To better understand current trends of urban population growth in Sub-Saharan Africa, high-quality spatiotemporal population estimates are necessary. While the joint use of remote sensing and deep learning has achieved promising results for population distribution estimation, most of the current work focuses on fine-scale spatial predictions derived from single date census, thereby neglecting temporal analyses. In this work, we focus on evaluating how deep learning change detection techniques can unravel temporal population dynamics at short intervals. Since Post-Classification Comparison (PCC) methods for change detection are known to propagate the error of the individual maps, we propose an end-to-end population growth mapping method. Specifically, a ResNet encoder, pretrained on a population mapping task with Sentinel-2 MSI data, was incorporated into a Siamese network. The Siamese network was trained at the census level to accurately predict population change. The effectiveness of the proposed method is demonstrated in Kigali, Rwanda, for the time period 2016-2020, using bi-temporal Sentinel-2 data. Compared to PCC, the Siamese network greatly reduced errors in population change predictions at the census level. These results show promise for future remote sensing-based population growth mapping endeavors. Code is available on GitHub.

Natural hazards, such as flooding, have been negatively impacting developed and emerging economies alike. The effects of floods are more prominent in countries of the Global South, where large parts of the population and infrastructure are insufficiently protected from natural hazards. From this scope, a lot of effort is required to mitigate these impacts by continuously providing new and more reliable tools to aid in mitigation and preparedness, during or after a flood event. Flood mapping followed by damage assessment plays an important role in all these stages. In this work we investigate a new dataset provided by DrivenData Labs based on Sentinel-1 (S1) imagery (VH, VV imagery and labels) to help map floods in the city of Beira in Mozambique. Exploiting Google Earth Engine (GEE), we deployed supervised and unsupervised machine learning (ML) methods on a dataset comprising imagery from 13 countries worldwide. We first mapped the floods country-by-country including Mozambique. This first part was helpful to understand the sensitivity of each method when applied to data from different regions and with different polarizations. We then trained the supervised model globally (in all 13 countries) and used it to predict floods in Beira. To assess the accuracy of the experiments we used the intersection over the union (IoU) metric, results of which we compared with the benchmark IoU achieved by the winner in the DrivenData competition for flood mapping in 2021. The implementation of unsupervised and supervised ML using VH and VV+VH produced satisfactory results, and showed to be better than using VV imagery; in Cambodia and Bolivia with VH polarization yielded IoUs values ranging from 0.819 to 0.856 which is above the benchmark (0.8094). The predictions in Beira using VH imagery yielded IoU of 0.568, which is a reasonable outcome. The proposed approach is a reliable alternative for flood mapping, especially in Mozambique due to its low cost and time effectiveness as even with unsupervised approaches, relatively high-quality results are yielded in near real-time. Finally, we used Sentinel-2 (S2) imagery for a land cover classification to perform damage assessment in Beira and integrated population data from Beira to enhance the quality the results. The results show that 20% of agricultural area and about 10% of built up area were flooded. Flooded built up area includes highly populated neighborhoods such as Chaimite and Ponta Gea that are located in the center of the city.

Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low-and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end -to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data.

The aim of this paper is to present developments of an advanced geospatial analytics algorithm that improves the prediction power of a random forest regression model while addressing the issue of spatial dependence commonly found in geographical data. We applied the methodology to a simple model of mean household income in the European Union regions to allow easy understanding and reproducibility of the analysis. The results are encouraging and suggest an improvement in the prediction power compared to previous techniques. The algorithm has been implemented in R and is available in the updated version of the SpatialML package in the CRAN repository.

Some studies have established relationships between neighborhood conditions and health. However, they neither evaluate the relative importance of neighborhood components in increasing obesity nor, more crucially, how these neighborhood factors vary geographically. We use the geographical random forest to analyze each factor's spatial variation and contribution to explaining tract-level obesity prevalence in Chicago, Illinois, United States. According to our findings, the geographical random forest outperforms the typically used nonspatial random forest model in terms of the out-of-bag prediction accuracy. In the Chicago tracts, poverty is the most important factor, whereas biking is the least important. Crime is the most critical factor in explaining obesity prevalence in Chicago's south suburbs while poverty appears to be the most important predictor in the city's south. For policy planning and evidence-based decision-making, our results suggest that social and ecological patterns of neighborhood characteristics are associated with obesity prevalence. Consequently, interventions should be devised and implemented based on local circumstances rather than generic notions of prevention strategies and healthcare barriers that apply to Chicago.

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.

Urbanization processes are manifested by the change in the physical morphology of cities. Gaining knowledge about cities through their morphology is naturally linked to the capability of remote sensing (RS) that can monitor city forms with a synoptic view. Yet, our knowledge of the urban form does not linearly increase with the increase of image data. Thus, the role, challenges and potentials of RS in deriving knowledge about urban morphology are worth investigating. We argue that ongoing efforts of mapping urban elements in RS are only marginally contributing to the understanding of cities in terms of urban morphology. We further reason that magnifying the role of RS depends on a suggested workflow involving steps that are external to RS, mainly including characterizing urban morphology through meaningful measurements of mapped elements, and interpreting the measured physical forms as proxies of the socioeconomic status. To exemplify the major steps, we focus on urban poverty (deprivation), and examine its manifestation through the morphology of buildings. Our findings show that challenges appear as soon as the collection of building information from RS images starts. This is mainly caused by inconsistent, incomplete and inaccurate GIS based representation of buildings on images, as well as low quality predictions, hidden from accuracy metrics. Although the potential of deriving meaningful urban morphological patterns from building maps for explaining socioeconomic patterns still holds, several uncertainties remain unsolved, such as the way urban processes are manifested morphologically and how the morphology is captured with the influence of building map quality. Our main conclusion is that as RS imagebased morphological information propagates and fluctuates along the process of knowledge derivation, causing difficulties in quantifying the exact amount of urban knowledge derived. Nonetheless, useful knowledge could already be obtained even with suboptimal data sources and model performances, which opens the opportunity to facilitate transferable and reproducible urban morphology studies by using widely accessible data despite their suboptimal quality.

Remote sensing has been used for decades to produce vector-borne disease risk maps aiming at better targeting control interventions. However, the coarse and climatic-driven nature of these maps largely hampered their use in the fight against malaria in highly heterogeneous African cities. Remote sensing now offers a large panel of data with the potential to greatly improve and refine malaria risk maps at the intra-urban scale. This research aims at testing the ability of different geospatial datasets exclusively derived from satellite sensors to predict malaria risk in two sub-Saharan African cities: Kampala (Uganda) and Dar es Salaam (Tanzania). Using random forest models, we predicted intra-urban malaria risk based on environmental and socioeconomic predictors using climatic, land cover and land use variables among others. The combination of these factors derived from different remote sensors showed the highest predictive power, particularly models including climatic, land cover and land use predictors. However, the predictive power remained quite low, which is suspected to be due to urban malaria complexity and malaria data limitations. While huge improvements have been made over the last decades in terms of remote sensing data acquisition and processing, the quantity and quality of epidemiological data are not yet sufficient to take full advantage of these improvements.

In the past two decades, Earth observation (EO) data have been utilized for studying the spatial patterns of urban deprivation. Given the scope of many existing studies, it is still unclear how very-high-resolution EO data can help to improve our understanding of the multidimensionality of deprivation within settlements on a city-wide scale. In this work, we assumed that multiple facets of deprivation are reflected by varying morphological structures within deprived urban areas and can be captured by EO information. We set out by staying on the scale of an entire city, while zooming into each of the deprived areas to investigate deprivation through land cover (LC) variations. To test the generalizability of our workflow, we assembled multiple WorldView-3 datasets (multispectral and shortwave infrared) with varying numbers of bands and image features, allowing us to explore computational efficiency, complexity, and scalability while keeping the model architecture consistent. Our workflow was implemented in the city of Nairobi, Kenya, where more than sixty percent of the city population lives in deprived areas. Our results indicate that detailed LC information that characterizes deprivation can be mapped with an accuracy of over seventy percent by only using RGB-based image features. Including the near-infrared (NIR) band appears to bring significant improvements in the accuracy of all classes. Equally important, we were able to categorize deprived areas into varying profiles manifested through LC variability using a gridded mapping approach. The types of deprivation profiles varied significantly both within and between deprived areas. The results could be informative for practical interventions such as land-use planning policies for urban upgrading programs.

Routine and accurate data on deprivation are needed for urban planning and decision support at various scales (i.e., from community to international). However, analyzing information requirements of diverse users on urban deprivation, we found that data are often not available or inaccessible. To bridge this data gap, Earth Observation (EO) data can support access to frequently updated spatial information. However, a user-centered approach is urgently required for the production of EO-based mapping products. Combining an online survey and several forms of user interactions, we defined five system specifications (derived from user requirements) for designing an open-access spatial information system for deprived urban areas. First, gridded maps represent the optimal spatial granularity to deal with high uncertainties of boundaries of deprived areas and to protect privacy. Second, a high temporal granularity of 1-2 years is important to respond to the high spatial dynamics of urban areas. Third, detailed local-scale information should be part of a city-to-global information system. Fourth, both aspects, community assets and risks, need to be part of an information system, and such data need to be combined with local community-based information. Fifth, in particular, civil society and government users should have fair access to data that bridges the digital barriers. A data ecosystem on urban deprivation meeting these requirements will be able to support community-level action for improving living conditions in deprived areas, local science-based policymaking, and tracking progress towards global targets such as the SDGs.