Comparative Analysis Of Machine Learning Algorithms For Land Use And Land Cover Mapping: Case Study Of Berrechid-Settat Region, Morocco
https://doi.org/10.24057/2071-9388-2025-3980
Abstract
This study analyses the spatiotemporal dynamics of Land Use and Land Cover (LULC) in the Berrechid-Settat area of Morocco throughout three reference years: 2010, 2015, and 2023. Satellite images from Landsat 7 (ETM+) and Landsat 8 OLI were processed using the Google Earth Engine (GEE) platform to facilitate quick access, preprocessing, and analysis of extensive datasets. To classify LULC changes and assess the efficacy of machine learning models, Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM) were examined. These models were used to categorise five principal LULC classes: water bodies, forests, urban regions, vegetation, and barren lands. Our findings indicated that Random Forest consistently yielded the highest classification accuracy, achieving an Overall Accuracy (OA) of 91.84% and a Kappa Coefficient (KC) of 0.86 in 2023, thereby affirming its efficacy for multi-temporal land use and land cover mapping. The Decision Tree exhibited competitive performance in 2010 (87.36% OA, a KC of 0.79) but showed diminished stability in later years. The SVM displayed middling performance, particularly excelling in the classification of urban areas (about 94%) but exhibiting reduced accuracy for forest regions. This analysis emphasises the efficacy of GEE and Python libraries in analysing large satellite imagery and the proficiency of DT and RF models in land use and land cover classification. The results can guide regional planning and land management policies, fostering sustainable development.
Keywords
Supporting agencies: The authors wish to express their sincere gratitude to Dr. Thanh Thi Nguyen from the University of Kassel, Germany, for her valuable guidance, constructive feedback, and insightful discussions, which significantly contributed to improving the quality of this study.
About the Authors
Youssef Laalaoui
Geosciences, Water and Environment Laboratory, Earth Sciences Department, Faculty of Sciences, Mohammed V University in Rabat
Morocco
Morocco
4 Ibn Battouta Avenue, 1014, Rabat
Naïma El Assaoui
Geosciences, Water and Environment Laboratory, Earth Sciences Department, Faculty of Sciences, Mohammed V University in Rabat
Morocco
Morocco
4 Ibn Battouta Avenue, 1014, Rabat
Oumaima Ouahine
Geosciences, Water and Environment Laboratory, Earth Sciences Department, Faculty of Sciences, Mohammed V University in Rabat
Morocco
Morocco
4 Ibn Battouta Avenue, 1014, Rabat
References
1. Achahboun C., Chikhaoui M., Naimi M. and Bellafkih M. (2023). Crops Classification Using Machine Learning And Google Earth Engine. Proceedings - SITA 2023: 2023 14th International Conference on Intelligent Systems: Theories and Applications. DOI: 10.1109/SITA60746.2023.10373760
2. Akar O. and Gormus K.S. (2021). Land Use and Land Cover Classification Using Machine Learning and Deep Learning Algorithms. Environmental Monitoring and Assessment, 193(2), 59. DOI: 10.1007/s10661-021-08853-y
3. Ali K. and Johnson B.A. (2022). Land-use and land-cover classification in semi-arid areas from medium-resolution remote-sensing imagery: A deep learning approach. Sensors, 22(22), 8750.
4. Alshari E.A. and Gawali B.W. (2021). Development of classification system for LULC using remote sensing and GIS. Global Transitions Proceedings, 2(1), 8–17.
5. Amazirh A., Ouassanouan Y., Bouimouass H., Baba M.W., Bouras E.H., Rafik A., Benkirane M., Hajhouji Y., Ablila Y. and Chehbouni A. (2024). Remote Sensing-Based Multiscale Analysis of Total and Groundwater Storage Dynamics over Semi-Arid North African Basins. Remote Sensing, 16(19). DOI: 10.3390/rs16193698
6. Amin G., Imtiaz I., Haroon E., Saqib N.U., Shahzad M.I. and Nazeer M. (2024). Assessment of Machine Learning Algorithms for Land Cover Classification in a Complex Mountainous Landscape. Journal of Geovisualization and Spatial Analysis, 8(2), 34. DOI: 10.1007/s41651-02400195-z
7. Andrew O., Apan A., Paudyal D.R. and Perera K. (2023). Convolutional Neural Network-Based Deep Learning Approach for Automatic Flood Mapping Using NovaSAR-1 and Sentinel-1 Data. ISPRS International Journal of Geo-Information, 12(5). DOI: 10.3390/ijgi12050194
8. Assaoui N.E. (2023). Use of Remote Sensing and GIS to Study the Evolution of Irrigated Areas and Their Impact on Groundwater in a Semi-Arid Region (Morocco). In: Z. A. Ergüler, R. Hadji, H. I. Chaminé, J. Rodrigo-Comino, A. Kallel, B. Merkel, M. Eshagh, H. Chenchouni, S. Grab, M. Karakus, S. Khomsi, J. Knight, M. Bezzeghoud, M. Barbieri, S. Panda, A. C. Benim, and H. El-Askary eds., Selected Studies in Geotechnics, Geo-informatics and Remote Sensing , 75–79. Springer Nature Switzerland.
9. Assaoui N.E., Sadok A. and Charafi M. (2021). Analysis of a water supply intake from a silted dam using two-dimensional horizontal numerical modeling: Case of Mechraa Hammadi dam (Morocco). Materials Today: Proceedings, 45, 7718–7724. DOI: https://doi.org/10.1016/j.matpr.2021.03.337
10. Audebert N., Le Saux B. and Lefèvre S. (2018). Deep learning for classification of hyperspectral data: A comparative review. Remote Sensing, 10(2), 157. DOI: 10.3390/rs10020157
11. Aydin I. and Sefercik U.G. (2025). Multispectral UAV-based LULC mapping performance improvement by integrating precise NDSM data and machine learning algorithms. Earth Science Informatics, 18(2). DOI: 10.1007/s12145-025-01841-w
12. Baatz R., Ghazaryan G., Hagenlocher M., Nendel C., Toreti A. and Rezaei E.E. (2025). Drought research priorities, trends, and geographic patterns. Hydrology and Earth System Sciences, 29(5), 1379–1393. DOI: 10.5194/hess-29-1379-2025
13. Belgiu M. and Csillik O. (2018). Comparison of random forest and support vector machine classifiers for large area land cover mapping. Remote Sensing, 10(1), 6. DOI: 10.3390/rs10010006
14. Belgiu M. and Drăguţ L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31. DOI: 10.1016/j.isprsjprs.2016.01.011
15. Bhungeni O., Ramjatan A. and Gebreslasie M. (2024). Evaluating Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal. Remote Sensing, 16(12), 2219.
16. Bouzekraoui H., El Asri Z., Ouikhalfan M. and Benyaich A. (2020). Urban sprawl and land degradation in the Casablanca-Settat region of Morocco: Analysis and implications. Urban Planning and Development, 146(3), 05020011. DOI: 10.1061/(ASCE)UP.1943-5444.0000594
17. Carlson D., Montealegre A.L. and Inoue Y. (2018). Geospatial analysis of land cover change using time-series Landsat imagery on Google Earth Engine. International Journal of Remote Sensing, 39(7), 1978–1995. DOI: 10.1080/01431161.2017.1407044
18. Carrara P., Bordogna G. and De Carolis G. (2024). Spatial Data Infrastructure for Remote Sensing: A Comprehensive Analysis. DOI: 10.20944/preprints202404.0593.v1
19. Chen D., Bi B., Luo Z.H., Yang Y.W., Webber M. and Finlayson B. (2018). A scientometric review of water research on the Yangtze river. Applied Ecology and Environmental Research, 16(6), 7969–7987. DOI: 10.15666/aeer/1606_79697987
20. Chen J., Hu Y., Fan W., Zhang Y. and Wang L. (2017). Urban land cover classification using integrated multispectral and texture analysis with Landsat 8 imagery. Remote Sensing, 9(4), 316. DOI: 10.3390/rs9040316
21. Chomani K. and Pshdari S. (2024a). Evaluation of Different Classification Algorithms for Land Use Land Cover Mapping. Kurdistan Journal of Applied Research, 9(2), 13–22. DOI: 10.24017/science.2024.2.2
22. Chomani K. and Pshdari S. (2024b). Evaluation of Different Classification Algorithms for Land Use Land Cover Mapping. Kurdistan Journal of Applied Research, 9(2), 13–22. DOI: 10.24017/science.2024.2.2
23. Congalton R.G. and Green K. (2019). Assessing the accuracy of remotely sensed data: principles and practices. CRC Press.
24. Conrad C., Schönbrodt-Stitt S., Loew A. and Sorensen R. (2020). A pixel-based classification framework for improving land cover mapping through spatial and temporal integration. Remote Sensing of Environment, 247, 111920. DOI: 10.1016/j.rse.2020.111920
25. Dharumarajan S. and Hegde R. (2022). Digital mapping of soil texture classes using Random Forest classification algorithm. Soil Use and Management, 38(1), 135–149. DOI: 10.1111/sum.12668
26. Dong J., Xiao X., Menarguez M.A., Zhang G., Qin Y. and Roy D.P. (2019). Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, time series, and rasterio library. International Journal of Applied Earth Observation and Geoinformation, 78, 65–74. DOI: 10.1016/j.jag.2019.01.012
27. Drusch M., Gascon F., Berger M. and Duesmann B. (2017). Sentinel-2: ESA’s optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 221, 255–261. DOI: 10.1016/j.rse.2017.05.032
28. Du T.L.T., Du Bui D., Nguyen M.D. and Lee H. (2018). Satellite-based, multi-indices for evaluation of agricultural droughts in a highly dynamic tropical catchment, Central Vietnam. Water (Switzerland), 10(5). DOI: 10.3390/w10050659
29. El Assaoui Fouad Amraoui N. and El Mansouri B. (2015). MODÉLISATION NUMERIQUE DE L’EFFET DES CHANGEMENTS CLIMATIQUES SUR LA NAPPE DE BERRECHID (MAROC) , Vol. 11, Issue 23, 1857–7881.
30. El Assaoui N., Bouiss C. and Sadok A. (2023). Assessment of Water Erosion by Integrating RUSLE Model, GIS and Remote Sensing – Case of Tamdrost Watershed (Morocco). Ecological Engineering & Environmental Technology, 24(3), 43–53. DOI: 10.12912/27197050/159530
31. ElAssaoui N., Amraoui F. and El Mansouri B. (2015). Modeling of climate changes impact on groundwater Resources of Berrechid Aquifer. International Journal of Innovative Research in Science Engineering and Technology, 4(7), 5681–5694.
32. Elgendy N. and Abdelatif T. (2021). Land use and land cover dynamics in Morocco: Insights into the spatial and temporal changes. Journal of African Earth Sciences, 179, 104163. DOI: 10.1016/j.jafrearsci.2021.104163
33. Feng Q., Gong J., Liu J. and Li Y. (2015). Flood mapping based on multiple endmember spectral mixture analysis and random forest classifier—The case of Yuyao, China. Remote Sensing, 7(9), 12539–12562.
34. Fentaw A.E. and Abegaz A. (2024). Analyzing Land Use/Land Cover Changes Using Google Earth Engine and Random Forest Algorithm and Their Implications to the Management of Land Degradation in the Upper Tekeze Basin, Ethiopia. Scientific World Journal, 2024. DOI: 10.1155/2024/3937558
35. Gerber F., Skakun S., Brown M.E. and Justice C.O. (2018). Automated geospatial data processing and visualization in Python using rasterio and GDAL. Computers & Geosciences, 118, 1–10. DOI: 10.1016/j.cageo.2018.05.014
36. Gohr C., Rodríguez G., Belomestnykh S., Berg-Moelleken D., Chauhan N., Engler J.-O., Heydebreck L.V., Hintz M.J., Kretschmer M., Krügermeier C., Meinberg J., Rau A.-L., Schwenck C., Aoulkadi I., Poll S., Frank E., Creutzig F., Lemke O., Maushart M., … Von Wehrden H. (2025). Artificial intelligence in sustainable development research. Nature Sustainability, 8(8), 970–978. DOI: 10.1038/s41893-025-01598-6
37. Harfouche A., Achard F. and Eva H.D. (2020). Time-series analysis of Landsat imagery for detecting forest cover changes in tropical regions. Forests, 11(8), 827. DOI: 10.3390/f11080827
38. He Y., Ding H. and Li P. (2020). Assessment of supervised machine learning classifiers for mapping land cover with Sentinel-2 imagery in Google Earth Engine. Remote Sensing, 12(1), 83. DOI: 10.3390/rs12010083
39. Jiang B., Dungan J.L., Matin A., Zarecor S. and Song X. (2021). A workflow for geospatial data integration and analysis using GDAL and rasterio libraries. Environmental Modelling & Software, 140, 105064. DOI: 10.1016/j.envsoft.2021.105064
40. Jiang J., Cai D., Yang Q. and Huang M. (2025). Scientometric insights into urban sustainability: exploring the vulnerability-adaptationsettlements nexus for climate resilience. Frontiers in Environmental Science, 13. DOI: 10.3389/fenvs.2025.1596271
41. Kamusoko C. and Gamba J. (2016). Machine learning techniques for land cover mapping in rural areas using Landsat 8 data: A comparison of SVM and RF classifiers. Remote Sensing, 8(9), 753. DOI: 10.3390/rs8090753
42. Kobayashi A., Hu C. and Andrefouet S. (2022). Improving accuracy in land cover classification and change detection using ensemble learning with pixel-based and object-based methods. International Journal of Remote Sensing, 43(2), 503–522. DOI: 10.1080/01431161.2021.1952635
43. Koukal T., Panferov O., Medina J.G. and Rouabhi A. (2020). Land cover changes and agricultural developments in Morocco: An assessment of spatial trends from 2000 to 2019. Remote Sensing Applications: Society and Environment, 19, 100357. DOI: 10.1016/j.rsase.2020.100357
44. Kussul N., Lavreniuk M., Skakun S. and Shelestov A. (2017). Land Use and Land Cover Classification Using Deep Learning Algorithms on Sentinel-2 Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(9), 3479–3490. DOI: 10.1109/JSTARS.2017.2724559
45. Laalaoui Y., Elassaoui N. and Ouahine O. (2024). Balancing urban growth and the sustainability of groundwater and agricultural land: Case of the berrechid-settat area. E3S Web of Conferences, 489, 04012.
46. Lee J., Xu P. and Ho H.T. (2017). Land cover classification for urban areas using Google Earth Engine and machine learning algorithms. Remote Sensing, 9(3), 248. DOI: 10.3390/rs9030248
47. Li W., Fu H., Yu L. and Wang L. (2019). A review of remote sensing-based land cover and land use change detection systems and models: Classification and assessment. Sensors, 19(9), 2326. DOI: 10.3390/s19092326
48. Lu D., Weng Q. and Li G. (2021). Evaluation of training sample sizes and class distribution on machine learning classifiers for land cover classification using Google Earth Engine. International Journal of Applied Earth Observation and Geoinformation, 100, 102327. DOI: 10.1016/j.jag.2021.102327
49. Meghraoui K., Sebari I., Pilz J., Ait El Kadi K. and Bensiali S. (2024). Applied Deep Learning-Based Crop Yield Prediction: A Systematic Analysis of Current Developments and Potential Challenges. Technologies, 12(4). DOI: 10.3390/technologies12040043
50. Nicolau A., Pires L.F. and Segovia J.A. (2023). Accuracy assessment: Quantifying classification quality. Lecture Notes in Geoinformation and Cartography, 235–254. DOI: 10.1007/978-3-031-26588-4_7
51. Peterson D.L. and Levinson D.H. (2020). Land use and land cover changes and their environmental implications in the Mediterranean basin. Environmental Science & Policy, 114, 245–254. DOI: 10.1016/j.envsci.2020.09.004
52. Phan T.N., Kuch V. and Lehnert L.W. (2020). Land cover classification using Google Earth Engine and random forest classifier—The role of image composition. Remote Sensing, 12(15), 2411.
53. Pickens A.H., Patel N., Senf C., Heurich M. and Hostert P. (2020). Remote sensing of vegetation cover dynamics and land cover change using Landsat data in complex landscapes. Remote Sensing of Environment, 242, 111770. DOI: 10.1016/j.rse.2020.111770
54. Riche A., Ricci R., Melgani F., Drias A. and Souissi B. (2024). Machine Learning Approach to LULC Forecasting. 2024 IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), 59–63. DOI: 10.1109/M2GARSS57310.2024.10537270
55. Saqr A.M., Kartal V., Karakoyun E. and Abd-Elmaboud M.E. (2025). Improving the Accuracy of Groundwater Level Forecasting by Coupling Ensemble Machine Learning Model and Coronavirus Herd Immunity Optimizer. Water Resources Management, 39(11), 5415–5442. DOI: 10.1007/s11269-025-04210-w
56. Sellami E.M. and Rhinane H. (2023). A new approach for mapping land use/land cover using google earth engine: a comparison of composition images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 48, 343–349.
57. Sharnagat N., Nema A.K., Mishra P.K., Patidar N., Kumar R., Suryawanshi A. and Radha L. (2025). State-of-the-Art Status of Google Earth Engine (GEE) Application in Land and Water Resource Management: A Scientometric Analysis. Journal of Geovisualization and Spatial Analysis, 9(1), 16. DOI: 10.1007/s41651-025-00218-3
58. Wachowska M., Kowalczyk A. and Kozak J. (2018). Using remote sensing for land cover classification and change detection: A comparative approach between machine learning algorithms. International Journal of Applied Earth Observation and Geoinformation, 75, 108–118. DOI: 10.1016/j.jag.2018.08.002
59. Wang J., Gong P. and Zhang B. (2018). Comparative evaluation of machine learning classifiers for land cover classification based on Landsat and Sentinel-2 data. International Journal of Remote Sensing, 39(16), 5604–5624. DOI: 10.1080/01431161.2018.1490972
60. Wu Q. (2020). geemap: A Python package for interactive mapping with Google Earth Engine. Journal of Open Source Software, 5(51), 2305.
61. Zhao Q., Yu L., Li X., Peng D., Zhang Y. and Gong P. (2021). Progress and trends in the application of google earth and google earth engine. Remote Sensing, 13(18). DOI: 10.3390/rs13183778
62. Zhao Z., Islam F., Waseem L.A., Tariq A., Nawaz M., Islam I.U., Bibi T., Rehman N.U., Ahmad W., Aslam R.W., and others. (2024). Comparison of three machine learning algorithms using google earth engine for land use land cover classification. Rangeland Ecology & Management, 92, 129–137.
Review
For citations:
Laalaoui Y., El Assaoui N., Ouahine O. Comparative Analysis Of Machine Learning Algorithms For Land Use And Land Cover Mapping: Case Study Of Berrechid-Settat Region, Morocco. GEOGRAPHY, ENVIRONMENT, SUSTAINABILITY. 2025;18(4):158-170. https://doi.org/10.24057/2071-9388-2025-3980
Views:
71
JATS XML
Email this article 