Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Morphometric and Landscape Feature Analysis with Artificial Neural Networks and SRTM data: Applications in Humid and Arid Environments
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Environmental and Natural Resources Information System.
2008 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

This thesis presents a semi-automatic method to analyze morphometric features and landscape elements based on Self Organizing Map (SOM) as an unsupervised Artificial Neural Network algorithm in two completely different environments: 1) the Man and Biosphere Reserve “Eastern Carpathians” (Central Europe) as a complex mountainous humid area and 2) Lut Desert, Iran, a hyper arid region characterized by repetition of wind-eroded features.

In 2003, the National Aeronautics and Space Administration (NASA) released the SRTM/ SIR-C band data with 3 arc seconds (approx. 90 m resolution) grid for approximately 80 % of Earth’s land surface. The X-band SRTM data were processed with a 1 arc second (approx. 30 m resolution) grid by the German space agency, DLR and the Italian space agency ASI, but due to the smaller X-SAR ground swath, large areas are not covered. The latest version 3.0 SRTM/C DEM and SRTM/X band DEM were re-projected to 90 and 30 m UTM grid and used to generate morphometric parameters of first order (slope) and second order (cross-sectional curvature, maximum curvatures and minimum curvature) by using a bivariate quadratic surface. The morphometric parameters are then used in a SOM to identify morphometric features (or landform elements) e.g. planar, channel, ridge in mountainous areas or yardangs (ridge) and corridors (valley) in hyper-arid areas.

Geomorphic phenomena and features are scale-dependent and the characteristics of features vary when measured over different spatial extents or different spatial resolution. Morphometric parameters were derived for nine window sizes of the 90 m DEM ranging from 5 × 5 to 55 ×55. Analysis of the SOM output represents landform entities with ground areas from 450 m to 4950 m that is local to regional scale features. Effect of two SRTM resolutions, C and X bands is studied on morphometric feature identification. The difference change analysis revealed the quantity of resolution dependency of morphometric features. Increasing the DEM spatial resolution from 90 to 30 m (corresponding to X band) by interpolation resulted in a significant improvement of terrain derivatives and morphometric feature identification.

Integration of morphometric parameters with climate data (e.g. Sum of active temperature above 10 ° C) in SOM resulted in delineation of morphologically homogenous discrete geo-ecological units. These units were reclassified to produce a Potential Natural Vegetation map. Finally, we combined morphometric parameters and remotely sensed spectral data from Landsat ETM+ to identify and characterize landscape elements. The single integrated data set of geo-ecosystems shows the spatial distribution of geomorphic, climatic and biotic/cultural properties in the Eastern Carpathians.

The results demonstrate that a SOM is a very efficient tool to analyze geo-morphometric features under diverse environmental conditions and at different scales and resolution. Finer resolution and decreasing window size reveals information that is more detailed while increasing window size and coarser resolution emphasizes more regional patterns. It was also successfully applied to integrate climatic, morphometric parameters and Landsat ETM+ data for landscape analysis. Despite the stochastic nature of SOM, the results are not sensitive to randomization of initial weight vectors if many iterations are used. This procedure is reproducible with consistent results.

Abstract [sv]

Avhandlingen presenterar en halvautomatisk metod för att analysera morfometriska kännetecken och landskapselement som bygger på Self Organizing Map (SOM), en oövervakad Artificiell Neural Nätverk algoritm, i två helt skilda miljöer: 1) Man and Biosphere Reserve "Eastern Carpathians" (Centraleuropa) som är ett komplext, bergigt och humid område och 2) Lut öken, Iran, en extrem torr region som kännetecknas av återkommande vinderoderade objekt.

Basen för undersökningen är det C-band SRTM digital höjd modell (DEM) med 3 bågsekunder rutnät som National Aeronautics and Space Administration släppte 2003 för ungefär 80 % av jordens yta. Dessutom används i ett mindre område X-band SRTM DEM med 1 bågsekund rutnät av den tyska rymdagenturen DLR. DEM transformerades till 90 och 30 m UTM nätet och därav genererades morfometriska parametrar av första (lutning) och andra ordning (tvärsnittböjning, största och minsta böjning). De morfometriska parametrar används sedan i en SOM för att identifiera morfometriska objekt (eller landform element) t.ex. plan yta, kanal, kam i bergsområden eller yardangs (kam) och korridorer (dalgångar) i extrem torra områden.

Geomorfiska fenomen och objekt är skalberoende och kännetecken varierar med geografiska områden och upplösning. Morfometriska parametrar har härletts från 90 m DEM för nio fönsterstorlekar från 5 × 5 till 55 × 55. Resultaten representerar landform enheter för områden från 450 m till 4950 m på marken dvs. lokal till regional skala. Inflytande av två SRTM upplösningar i C och X-banden har studerats för identifikation av morfometriska objekt. Förändringsanalys visade storleken av upplösningsberoende av morfometriska objekt. Ökning av DEM upplösningen från 90 till 30 m (motsvarande X-bandet) genom interpolation resulterade i en betydande förbättring av terräng parametrar och identifiering av morfometriska objekt.

Integration av morfometriska parametrar med klimatdata (t.ex. summan av aktiv temperatur över 10° C) i SOM resulterade i avgränsningen av homogena geoekologiska enheter. Dessa enheter ha används för att producera en karta av potentiell naturlig vegetation. Slutligen har vi kombinerat morfometriska parametrar och multispektrala fjärranalysdata från Landsat ETM för att identifiera och karaktärisera landskapselement. Dessa integrerade ekosystem data visar den geografiska fördelningen av morfometriska, klimatologiska och biotiska/kulturella egenskaper i östra Karpaterna.

Resultaten visar att SOM är ett mycket effektivt verktyg för att analysera geomorfometriska egenskaper under skilda miljöförhållanden, i olika skalor och upplösningar. Finare upplösning och minskad fönsterstorlek visar information som är mer detaljerad. Ökad fönsterstorlek och grövre upplösning betonar mer regionala mönster. Det var också mycket framgångsrikt att integrera klimatiska och morfometriska parametrar med Landsat ETM data för landskapsanalys. Trots den stokastiska natur av SOM, är resultaten inte känsliga för slumpvisa värden i de ursprungliga viktvektorerna när många iterationer används. Detta förfarande är reproducerbart med bestående resultat.

Place, publisher, year, edition, pages
Stockholm: KTH , 2008. , viii, 71 p.
Keyword [en]
Self Organizing Map, Neural Network, Morphometric Feature, Landscape, Yardang, Lut Desert, Potential natural vegetation, geoecosystem, Landform, Landsat ETM+, Morphometric Parameters, SRTM, Resolution, Curvatures, DEM.
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-4789ISBN: 978-91-7415-010-0 (print)OAI: oai:DiVA.org:kth-4789DiVA: diva2:13966
Public defence
2008-06-11, F3, Lindstedsvägen 26, 13:15
Opponent
Supervisors
Note
QC 20100924Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2011-09-01Bibliographically approved
List of papers
1. Geomorphometric feature analysis using morphometric parameterization and artificial neural networks
Open this publication in new window or tab >>Geomorphometric feature analysis using morphometric parameterization and artificial neural networks
2008 (English)In: Geomorphology, ISSN 0169-555X, Vol. 99, no 1-4, 1-12 p.Article in journal (Refereed) Published
Abstract [en]

This paper presents a semi-automatic method using an unsupervised neural network to analyze geomorphometric features as landform elements. The Shuttle Radar Topography Mission (SRTM) provided detailed digital elevation models (DEMs) for all land masses between 60 degrees N and 57 degrees S. Exploiting these data for recognition and extraction of geomorphometric features is a challenging task. Results obtained with two methods, Wood's morphometric parameterization and the Self Organizing Map (SOM), are presented in this paper.

Four morphometric parameters (slope, minimum curvature, maximum curvature and cross-sectional curvature) were derived by fitting a bivariate quadratic surface with a window size of 5 by 5 to the SRTM DEM. These parameters were then used as input to the two methods. Wood's morphometric parameterization provides point-based features (peak, pit and pass), line-based features (channel and ridge) and area-based features (planar). Since point-based features are defined as having a very small slope when their neighbors are considered, two tolerance values (slope tolerance and curvature tolerance) are introduced. Selection of suitable values for the tolerance parameters is crucial for obtaining useful results.

The SOM as an unsupervised neural network algorithm is employed for the classification of the same morphometric parameters into ten classes characterized by morphometric position (crest, channel, ridge and plan area) subdivided by slope ranges. These terrain features are generic landform element and can be used to improve mapping and modeling of soils, vegetation, and land use, as well as ecological, hydrological and geomorphological features. These landform elements are the smallest homogeneous divisions of the land surface at the given resolution. The result showed that the SOM is an efficient scalable tool for analyzing geomorphometric features as meaningful landform elements, and uses the, full potential of morphometric characteristics.

Keyword
Self Organizing Map; morphometric feature; neural network; landform
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8591 (URN)10.1016/j.geomorph.2007.10.002 (DOI)000257696000001 ()2-s2.0-44849093530 (Scopus ID)
Note
QC 20100727. Uppdaterad från in press till published (20100727).Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-27Bibliographically approved
2. A semi-automated method for analysis of landscape elements using shuttle radar topography mission and landsat ETM+data
Open this publication in new window or tab >>A semi-automated method for analysis of landscape elements using shuttle radar topography mission and landsat ETM+data
2009 (English)In: Computers & Geosciences, ISSN 0098-3004, E-ISSN 1873-7803, Vol. 35, no 2, 373-389 p.Article in journal (Refereed) Published
Abstract [en]

In this paper, we demonstrate artificial neural networks-self-organizing map (SOM)-as a semi-automatic method for extraction and analysis of landscape elements in the man and biosphere reserve "Eastern Carpathians". The Shuttle Radar Topography Mission (SRTM) collected data to produce generally available digital elevation models (DEM). Together with Landsat Thematic Mapper data, this provides a unique, consistent and nearly worldwide data set.

To integrate the DEM with Landsat data, it was re-projected from geographic coordinates to UTM with 28.5 m spatial resolution using cubic convolution interpolation. To provide quantitative morphometric parameters, first-order (slope) and second-order derivatives of the DEM-minimum curvature, maximum curvature and cross-sectional curvature-were calculated by fitting a bivariate quadratic surface with a window size of 9 x 9 pixels. These surface curvatures are strongly related to landform features and geomorphological processes.

Four morphometric parameters and seven Landsat-enhanced thematic mapper (ETM +) bands were used as input for the SOM algorithm. Once the network weights have been randomly initialized, different learning parameter sets, e.g. initial radius, final radius and number of iterations, were investigated. An optimal SOM with 20 classes using 1000 iterations and a final neighborhood radius of 0.05 provided a low average quantization error of 0.3394 and was used for further analysis. The effect of randomization of initial weights for optimal SOM was also studied. Feature space analysis, three-dimensional inspection and auxiliary data facilitated the assignment of semantic meaning to the output classes in terms of landfonn, based on morphometric analysis, and land use, based on spectral properties.

Results were displayed as thematic map of landscape elements according to form, cover and slope. Spectral and morphometric signature analysis with corresponding zoom samples superimposed by contour lines were compared in detail to clarify the role of morphometric parameters to separate landscape elements. The results revealed the efficiency of SOM to integrate SRTM and Landsat data in landscape analysis. Despite the stochastic nature of SOM, the results in this particular study are not sensitive to randomization of initial weight vectors if many iterations are used. This procedure is reproducible for the same application with consistent results.

Keyword
Self-organizing map, SRTM, Landscape, Neural network, ETM
National Category
Other Environmental Engineering
Identifiers
urn:nbn:se:kth:diva-7175 (URN)10.1016/j.cageo.2007.09.019 (DOI)000263398200019 ()2-s2.0-58349099655 (Scopus ID)
Note
Uppdaterad från submitted till published: 20101104. QC 20101104Available from: 2007-05-23 Created: 2007-05-23 Last updated: 2011-09-01Bibliographically approved
3. Application of Self Organizing Map and SRTM data to Characterize Yardangs in the Lut Desert, Iran
Open this publication in new window or tab >>Application of Self Organizing Map and SRTM data to Characterize Yardangs in the Lut Desert, Iran
2008 (English)In: Remote Sensing of Environment, ISSN 0034-4257, E-ISSN 1879-0704, Vol. 112, no 7, 3284-3294 p.Article in journal (Refereed) Published
Abstract [en]

Yardangs, an exclusive landform due to intensive wind erosion, cover a large area in the hyper-arid Lut desert of Iran. This paper presents a new approach using Self Organizing Map (SOM) as unsupervised algorithm of artificial neural networks for analysis and characterization of yardangs.

Nowadays, the Shuttle Radar Topography Mission (SRTM) with 3 arc sec data (approximately 90 m resolution) and nearly world wide coverage provides uniform good quality data.

The SRTM 3 arc sec data were re-projected to a 90 m UTM grid. Bivariate quadratic surfaces with moving window size of 5 x 5 were fitted to this DEM. The first derivative, slope steepness and the second derivatives minimum, maximum curvature and cross-sectional curvatures were calculated as geomorphometric parameters used as input to the SOMs. 42 SOMs with different learning parameter settings, e.g. initial and final radius, number of iterations, and the effect of random initial weights on average quantization error were investigated. A SOM with a low average quantization error (0.1040) was used for further analysis. Feature space analysis, morphometric signatures, three-dimensional inspection, auxiliary data like Landsat ETM+ and high resolution satellite imagery from QuickBird facilitated the assignment of semantic meaning to the output classes in terms of geomorphometric features. Results are provided in a geographic information system as thematic maps of landform entities based on form and slope, e.g. yardangs (ridge), corridors (valley) or planar areas.

The results showed that all yardangs and corridors were clearly recognized and classified by this method when their width was larger than the DEM resolution but became unrecognizable if their width is much smaller than the grid resolution. The identified yardangs and corridors are aligned NNW-SSE parallel to the prevailing direction of the strong local 120 days wind and cover about 31% and 42% of the study area respectively. The results demonstrate that SOM is a very efficient tool for analyzing aeolian landforms in hyper-arid environments that provides very useful information for terrain feature analysis in remote regions.

Keyword
Self Organizing Map; yardangs; SRTM; morphometric feature; neural network
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8593 (URN)10.1016/j.rse.2008.04.007 (DOI)000257600500007 ()2-s2.0-44649149517 (Scopus ID)
Note
QC 20100727. Uppdaterad från in press till published (20100727).Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-27Bibliographically approved
4. Self Organizing Maps for Multi-Scale Morphometric Feature Identification Using Shuttle Radar Topography Mission (SRTM) Data
Open this publication in new window or tab >>Self Organizing Maps for Multi-Scale Morphometric Feature Identification Using Shuttle Radar Topography Mission (SRTM) Data
2009 (English)In: Geocarto International, ISSN 1010-6049, Vol. 24, no 5, 335-355 p.Article in journal (Refereed) Published
Abstract [en]

This article presents a new procedure using artificial neural networks in the form of a self-organizing map (SOM), as a semi-automatic method for analysis and identification of morphometric features in the Man and Biosphere Reserve 'Eastern Carpathians' with nine spatial scales. The NASA Shuttle Radar Topography Mission (SRTM) has provided digital elevation models (DEM) for over 80% of the land surface on earth. The latest version 3.0 SRTM data provided by the Consultative Group for International Agricultural Research-Consortium for Spatial Information GeoPortal is the result of substantial editing effort on the SRTM digital elevation data produced by NASA. Easy availability of SRTM 3 arc second data has resulted in great advances in morphometric studies and numerical description of terrain surface features as shown by many literature references. The first derivative, slope steepness and second derivatives, minimum curvature, maximum curvature and cross-sectional curvature of elevation were derived by fitting bivariate quadratic surfaces with nine window sizes ranging from 5 to 55 cells to the processed SRTM DEM 90 m Version 3.0. These analyses represent landform entities with ground distances from 450 to 4950 m, which are local to regional features. The four morphometric parameters were used as input for the SOM algorithm. Forty-two SOMs with different learning parameter sets, e.g. initial radius, final radius and number of iterations were investigated. An optimal SOM with 10 classes based on 1000 iteration and a final neighbourhood radius of 0.01 provide a low average quantization error of 0.1780 and was used for further analysis. The effect of the random initial weights for optimal SOM was also studied. The results in this particular study are not sensitive to the randomization of initial weight vectors if many iterations are used. Feature space analysis, morphometric signatures, three-dimensional inspection and auxiliary data facilitated the assignment of semantic meaning to the output classes in terms of morphometric features. Results are provided as thematic maps of landform entities based on form and slopes. The result showed that a SOM is an efficient scalable tool for analysing geomorphometric features as meaningful landforms over different spatial extents, and uses the full potential of morphometric characteristics. This procedure is reproducible for the same application with consistent results.

Keyword
Landform; Morphometric feature; Multi-scale; Neural network; Self organizing map
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8594 (URN)10.1080/10106040802642577 (DOI)2-s2.0-70349567236 (Scopus ID)
Note
QC 20100727. Uppdaterad från submitted till published (20100727).Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-27Bibliographically approved
5. Effect of SRTM Resolution on Morphometric Feature Identification Using Neural Network-Self Organizing Map
Open this publication in new window or tab >>Effect of SRTM Resolution on Morphometric Feature Identification Using Neural Network-Self Organizing Map
2010 (English)In: Geoinformatica, ISSN 1384-6175, E-ISSN 1573-7624, Vol. 14, no 4, 405-424 p.Article in journal (Refereed) Published
Abstract [en]

In this study, we present a semi-automatic procedure using Neural Networks-Self Organizing Map-and Shuttle Radar Topography Mission DEMs to characterize morphometric features of the landscape in the Man and Biosphere Reserve "Eastern Carpathians". We investigate specially the effect of two resolutions, SIR-C with 3 arc seconds and X-SAR with 1 arc second for morphometric feature identification. Specifically we investigate how the SRTM/C band data with 30 m interpolated grid, corresponding to SRTM/X band 30 m, affect the morphometric characterization and topography derivatives. To reduce misregistration between the DEMs, spatial co-registration was performed and a RMSE of 0.48 pixel was achieved. Morphometric parameters such as slope, maximum curvature, minimum curvature and cross-sectional curvature are derived using a bivariate quadratic approximation on 90 m, 30 m and interpolated 30 m DEMs. Self Organizing Map (SOM) is used for the classification of morphometric parameters into ten exclusive and exhaustive classes. These classes were analyzed as morphometric features such as ridge, channel, crest line and planar for all data sets based on feature space (scatter plot), morphometric signatures and 3D inspection of the area. The map quality is analyzed by oblique views with contour lines overlaid. Using the X band DEM with 30 m grid as benchmark, a change detection technique was used to quantify differences in morphometric features and to assess the scale effect going from a 90 m (C-band) DEM to an interpolated 30 m DEM. The same procedure is used to study the effect of different resolutions on morphometric features. Morphometric parameters were computed by a moving window size 5 x 5 (corresponding to 450 m on the ground) over SRTM- 90 m. To cover the same ground area, a moving window size of 15 x 15 is used for the 30 m DEM. The change analysis showed the amount of resolution dependency of morphometric features. Overall, the results showed that the introduced method is very useful for identification of morphometric features based on SRTM resolution. Decreasing the grid size from 90 m to 30 m reveals considerably more detailed information emphasizing local conditions. Comparison between results from DEM-30 m as reference data set and interpolated 30 m, showed a rate of change of 31.5% which is negligible. About 17% of this rate correspond to classes with mean slope > 10A degrees. Of the morphometric parameters, the cross sectional curvature is most sensitive to DEM resolution. Increasing spatial resolution reduces the main constrains for morphometric analysis with SRTM 90 m data, such as unrealistic features and isolated single elements in the output map. So in case of lack of high resolution data, the SRTM 90 m data could be interpolated and used for further geomorphic analysis.

Keyword
Self organizing map, SRTM, Neural network, Morphometric features, Resolution
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8595 (URN)10.1007/s10707-009-0085-4 (DOI)000279082900001 ()2-s2.0-77954029474 (Scopus ID)
Note
QC 20100924. Uppdaterad från submitted till published (20100924).Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-09-24Bibliographically approved
6. Artificial Neural Networks for Landscape Analysis of the Biosphere Reserve “Eastern Carpathians” with Landsat ETM+ and SRTM data
Open this publication in new window or tab >>Artificial Neural Networks for Landscape Analysis of the Biosphere Reserve “Eastern Carpathians” with Landsat ETM+ and SRTM data
2008 (English)In: The Problems of Landscape Ecology, ISSN 1899-3850, Vol. 20, 171-183 p.Article in journal (Refereed) Published
Abstract [en]

In this paper we propose a semi-automatic method for landscape analysis with both spectral and morphometric constituents. SRTM data are used to calculate first derivatives (slope) and second derivatives of elevation such as minimum curvature, maximum curvatures and cross-sectional curvature by fitting a bivariate quadratic surface with a window size 9 by 9. Together with multi-spectral remote sensing data like Landsat 7 ETM+ with 28.5 meter raster elements, these data provide comprehensive information for the analysis of the landscape in the study area. Unsupervised neural network algorithm –Self Organizing map- divided all input vectors into inclusive and exhaustive classes on the basis of similarity between attribute vectors. Morphometric analysis, spectral signature analysis, feature space analysis are used to assign semantic meaning to the classes as landscape elements according to form, cover and slope e.g. deciduous forest on ridge (convex landform) with steep slopes.

Keyword
SRTM, Self Organizing Map, landform, morphometric parameter, ETM+
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8596 (URN)
Note
QC 20100728. Uppdaterad från in press till published (20100728).Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-28Bibliographically approved
7. Self Organizing Map: Application in Morphometric Feature Identification in Humid and Hyper Arid Environments
Open this publication in new window or tab >>Self Organizing Map: Application in Morphometric Feature Identification in Humid and Hyper Arid Environments
2008 (English)In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS)”, 6-11 July 2008, Boston, Massachusetts, U.S.A, 2008Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a robust new approach using artificial neural networks in the form of a Self Organizing Map (SOM) as a semi-automatic method for analysis and identification of morphometric features in two completely different environments, the Man and Biosphere Reserve “Eastern Carpathians” (Central Europe) in a complex mountainous humid area and Yardangs in Lut Desert, Iran, a hyper arid region characterized by homogeneous repetition of wind-eroded landforms.

 

The NASA Shuttle Radar Topography Mission (SRTM) has provided Digital Elevation Models (DEM) for over 80% of the land surface. Version 3.0 SRTM data provided by the CGIAR-CSI GeoPortal are the result of substantial editing effort on the SRTM DEM produced by NASA. Easy availability of SRTM 3 arc second data promoted great advances in morphometric studies and numerical description of terrain surface features as shown by many literature references. The goal of this study was to develop a new semi-automatic DEM-based method for geomorphometric feature recognition and to explore the potential and limitation of SRTM 90 meter data in such studies.

 

The 3 arc seconds data were re-projected to a 90 m UTM grid. Bivariate quadratic surfaces with moving window size of 5×5 were fitted to this DEM. The first derivative, slope steepness and the second derivatives minimum curvature, maximum curvature and cross-sectional curvature were calculated as geomorphometric parameters and were used as input to the SOMs. Different learning parameter setting, e.g. initial radius, final radius, number of iterations, and the effect of the random initial weights on average quantization error were investigated. A SOM with a low average quantization error was used for further analysis. Feature space analysis, morphometric signatures, three-dimensional inspection and auxiliary data facilitated the assignment of semantic meaning to the output classes in terms of geomorphometric features. Results are provided in a geographic information system as thematic maps of landform entities based on form and slope.

 

Geomorphometric features are scale-dependent and the resolution of the DEM limits the information, which can be derived. Mega-Yardangs, an aeolian landform due to intensive wind erosion, cover a large area in the hyper-arid Lut desert. They form elongated depressions and ridges with a width ranging from a few meters to hundreds of meters. These features can clearly be recognized and classified when their width is significantly larger than the DEM resolution but become unrecognizable if their width is less than the grid resolution.

 

Eastern Carpathians are characterized by elongated ridges and valleys. These ridges are dissected resulting in small patches of landforms like ridge with very steep slope, channels with moderate slopes and plains with gentle slope. These local landform patches are large enough to be recognized in morphometric parameters calculated with a 5×5 window, corresponding to 450 m on the ground. With much larger window sizes, these local features disappear and replaced by features describing regional

patterns and ridges. Therefore, size, shape and pattern of identified geomorphometric objects depend on the underlying DEM resolution and the selected window size.

 

The results demonstrate that a SOM is an efficient scalable tool for analyzing geo-morphometric features as meaningful landforms under diverse environmental conditions. This method provides additional information for geomorphologic and landscape analysis even in inaccessible regions and uses the full potential of morphometric characteristics.

Keyword
Self Organizing Map; Morphometric feature; Neural Network; Yardang; Desert
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8597 (URN)
Note
QC 20100728Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-28Bibliographically approved
8. Landforms identification using neural network self organizing map and SRTM data (Case study: Eastern Carpathians)
Open this publication in new window or tab >>Landforms identification using neural network self organizing map and SRTM data (Case study: Eastern Carpathians)
2007 (English)In: Image and Signal Processing for Remote Sensing XIII: Florence; 18 September 2007 through 20 September 2007 / [ed] Bruzzone, L., 2007, 67481H-1-67481H-12 p.Conference paper, Published paper (Refereed)
Abstract [en]

During an 11 days mission in February 2000 the Shuttle Radar Topography Mission (SRTM) collected data over 80% of the Earth's land surface, for all areas between 60 degrees N and 56 degrees S latitude. Since SRTM data became available, many studies utilized them for application in topography and morphometric landscape analysis. Exploiting SRTM data for recognition and extraction of topographic features is a challenging task and could provide useful information for landscape studies at different scales.

In this study the 3 arc second SRTM digital elevation model was projected on a UTM grid with 90 meter spacing for a mountainous terrain at the Polish - Ukrainian border. Terrain parameters (morphometric parameters) such as slope, maximum curvature, minimum curvature and cross-sectional curvature are derived by fitting a bivariate quadratic surface with a window size of 5x5 corresponding to 450 meters on the ground. These morphometric parameters are strongly related to topographic features and geomorphological processes. Such data allow us to enumerate topographic features in a way meaningful for landscape analysis.

Kohonen Self Organizing Map (SOM) as an unsupervised neural network algorithm is used for classification of these morphometric parameters into 10 classes representing landforms elements such as ridge, channel, crest line, planar and valley bottom. These classes were analyzed and interpreted based on spectral signature, feature space, and 3D presentations of the area. Texture contents were enhanced by separating the 10 classes into individual maps and applying occurrence filters with 9x9 window to each map. This procedure resulted in 10 new inputs to the SOM. Again SOM was trained and a map with four dominant landforms, mountains with steep slopes, plane areas with gentle slopes, dissected ridges and lower valleys with moderate to very steep slopes and main valleys with gentle to moderate slopes was produced. Both landform maps were evaluated by superimposing contour lines.

Results showed that Self Organizing Map is a very promising and efficient tool for such studies. There is a very good agreement between identified landforms and contour lines. This new procedure is encouraging and offers new possibilities in the study of both type of terrain features, general landforms and landform elements.

Series
Proceedings of SPIE - The International Society for Optical Engineering, ISSN 0277-786X ; 6748
Keyword
Landforms; Morphometric features; Neural network; Self organizing map; SRTM
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8598 (URN)10.1117/12.737949 (DOI)000253478400041 ()2-s2.0-42449146140 (Scopus ID)978-0-8194-6906-9 (ISBN)
Note
QC 20100728Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-28Bibliographically approved
9. Contribution of Landsat ETM+ thermal band to land cover classification using SMAP and ML algorithms (Case study; Eastern Carpathians)
Open this publication in new window or tab >>Contribution of Landsat ETM+ thermal band to land cover classification using SMAP and ML algorithms (Case study; Eastern Carpathians)
2007 (English)In: Image and Signal Processing for Remote Sensing XIII: Florence; 18 September 2007 through 20 September 2007 / [ed] Bruzzone, L., 2007, 67481F-1-67481F-12 p.Conference paper, Published paper (Refereed)
Abstract [en]

Landsat Thermal band measures the emitted radiation of the earth surface. In many studies the ETM+ thermal band with 60 meter resolution is excluded from processing and classification despite the valuable information content.

Two different methods of Bayesian segmentation algorithm were used with different band combinations. Sequential Maximum a Posteriori (SMAP) is a Bayesian image segmentation algorithm which unlike the traditional Maximum likelihood (ML) classification attempts to improve accuracy by taking contextual information into account, rather than classifying pixels separately.

Landsat 7 ETM+ data with Path/Row 186-26, dated 30 September 2000 were used. In order to study the role of thermal band with these methods, two data sets with and without the thermal band were used. Nine band combinations including ETM+ and Principal Component (PC) data were selected based on the highest value of Optimum Index Factor (OIF). Using visual and digital analysis, field observation data and auxiliary map data like CORINE land cover, 14 land cover classes are identified. Spectral signatures were derived for every land cover. Spectral signatures as well as feature space analysis were used for detailed analysis of efficiency of the reflective and thermal bands.

The result shows that SMAP as the superior method can improve Kappa values compared with ML algorithm for all band combinations with on average 17%. Using all 7 bands both SMAP and ML classifications algorithm achieved the highest Kappa accuracy of 80.37 % and 64.36 % respectively. Eliminating the thermal band decreased the Kappa values by about 8% for both algorithms. The band combination including PCI, 2, 3, and 4 (PCA calculated for all 7 bands) produced the same Kappa as bands 3, 4, 5 and 6. The Kappa value for band combination 3, 4, 5 and 6 was also about 4% higher than using 6 bands without the thermal band for both algorithms.

Contextual classification algorithm like SMAP can significantly improve classification results. The thermal band bears complementary information to other spectral bands and despite the lower spatial resolution improves classification accuracy.

Series
Proceedings of SPIE - The International Society for Optical Engineering, ISSN 0277-786X ; 6748
Keyword
SMAP; landsat ETM; thermal band; maximum likelihood
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8599 (URN)10.1117/12.737841 (DOI)000253478400040 ()2-s2.0-42449113779 (Scopus ID)978-0-8194-6906-9 (ISBN)
Note
QC 20100728Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-28Bibliographically approved
10. Comparison of multi-resolution SRTM data for morphometric features identification using neural network self-organizing map (case study: Eastern Carpathians)
Open this publication in new window or tab >>Comparison of multi-resolution SRTM data for morphometric features identification using neural network self-organizing map (case study: Eastern Carpathians)
2007 (English)In: Remote Sensing for Environmental Monitoring, GIS Applications, and Geology VII: Florence; 17 September 2007 through 20 September 2007 / [ed] Ehlers, M.; Michel, U., 2007, 67491J-1-67491J-12 p.Conference paper, Published paper (Refereed)
Abstract [en]

The Shuttle Radar Topography Mission (SRTM) was launched on 11 February 2000 and 3 arc second data were publicly released in July 2004. Easy availability of SRTM 3 arc second data, covering almost 80% of the land surface on earth, has resulted in great advances in morphometric studies and numerical description of landscape features.

In this study we introduce a new procedure using Neural Network - Self Organizing Map - to characterize morphometric features of landscapes.. We also investigate the effect of two resolutions for morphometric feature identification. Specifically we investigate how the SRTM 3arc second latitude / longitude data projected to UTM coordinates with 90 meter respectively 28.5 m grid, corresponding to Landsat TM data resolution, affect the morphometric characterization. Morphometric parameters such as slope, maximum curvature, minimum curvature and cross-sectional curvature are derived by fitting a bivariate quadratic surface with a window size of 5x5 for the 90 m data (450 m on the ground) and 9x9 for the 28.5 m data (about 250 m).

Kohonen Self Organizing Map as an unsupervised neural network algorithm is employed for the classification of these morphometric parameters into 10 exclusive and exhaustive classes. These classes were analyzed and interpreted as morphometric features such as ridge, channel, crest line, planar and valley bottom for both data sets based on morphometric signatures, feature space and 3D inspection of the area. The difference change detection technique was used between two DEMs (DEM-90 and DEM-28.5 m) to analyze differences in morphometric features identification.

The results showed that the introduced method is very useful for identification of morphometric features. Increasing spatial resolution from 90 meter to 28.5 meter, can produce digital elevation models (DEMs) allowing more precise identification of morphometric features and landforms. Increasing spatial resolution overcomes the main constrains for morphometric analysis with SRTM 90 m data, such as artifacts, unrealistic feature presentations and isolated single elements in the output map. Increased spatial resolution together with the smaller window size emphasized local conditions but main morphometric features were preserved. An overall change of 66.36 % is observed for morphometric features in the 28.5 meter DEM. The most and least frequent changes occurred for class no.6 (moderate slopes, channel) with 82.74% and class no.7 (Gentle slope to flat, valley bottom, planar) with 43.31 % respectively. Increasing spatial resolution can be applied also to watersheds studies like drainage modeling.

Series
Proceedings of SPIE - The International Society for Optical Engineering, ISSN 0277-786X ; 6749
Keyword
Self Organizing Map; SRTM; neural network; morphometric features
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-8600 (URN)10.1117/12.737857 (DOI)000252485700039 ()2-s2.0-40749113565 (Scopus ID)978-0-8194-6907-6 (ISBN)
Note
QC 20100728Available from: 2008-06-02 Created: 2008-06-02 Last updated: 2010-07-28Bibliographically approved

Open Access in DiVA

fulltext(6195 kB)4160 downloads
File information
File name FULLTEXT01.pdfFile size 6195 kBChecksum MD5
2bc2ce59943513e026060202cb249586796c8f88d2db6af27f9efdc35235af246b06332b
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Ehsani, Amir Houshang
By organisation
Environmental and Natural Resources Information System
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 4160 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1004 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf