Authors :
Rasoanaina Jacquis; Rakotoson Andriatiana Tolontsoa; Tovonirina Mamiharizo Jackie; Razafiarisera Ralay Tiana; Rasolomanana Eddy Harilala
Volume/Issue :
Volume 11 - 2026, Issue 7 - July
Google Scholar :
https://tinyurl.com/35bx27sr
Scribd :
https://tinyurl.com/3c37u5kz
DOI :
https://doi.org/10.38124/ijisrt/26jul913
Note : A published paper may take 4-5
working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and
ResearchGate.
Abstract :
This study integrates multicriteria environmental analysis and spatially cross-validated machine learning to assess
synthetic erosion vulnerability in the Betsiboka Region, Madagascar. The vulnerability index combined low NDVI, slope,
hydrographic proximity, elevation, and available geological, soil, rainfall, and land-cover factors on a 1 km grid.
Hydrographic proximity was modelled using an exponential distance-decay function with a characteristic distance of 3 km,
while geology was represented through normalized susceptibility scores ranging from 0 to 1. Three regression algorithms—
Random Forest, Extra Trees, and Histogram Gradient Boosting—were evaluated using five-fold spatial block crossvalidation.
Keywords :
Erosion Vulnerability; Multicriteria Analysis; Spatial Cross-Validation; Machine Learning; Betsiboka Region.
References :
- Borrelli, P., Robinson, D.A., Fleischer, L.R., Lugato, E., Ballabio, C., Alewell, C., Meusburger, K., Modugno, S., Schütt, B., Ferro, V., Bagarello, V., Van Oost, K., Montanarella, L. and Panagos, P. (2017) ‘An assessment of the global impact of 21st century land use change on soil erosion’, Nature Communications, 8, Article 2013. https://doi.org/10.1038/s41467-017-02142-7.
- Cox, R., Bierman, P., Jungers, M.C. and Rakotondrazafy, A.F.M. (2009) ‘Erosion rates and sediment sources in Madagascar inferred from ¹⁰Be analysis of lavaka, slope, and river sediment’, The Journal of Geology, 117(4), pp. 363–376. https://doi.org/10.1086/598945.
- Ralison, O.H., Borges, A.V., Dehairs, F., Middelburg, J.J. and Bouillon, S. (2008) ‘Carbon biogeochemistry of the Betsiboka estuary, north-western Madagascar’, Organic Geochemistry, 39, pp. 1649–1658. https://doi.org/10.1016/j.orggeochem.2008.01.010.
- Paul, J.D., Radimilahy, A., Randrianalijaona, R. and Mulyakova, T. (2022) ‘Lateritic processes in Madagascar and the link with agricultural and socioeconomic conditions’, Journal of African Earth Sciences, 196, Article 104681. https://doi.org/10.1016/j.jafrearsci.2022.104681.
- Elbadaoui, K., Mansour, S., Ikirri, M., Abdelrahman, K., Abu-Alam, T. and Abioui, M. (2023) ‘Integrating Erosion Potential Model (EPM) and PAP/RAC guidelines for water erosion mapping and detection of vulnerable areas in the Toudgha River watershed of the Central High Atlas, Morocco’, Land, 12(4), Article 837. https://doi.org/10.3390/land12040837.
- Mosavi, A., Sajedi-Hosseini, F., Choubin, B., Taromideh, F., Rahi, G. and Dineva, A.A. (2020) ‘Susceptibility mapping of soil water erosion using machine learning models’, Water, 12(7), Article 1995. https://doi.org/10.3390/w12071995.
- Roberts, D.R., Bahn, V., Ciuti, S., Boyce, M.S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J.J., Schröder, B., Thuiller, W., Warton, D.I., Wintle, B.A., Hartig, F. and Dormann, C.F. (2017) ‘Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure’, Ecography, 40(8), pp. 913–929. https://doi.org/10.1111/ecog.02881.
- Humanitarian OpenStreetMap Team (2026) Madagascar: Waterways (OpenStreetMap Export). Humanitarian Data Exchange. Dataset accessed 16 July 2026.
- UNITAR–UNOSAT (2020) Satellite-detected surface waters in the Republic of Madagascar, 9–13 February 2020. Product FL20200128MDG, Product ID 2807. Geneva: United Nations Institute for Training and Research.
- U.S. Geological Survey, Earth Resources Observation and Science Center (2023) USGS EROS Archive—Vegetation Monitoring—eVIIRS Global Normalized Difference Vegetation Index. Sioux Falls, SD: USGS EROS Center.
- U.S. Geological Survey, Earth Resources Observation and Science Center (2018) USGS EROS Archive—Digital Elevation—Shuttle Radar Topography Mission 1 Arc-Second Global. Sioux Falls, SD: USGS. doi: 10.5066/F7PR7TFT.
- Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., VanderPlas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M. and Duchesnay, É. (2011) ‘Scikit-learn: Machine learning in Python’, Journal of Machine Learning Research, 12, pp. 2825–2830.
- Breiman, L. (2001) ‘Random forests’, Machine Learning, 45(1), pp. 5–32. doi: 10.1023/A:1010933404324.
- Geurts, P., Ernst, D. and Wehenkel, L. (2006) ‘Extremely randomized trees’, Machine Learning, 63(1), pp. 3–42. doi: 10.1007/s10994-006-6226-1.
- Friedman, J.H. (2001) ‘Greedy function approximation: A gradient boosting machine’, The Annals of Statistics, 29(5), pp. 1189–1232. doi: 10.1214/aos/1013203451.
This study integrates multicriteria environmental analysis and spatially cross-validated machine learning to assess
synthetic erosion vulnerability in the Betsiboka Region, Madagascar. The vulnerability index combined low NDVI, slope,
hydrographic proximity, elevation, and available geological, soil, rainfall, and land-cover factors on a 1 km grid.
Hydrographic proximity was modelled using an exponential distance-decay function with a characteristic distance of 3 km,
while geology was represented through normalized susceptibility scores ranging from 0 to 1. Three regression algorithms—
Random Forest, Extra Trees, and Histogram Gradient Boosting—were evaluated using five-fold spatial block crossvalidation.
Keywords :
Erosion Vulnerability; Multicriteria Analysis; Spatial Cross-Validation; Machine Learning; Betsiboka Region.