Machine learning methods of remote sensing data processing for mapping salt pan crust dynamics in Sebkha de Ndrhamcha, Mauritania

• Autorzy: Lemenkova Polina

Identyfikatory

DOI

10.2478/arsa-2025-0003

• Języki publikacji: EN

Abstrakty

EN

The advances in Machine Learning (ML) and computer technologies enabled to process satellite images using programming. Environmental applications that handle Remote Sensing (RS) data for spatial analysis use such an approach, for example, Python’s library scikit-learn using algorithms on pattern identification, predictions or image classification. This paper presents an ML method of satellite image processing using Geographic Resources Analysis Support System (GRASS) Geographic Information System (GIS). The aim is to classify multispectral Landsat images using ML for identification of changes in salt pans of West Mauritania, Africa over the period 2014-2023. We define 10 classes of land cover categories and perform analysis of geological, lithological and landscape setting, and then introduce the principles, algorithms and processing of the ML methods of GRASS GIS. The following classification models were employed to implement image classification with training: Random Forest (RF), Decision Tree, Gradient Boosting and Support Vector Machine (SVM). The results were compared with clustering performed by k-means and maximum likelihood discriminant analysis. The cartographic visualisation and validation was implemented through accuracy analysis. Results for the best performing SVM model with seven-band input produced an overall accuracy of 76%, for the RF model - 73%, compared to 69% for Decision Tree Classifier - 69% and for Gradient Boosting Classifier - 67%. The SVM model embedded in GRASS GIS generates robust land cover maps with good accuracy from multispectral satellite images. The paper demonstrated an ML-based automated approach to satellite image processing, which links Artificial Intelligence (AI) with cartographic tasks.

Słowa kluczowe

EN

machine learning; Random Forest; Support Vector Machine; GRASS GIS; satellite image; remote sensing; saline lakes

• Wydawca: Centrum Badań Kosmicznych PAN ; De Gruyter
• Czasopismo: Artificial Satellites : Journal of Planetary Geodesy
• Rocznik: 2025
• Tom: Vol. 60, No. 2
• Strony: 37--69
• Opis fizyczny: Bibliogr. 89 poz., rys., tab.

Twórcy

autor

Lemenkova Polina

• Alma Mater Studiorum - Università di Bologna, Dipartimento di Scienze Biologiche, Geologiche ed Ambientali, Bologna, Emilia-Romagna, Italy

Bibliografia

• Abujayyab, S. K., Almajalid, R., Wazirali, R., Ahmad, R., Taşoğlu, E., Karas, I. R. and Hijazi, I. (2023). Integrating object-based and pixel-based segmentation for building footprint extraction from satellite images, Journal of King Saud University - Computer and Information Sciences 35(10): 101802.
• Ali, A. O., Morshedy, A. S., El-Zahhar, A. A., Alghamdi, M. M. and El Naggar, A. M. (2024). African continent: Rich land of minerals and energy sources, Inorganic Chemistry Communications 169: 113123.
• Ali, M. M. and Abd Ellah, R. G. (2023). Chapter 1 - history and formation of african lakes, in M. El-Sheekh and H. E. Elsaied (eds), Lakes of Africa, Elsevier, pp. 1-31.
• Ashpole, I. and Washington, R. (2013). A new high-resolution central and western saharan summertime dust source map from automated satellite dust plume tracking, Journal of Geophysical Research: Atmospheres 118(13): 6981-6995.
• Ayoade, O., Rivas, P., Orduz, J. and Rafi, N. (2023). Chapter 13 - satellite image classification using quantum machine learning, in Z. Sun, N. Cristea and P. Rivas (eds), Artificial Intelligence in Earth Science, Elsevier, pp. 337-355.
• Barry, S. (2003). Contribution à l’étude géomorphologique de la cote mauritanienne: cas de nouakchott et ses environs, DES en géographie, Université Cheikh Anta Diop de Dakar, Département de géographie, 116p.
• Bayod Rújula, A. A. and Dia, N. K. (2010). Application of a multi-criteria analysis for the selection of the most suitable energy source and water desalination system in mauritania, Energy Policy 38(1): 99-115.
• Belmahdi, F., Lazri, M., Ouallouche, F., Labadi, K., Absi, R. and Ameur, S. (2023). Application of dempster-shafer theory for optimization of precipitation classification and estimation results from remote sensing data using machine learning, Remote Sensing Applications: Society and Environment 29: 100906.
• Bojer, A. K., Woldetsadik, M. and Biru, B. H. (2024). Machine learning and cordex-africa regional model for assessing the impact of climate change on the gilgel gibe watershed, ethiopia, Journal of Environmental Management 363: 121394.
• Borgia, C., García-Bolaῆos, M. and Mateos, L. (2012). Patterns of variability in large-scale irrigation schemes in mauritania, Agricultural Water Management 112: 1-12.
• Campos, J. C., Sillero, N. and Brito, J. C. (2012). Normalized difference water indexes have dissimilar performances in detecting seasonal and permanent water in the Sahara-sahel transition zone, Journal of Hydrology 464-465: 438-446.
• Cedric, L. S., Adoni, W. Y. H., Aworka, R., Zoueu, J. T., Mutombo, F. K., Krichen, M. and Kimpolo, C. L. M. (2022). Crops yield prediction based on machine learning models: Case of west african countries, Smart Agricultural Technology 2: 100049.
• Choplin, A. and Dessie, E. (2017). Titling the desert: Land formalization and tenure (in)security in nouakchott (mauritania), Habitat International 64: 49-58.
• Dunga, L., Lück-Vogel, M., Blamey, L. K., Bolton, J., Rothman, M., Desmet, P. and Sink, K. (2024). Mapping south africa’s canopy-forming kelp forests using low-cost, high-resolution sentinel-2 imagery, Estuarine, Coastal and Shelf Science 310: 108989.
• Ebrahim, G. Y., Stefan, C., Sallwey, J. and Lautze, J. (2024). Mapping the potential of managed aquifer recharge in africa: Gis-based multi-criteria decision analysis approach, Groundwater for Sustainable Development 27: 101374.
• Ebrahimy, H. and Zhang, Z. (2023). Per-pixel accuracy as a weighting criterion for combining ensemble of extreme learning machine classifiers for satellite image classification, International Journal of Applied Earth Observation and Geoinformation 122: 103390.
• Einsele, G., Herm, D. and Schwarz, H. (1974a). Holocene eustatic (?) sea level fluctuation at the coast of mauritania, Meteor Forschungsergebnisse: Reihe C, Geologie und Geophysik 18: 43-62. URL: https://oceanrep.geomar.de/id/eprint/56634.
• Einsele, G., Herm, D. and Schwarz, H. (1974b). Sea level fluctuation during the past 6000 yr at the coast of mauritania, Quaternary Research 4(3): 282-289.
• Elouard, P. and Faure, H. (1972). Quaternaire littoral de la région de Nouakchott et de la sebkha de Ndrhamcha, Actes 6e Congr. panaf. Prréhist. Etude Quat., pp. 49-54.
• Fisher-Holloway, B. and Mokhele, M. (2023). Geographical patterns of warehousing facilities in the cape functional region, south africa, Regional Science Policy & Practice 15(6): 1317-1338.
• Gawusu, S., Mvile, B. N., Abu, M. and Kalimenze, J. D. (2024). Machine learning based prospect targeting: A case of gold occurrence in central parts of tanzania, east africa, Ore and Energy Resource Geology 17: 100065.
• Giresse, P., Barusseau, J.-P., Causse, C. and Diouf, B. (2000). Successions of sea-level changes during the pleistocene in mauritania and senegal distinguished by sedimentary facies study and u/th dating, Marine Geology 170(1): 123-139.
• Giresse, P., Diouf, M. and Barusseau, J.-P. (1988). Lithological, mineralogical and geochemical observations of senegalo-mauritanian quaternary shoreline deposits: Possible chronological revisions, Palaeogeography, Palaeoclimatology, Palaeoecology 68(2): 241-257.
• Quaternary Coastal Changes. Grandjean, G., Paillou, P., Baghdadi, N., Heggy, E., August, T. and Lasne, Y. (2006). Surface and subsurface structural mapping using low frequency radar: A synthesis of the mauritanian and egyptian experiments, Journal of African Earth Sciences 44(2): 220-228. Remote Sensing Applications to Geological Problems in Africa.
• GRASS Development Team (2022). Geographic Resources Analysis Support System (GRASS GIS) Software, Version 8.2, Open Source Geospatial Foundation. URL: https://grass.osgeo.org
• Gómez, D., Salvador, P., Sanz, J., Casanova, C., Taratiel, D. and Casanova, J. (2019). Desert ´ locust detection using earth observation satellite data in mauritania, Journal of Arid Environments 164: 29-37.
• Hamoud, A., El Hadi, H., Tahiri, A., Chakiri, S., Mehdioui, S., Baghdad, B., El Maidani, A., Bejjaji, Z. and Aoufa, M. (2021). Mauritanian geological resources: A lever for sustainable regional development via geotourism, International Journal of Geoheritage and Parks 9(4): 415-429.
• Handford, C. (1981). A process-sedimentary framework for characterizing recent and ancient sabkhas, Sedimentary Geology 30(4): 255-265.
• Henrich, R., Cherubini, Y. and Meggers, H. (2010). Climate and sea level induced turbidite activity in a canyon system offshore the hyperarid western sahara (mauritania): The timiris canyon, Marine Geology 275(1): 178-198.
• Karila, K., Matikainen, L., Karjalainen, M., Puttonen, E., Chen, Y. and Hyyppä, J. (2023). Automatic labelling for semantic segmentation of vhr satellite images: Application of airborne laser scanner data and object-based image analysis, ISPRS Open Journal of Photogrammetry and Remote Sensing 9: 100046.
• Kocurek, G., Havholm, K. G., Deynoux, M. and Blakey, R. C. (1991). Amalgamated accumulations resulting from climatic and eustatic changes, akchar erg, mauritania, Sedimentology 38(4): 751-772.
• Lemenkova, P. (2015). Topology, Homogeneity and Scale Factors for Object Detection: Application of eCognition Software for Urban Mapping using Multispectral Satellite Image, in A. Girgvliani, A. Bardavelidze, D. Zautashvili and M. Kotishadze (eds), Internet and Society, ATSU Press, pp. 80-85.
• Lemenkova, P. (2020a). Object Based Image Segmentation Algorithm of SAGA GIS for Detecting Urban Spaces in Yaoundé, Cameroon, Central European Journal of Geography and Sustainable Development 2: 38-51.
• Lemenkova, P. (2020b). Sentinel-2 for High Resolution Mapping of Slope-Based Vegetation Indices Using Machine Learning by SAGA GIS, Transylvanian Review of Systematical and Ecological Research 22: 17-34.
• Lemenkova, P. (2022a). A Script-Driven Approach to Mapping Satellite-Derived Topography and Gravity Data Over the Zagros Fold-and-Thrust Belt, Iran, Artificial Satellites 57: 110-137.
• Lemenkova, P. (2022b). Console-Based Mapping of Mongolia Using GMT Cartographic Scripting Toolset for Processing TerraClimate Data, Geosciences 12(140): 1-36.
• Lemenkova, P. (2022c). Handling Dataset with Geophysical and Geological Variables on the Bolivian Andes by the GMT Scripts, Data 7: 74.
• Lemenkova, P. (2022d). Mapping Climate Parameters over the Territory of Botswana Using GMT and Gridded Surface Data from TerraClimate, ISPRS International Journal of Geo-Information 11: 473.
• Lemenkova, P. (2023a). A GRASS GIS Scripting Framework for Monitoring Changes in the Ephemeral Salt Lakes of Chotts Melrhir and Merouane, Algeria, Applied System Innovation 6: 61.
• Lemenkova, P. (2023b). Monitoring Seasonal Fluctuations in Saline Lakes of Tunisia Using Earth Observation Data Processed by GRASS GIS, Land 12: 1995.
• Lemenkova, P. (2023c). Using open-source software GRASS GIS for analysis of the environmental patterns in Lake Chad, Central Africa, Die Bodenkultur: Journal of Land Management, Food and Environment 74: 49-64.
• Lemenkova, P. (2024a). Approche cartographique par le sig grass pour l’analyse de la structure du paysage au libéria, afrique de l’ouest, Dynamiques environnementales. Journal international de geosciences et de l’environnement 53: 1-36.
• Lemenkova, P. (2024b). Approche cartographique par le SIG GRASS pour l’analyse de la structure du paysage au Libéria, Afrique de l’Ouest, Dynamiques environnementales 53: 1-36.
• Lemenkova, P. (2024c). Artificial Intelligence for Computational Remote Sensing: Quantifying Patterns of Land Cover Types Around Cheetham Wetlands, Port Phillip Bay, Australia, Journal of Marine Science and Engineering 12: 1-27.
• Lemenkova, P. (2024d). Mapping Coastal Regions of Guinea-Bissau for Analysis of Mangrove Dynamics Using Remote Sensing Data, Transylvanian Review of Systematical and Ecological Research 26: 17-30.
• Lemenkova, P. (2024e). Mapping Woodlands in Angola, Tropical Africa: Calculation of Vegetation Indices From Remote Sensing Data, Agriculture and Forestry 70: 185-202.
• Lemenkova, P. (2024f). Support Vector Machine Algorithm for Mapping Land Cover Dynamics in Senegal, West Africa, Using Earth Observation Data, Earth 5: 420-462.
• Lemenkova, P. (2025a). Automation of image processing through ml algorithms of grass gis using embedded scikit-learn library of python, Examples and Counterexamples 7: 100180.
• Lemenkova, P. (2025b). Improving bimonthly landscape monitoring in morocco, north africa, by integrating machine learning with grass gis, Geomatics 5(1).
• Lemenkova, P. and Debeir, O. (2023a). Computing Vegetation Indices from the Satellite Images Using GRASS GIS Scripts for Monitoring Mangrove Forests in the Coastal Landscapes of Niger Delta, Nigeria, Journal of Marine Science and Engineering 11: 871.
• Lemenkova, P. and Debeir, O. (2023b). Time Series Analysis of Landsat Images for Monitoring Flooded Areas in the Inner Niger Delta, Mali, Artificial Satellites 58: 278-313.
• M. Pichel, L., Finch, E. and Gawthorpe, R. L. (2019). The impact of pre-salt rift topography on salt tectonics: A discrete-element modeling approach, Tectonics 38(4): 1466-1488.
• Manning-Berg, A. R., Goodman, E. E. and Kah, L. C. (2024). Calcitized evaporites in the mesoproterozoic atar and el meriti groups, mauritania, africa, Palaeogeography, Palaeoclimatology, Palaeoecology 636: 111974.
• Medus, J. (1987). West african holocene stratigraphy, transgressions and climatic changes, Progress in Oceanography 18(1): 167-175.
• Mitasova, H. and Neteler, M. (2004). Grass as open source free software gis: Accomplishments and perspectives, Transactions in GIS 8(2): 145-154.
• Mohamed, A.-S., Leduc, C., Marlin, C., Wagué, O. and Sidi Cheikh, M.-A. (2017). Impacts of climate change and anthropization on groundwater resources in the nouakchott urban area (coastal mauritania), Comptes Rendus Geoscience 349(6): 280-289. Vulnerability of inter-tropical littoral areas.
• Nartišs, M. and Melniks, R. (2023). Improving pixel-based classification of grass gis with ˇ support vector machine, Transactions in GIS 27(7): 1865-1880.
• Nasiri, V., Hawryło, P., Janiec, P. and Socha, J. (2023). Comparing object-based and pixel-based machine learning models for tree-cutting detection with planetscope satellite images: Exploring model generalization, International Journal of Applied Earth Observation and Geoinformation 125: 103555.
• Nenkam, A. M., Wadoux, A. M.-C., Minasny, B., Silatsa, F. B., Yemefack, M., Ugbaje, S. U., Akpa, S., Zijl, G. V., Bouasria, A., Bouslihim, Y., Chabala, L. M., Ali, A. and McBratney, A. B. (2024). Applications and challenges of digital soil mapping in africa, Geoderma 449: 117007.
• Neteler, M., Bowman, M. H., Landa, M. and Metz, M. (2012). Grass gis: A multi-purpose open source gis, Environmental Modelling & Software 31: 124-130.
• Neteler, M. and Mitasova, H. (2002). Open Source GIS: A GRASS GIS Approach, 0893-3405, 2 edn, Kluwer, Boston, MA.
• Niang, A. J. (2022). Remote Sensing and GIS Application for Natural Hazards Assessment of the Mauritanian Coastal Zone, Springer International Publishing, Cham, pp. 195-223.
• Ould Ahmedou, D., Ould Mahfoudh, A., Dupont, P., Ould El Moctar, A., Valance, A. and Rasmussen, K. R. (2007). Barchan dune mobility in mauritania related to dune and interdune sand fluxes, Journal of Geophysical Research: Earth Surface 112(F2).
• Ould Sidi Cheikh, M. A., Ozer, P. and Ozer, A. (2007). Risques d’inondation dans la ville de nouakchott (mauritanie), Geo-Eco-Trop: Revue Internationale de Geologie, de Géographie et d’Écologie Tropicales 31.
• Pande, C. B., Egbueri, J. C., Costache, R., Sidek, L. M., Wang, Q., Alshehri, F., Din, N. M., Gautam, V. K. and Chandra Pal, S. (2024). Predictive modeling of land surface temperature (lst) based on landsat-8 satellite data and machine learning models for sustainable development, Journal of Cleaner Production 444: 141035.
• Parajuli, S. P., Yang, Z.-L. and Kocurek, G. (2014). Mapping erodibility in dust source regions based on geomorphology, meteorology, and remote sensing, Journal of Geophysical Research: Earth Surface 119(9): 1977-1994.
• Pillay, T., Cawthra, H., Lombard, A. and Sink, K. (2021). Benthic habitat mapping from a machine learning perspective on the cape st francis inner shelf, eastern cape, south africa, Marine Geology 440: 106595.
• Plaziat, J.-C. (1991). Paleogeographic significance of the cardium, potamids and foraminifera living in intra-continental salt lakes of north africa (sahara quaternary, egypt present lakes), Journal of African Earth Sciences (and the Middle East) 12(1): 383-389. Sedimentary and Diagenetic Dynamics of Continental Phanerozoic Sediments in Africa.
• Quebedeaux, B. and Parks, L. L. (1984). Vegetable crop development in mauritania, Agricultural Administration 15(3): 133-156.
• Rahman, A., Abdullah, H. M., Tanzir, M. T., Hossain, M. J., Khan, B. M., Miah, M. G. and Islam, I. (2020). Performance of different machine learning algorithms on satellite image classification in rural and urban setup, Remote Sensing Applications: Society and Environment 20: 100410.
• Rathore, M. M. U., Ahmad, A., Paul, A. and Wu, J. (2016). Real-time continuous feature extraction in large size satellite images, Journal of Systems Architecture 64: 122-132. Real-Time Signal Processing in Embedded Systems.
• Rocchini, D., Delucchi, L., Bacaro, G., Cavallini, P., Feilhauer, H., Foody, G. M., He, K. S., Nagendra, H., Porta, C., Ricotta, C., Schmidtlein, S., Spano, L. D., Wegmann, M. and Neteler, M. (2013). Calculating landscape diversity with information-theory based indices: A grass gis solution, Ecological Informatics 17: 82-93. Special issue of the 7th International Conference on Ecological Informatics, 13-16 December 2010, Ghent, Belgium: ’Unravelling complexity and supporting sustainability’.
• Rocchini, D., Petras, V., Petrasova, A., Chemin, Y., Ricotta, C., Frigeri, A., Landa, M., Marcantonio, M., Bastin, L., Metz, M., Delucchi, L. and Neteler, M. (2017). Spatio-ecological complexity measures in grass gis, Computers & Geosciences 104: 166-176.
• Semega, B. (2008). Energie éolienne et dessalement dans le contexte mauritanien, des modéles de developpement pour le sud, Energie Francophonie 179.
• Senhoury, A., Niang, A., Diouf, B. and Thomas, Y.-F. (2016). Managing Flood Risks Using Nature-Based Solutions in Nouakchott, Mauritania, Springer International Publishing, Cham, pp. 435-455.
• Shoko, C. and Dube, T. (2024). A review of remote sensing of flood monitoring and assessment in southern africa, Physics and Chemistry of the Earth, Parts A/B/C 136: 103796.
• Soulié-Märsche, I. (2008). Charophytes, indicators for low salinity phases in north african sebkhet, Journal of African Earth Sciences 51(2): 69-76.
• Tari, G., Novotny, B., Jabour, H. and Hafid, M. (2017). Chapter 15 - salt tectonics along the atlantic margin of nw africa (morocco and mauritania), in J. I. Soto, J. F. Flinch and G. Tari (eds), Permo-Triassic Salt Provinces of Europe, North Africa and the Atlantic Margins, Elsevier, pp. 331-351.
• Twumasi-Ankrah, M. J., Zhan, J. and Asamoah, E. F. (2024). Mapping ecoregional vulnerability to climate change for africa, Science of The Total Environment 953: 176219.
• van Asten, P., Barbiéro, L., Wopereis, M., Maeght, J. and van der Zee, S. (2003). Actual and potential salt-related soil degradation in an irrigated rice scheme in the sahelian zone of mauritania, Agricultural Water Management 60(1): 13-32.
• Vermeer, D. (2010). Mauritania, Springer Netherlands, Dordrecht, pp. 917-919.
• Versteegh, G. J. M., Zonneveld, K. A. F., Hefter, J., Romero, O. E., Fischer, G. and Mollenhauer, G. (2022). Performance of temperature and productivity proxies based on long-chain alkane-1, mid-chain diols at test: a 5-year sediment trap record from the mauritanian upwelling, Biogeosciences 19(5): 1587-1610.
• Vázquez, R., Parras-Berrocal, I., Koseki, S., Cabos, W., Sein, D. and Izquierdo, A. (2023). Seasonality of coastal upwelling trends in the mauritania-senegalese region under rcp8.5 climate change scenario, Science of The Total Environment 898: 166391.
• Walther, B. A. and Huettmann, F. (2021). Palearctic passerine migrant declines in african wintering grounds in the anthropocene (1970-1990 and near future): A conservation assessment using publicly available gis predictors and machine learning, Science of The Total Environment 777: 146093.
• Wessel, P., Luis, J. F., Uieda, L., Scharroo, R., Wobbe, F., Smith, W. H. F. and Tian, D. (2019). The Generic Mapping Tools Version 6, Geochemistry, Geophysics, Geosystems 20(11): 5556-5564.
• Wijnsma, G., Wolff, W. J., Meijboom, A., Duiven, P. and De Vlas, J. (1999). Species richness and distribution of benthic tidal flat fauna of the banc d’arguin, mauritania, Oceanologica Acta 22(2): 233-243.
• Wissmann, G. (1982). Stratigraphy and structural features of the continental margin basin of senegal and mauritania, Geology of the Northwest African Continental Margin, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 160-181.
• Yang, J., Fricker, P. and Jung, A. (2024). From intangible to tangible: The role of big data and machine learning in walkability studies, Computers, Environment and Urban Systems 109: 102087.
• Álvaro, J. J. (2012). Colour banding in a latest neoproterozoic-cambrian microbially variegated sabkha of the taoudeni basin, adrar of mauritania, Palaeogeography, Palaeoclimatology, Palaeoecology 367-368: 209-218. Special Issue: Time-Specific Facies: the color and texture of biotic events.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).