration of data from different sources (streaming data sources and data sources at rest) with different characteristics and types, which consequently have different processing needs. Deciding which processing framework to use for specific big data to perform a given task is usually a challenge for researchers from the disaster management field. While many things can be accomplished with population and movement data, for disaster management key, and arguably most important task is to analyze the displacement of the population during and after a disaster. Therefore, in this Licentiate, the knowledge and framework resulting from a literature review were used to select tools, and processing strategies to perform population displacement analysis after a disaster. This is a use case of the framework as well as an illustration of the value and challenges (e.g., gaps in data due to power outages) of using CDR data analysis to support disaster management.

Using CDR data, the displaced population was inferred by analyzing the variation of home cell-tower for each anonymized mobile phone subscriber before and after a disaster. The effectiveness of the proposed method is evaluated using remote sensing-based building damage assessment data and Displacement Tracking Matrix (DTM) from individuals’ survey responses at shelters after a severe cyclone in Beira city, central Mozambique, in March 2019.

The results show an encouraging correlation coefficient (over 70%) between the number of arrivals in each neighborhood estimated using CDR data and from DTM. In addition to this, CDR-based analysis derives the spatial distribution of displaced populations with high coverage of people, i.e., including not only people in shelters but everyone who used a mobile phone before and after a disaster. Moreover, results suggest that if CDR data are available after a disaster, population displacement can be estimated and this information can be used for response activities and for example to contribute to reducing waterborne diseases (e.g., diarrheal disease) and diseases associated with crowding (e.g., acute respiratory infections) in shelters and host communities.

Spread prediction models are vital tools to help health authorities and governments fight against infectious diseases such as COVID-19. The availability of historical daily COVID-19 cases, in conjunction with other datasets such as temperature and humidity (which are believed to play a key role in the spread of the disease), has opened a window for researchers to investigate the potential of different techniques to model and thereby expand our understanding of the factors (e.g., interaction or exposure resulting from mobility) that govern the underlying dynamics of the spread. Traditionally, infectious diseases are modeled using compartmental models such as the SIR model. However, this model shortcoming is that it does not account for mobility, and the resulting mixing or interactions, which we conjecture are a key factor in the dynamics of the spread. Statistical analysis and deep learning-based approaches such as autoregressive integrated moving average (ARIMA), gated recurrent units, variational autoencoder, long short-term memory (LSTM), convolution LSTM, stacked LSTM, and bidirectional LSTM have been tested with COVID-19 historical data to predict the disease spread mainly in medium- and high-income countries with good COVID-19 testing capabilities. However, few studies have focused on low-income countries with low access to COVID-19 testing and, hence, highly biased historical datasets. In addition to this, the arguable best model (BiLSTM) has not been tested with an arguably good set of features (people mobility data, temperature, and relative humidity). Therefore, in thisstudy, the multi-layer BiLSTM model is tested with mobility trend data from Google, temperature, and relative humidity to predict daily COVID-19 cases in low-income countries. The performance of the proposed multi-layer BiLSTM is evaluated by comparing its RMSE with the one from multi-layer LSTM (with the same settings as BiLSTM) in four developing countries namely Mozambique, Rwanda, Nepal, and Myanmar. The proposed multi-layer BiLSTM outperformed the multilayer LSTM in all four countries. The proposed multi-layer BiLSTM was also evaluated by comparing its root mean-squared error (RMSE) with multi-layer LSTM models, ARIMA- and stacked LSTM-based models in eight countries, namely Italy, Turkey, Australia, Brazil, Canada, Egypt, Japan, and the UK. Finally, the proposed multi-layer BiLSTM model was evaluated at the city level by comparing its average relative error with the other four models, namely the LSTM-based model considering multi-layer architecture, Google Cloud Forecasting, the LSTM-based model with mobility data only, and the LSTM-based model with mobility, temperature, and relative humidity data for 7 periods (of 28 days each) in six highly populated regions in Japan, namely Tokyo, Aichi, Osaka, Hyogo, Kyoto, and Fukuoka. The proposed multi-layer BiLSTM model outperformed the multi-layer LSTM model and other previous models by up to 1.6 and 0.6 times in terms of RMSE and ARE, respectively.Therefore, the proposed model enables more accurate forecasting of COVID-19 cases and can support governments and health authorities in their decisions, mainly in developing countries with limited resources.

Natural hazards result in devastating losses in human life, environmental assets and personal, and regional and national economies. The availability of different big data such as satellite imageries, Global Positioning System (GPS) traces, mobile Call Detail Records (CDRs), social media posts, etc., in conjunction with advances in data analytic techniques (e.g., data mining and big data processing, machine learning and deep learning) can facilitate the extraction of geospatial information that is critical for rapid and effective disaster response. However, disaster response systems development usually requires the integration of data from different sources (streaming data sources and data sources at rest) with different characteristics and types, which consequently have different processing needs. Deciding which processing framework to use for a specific big data to perform a given task is usually a challenge for researchers from the disaster management field. Therefore, this paper contributes in four aspects. Firstly, potential big data sources are described and characterized. Secondly, the big data processing frameworks are characterized and grouped based on the sources of data they handle. Then, a short description of each big data processing framework is provided and a comparison of processing frameworks in each group is carried out considering the main aspects such as computing cluster architecture, data flow, data processing model, fault-tolerance, scalability, latency, back-pressure mechanism, programming languages, and support for machine learning libraries, which are related to specific processing needs. Finally, a link between big data and processing frameworks is established, based on the processing provisioning for essential tasks in the response phase of disaster management.

Under normal circumstances, people's homes and work locations are given by their addresses, and this information is used to create a disaster management plan in which there are instructions to individuals on how to evacuate. However, when a disaster strikes, some shelters are destroyed, or in some cases, distance from affected areas to the closest shelter is not reasonable, or people have no possibility to act rationally as a natural response to physical danger, and hence, the evacuation plan is not followed. In each of these situations, people tend to find alternative places to stay, and the evacuees in shelters do not represent the total number of the displaced population. Knowing the spatial distribution of total displaced people (including people in shelters and other places) is very important for the success of the response activities which, among other measures, aims to provide for the basic humanitarian needs of affected people. Traditional methods of people displacement estimation are based on population surveys in the shelters. However, conducting a survey is infeasible to perform at scale and provides low coverage, i.e., can only cover the numbers for the population that are at the shelters, and the information cannot be delivered in a timely fashion. Therefore, in this research, anonymized mobile Call Detail Records (CDRs) are proposed as a source of information to infer the spatial distribution of the displaced population by analyzing the variation of home cell-tower for each anonymized mobile phone subscriber before and after a disaster. The effectiveness of the proposed method is evaluated using remote-sensing-based building damage assessment data and Displacement Tracking Matrix (DTM) from an individual's questionnaire survey conducted after a severe cyclone in Beira city, central Mozambique, in March 2019. The results show an encouraging correlation coefficient (over 70%) between the number of arrivals in each neighborhood estimated using CDRs and from DTM. In addition to this, CDRs derive spatial distribution of displaced populations with high coverage of people, i.e., including not only people in the shelter but everyone who used a mobile phone before and after the disaster. Moreover, results suggest that if CDRs data are available right after a disaster, population displacement can be estimated, and this information can be used for response activities and hence contribute to reducing waterborne diseases (e.g., diarrheal disease) and diseases associated with crowding (e.g., acute respiratory infections) in shelters and host communities.

Spatio-temporal exposure risk to an infectious disease is vital information for helping decision-makers fighting against an outbreak or spread, e.g., COVID-19. In order to estimate the spatio-temporal exposure risk, mobility data in conjunction with social network analysis have been used. However, existing studies have been using data with a narrow range of covered users to estimate the flow between locations, which in turn is used to estimate the exposure risk. In addition to this, none of the existing studies have explicitly used the risk score estimated using real-world data to validate the exposure risk from social network analysis. Moreover, there are no studies that have investigated the relationship between the exposure risk estimated using mobility data and the distribution of Points of Interest (PoI). Therefore, in this study, over 240 million anonymized Call Detail Records (CDRs) from one of the biggest Mobile Network Operator in Mozambique are used to estimate the daily origin-destination (OD) matrices. The daily OD matrices are estimated at province level since the available COVID-19 validation data is at that level. The estimated daily OD matrices are then used to construct the daily directed-weighted networks, in which the nodes represent provinces and the edges indicate the people flowing between each pair of provinces. Then, three centrality measures, namely weighted in-degree centrality, improved in-degree centrality, and weighted PageRank, were used to estimate the spatio-temporal exposure risk at province level. The results were evaluated by computing the Spearman's rank correlation between risk score estimated using the daily COVID-19 reported cases and the exposure risk estimated using the three measures. The comparison results revealed that, in general, the weighted PageRank algorithm is the best measure at estimating exposure risk compared to the other two measures. Accordingly, three Poisson regression models were implemented to model the relationship between the COVID-19 cases in each province and the corresponding exposure risk estimated using the three centrality measures. The results showed that the coefficients of the models estimated using the maximum likelihood method are statistically significant (p-value \textless 0.05). This means that the exposure risk does in fact influence the number of COVID-19 cases. Since the sign of the coefficients of the models is positive, we conclude that the number of COVID-19 cases in each province increases with increasing of the spatial exposure risk. The analysis was also  conducted at district level, i.e., in Greater Maputo Area, which is located in south part of Mozambique and consists of all Maputo city districts (except Kanyaka), Matola city, Matola-Rio, Boane, and Marracuene districts. However, due to the unavailability of daily COVID-19 cases at district level, the validation was done by comparing the daily exposure risk estimated using the three centrality measures and the distribution of different types of PoI, namely commercial, education, financial, government, healthcare, public, sport, and transport. The results revealed good Spearman's rank correlation between education, financial, and transport related PoI and the three centrality measures. Government related PoI presented the lowest correlation results compared to the three centrality measures. The remainder of PoI showed medium-low to medium-high correlation coefficient compared to the three centrality measures. In order to capture the differences, average Spearnman's rank correlation between the centrality measures and PoI was computed. Weighted pagerank outperformed the other two centrality measures in most of PoI classes, namely education, healthcare, public, sport, and transport. Weighted pagerank was only outperformed by improved in-degree centrality measure in one PoI class (commercial). Although with small differences, overall weighted pagerank revealed to be a good algorithm to estimate the spatio-temporal exposure risk for COVID-19. Therefore, anonymized CDRs in conjunction with weighted pagerank algorithm can help decision-makers estimate the spatio-temporal exposure risk in case of an outbreak and hence reduce the impact of a disease on human lives by imposing several informed interventions to contain and delay its spread.

City-scale traffic prediction is an important task for public safety, traffic management, and deployment of intelligent transportation systems. Many approaches have been proposed to address traffic prediction task using machine learning techniques. In this paper, we present a framework to help on addressing the task at hand (density-, traffic flow- and origin-destination flow predictions) considering data type, features, deep learning techniques such as Convolutional Neural Networks (CNNs), e.g., Autoencoder, Recurrent Neural Networks (RNNs), e.g., Long Short Term Memory (LSTM), and Graph Convolutional Networks (GCNs). An autoencoder model is designed in this paper to predict traffic density based on historical data. Experiments on real-world taxi order data demonstrate the effectiveness of the model.