Tola D. auteur aut IRD Satgé Frédéric auteur aut IRD Zolá R. P. auteur aut IRD Sainz H. auteur aut IRD Condori B. auteur aut IRD Miranda R. auteur aut IRD Yujra E. auteur aut IRD Molina-Carpio J. auteur aut IRD Hostache Renaud auteur aut IRD Espinoza-Villar R. auteur aut IRD text journalArticle eng text/pdf reformatted digital access This study assesses the relative performance of Sentinel-1 and -2 and their combination with topographic information for plow agricultural land soil salinity mapping. A learning database made of 255 soil samples' electrical conductivity (EC) along with corresponding radar (R), optical (O), and topographic (T) information derived from Sentinel-2 (S2), Sentinel-1 (S1), and the SRTM digital elevation model, respectively, was used to train four machine learning models (Decision tree-DT, Random Forest-RF, Gradient Boosting-GB, Extreme Gradient Boosting-XGB). Each model was separately trained/validated for four scenarios based on four combinations of R, O, and T (R, O, R+O, R+O+T), with and without feature selection. The Recursive Feature Elimination with k-fold cross validation (RFEcv 10-fold) and the Variance Inflation Factor (VIF) were used for the feature selection process to minimize multicollinearity by selecting the most relevant features. The most reliable salinity estimates are obtained for the R+O+T scenario, considering the feature selection process, with R2 of 0.73, 0.74, 0.75, and 0.76 for DT, GB, RF, and XGB, respectively. Conversely, models based on R information led to unreliable soil salinity estimates due to the saturation of the C-band signal in plowed lands. specialized soil salinity mapping plowed lands machine learning Sentinel-1 Sentinel-2 BOLIVIE ANDES 126 068 16 18 3456 [18 ] 2024 https://www.documentation.ird.fr/hor/fdi:010091909 10.3390/rs16183456 [F B010091909] https://www.documentation.ird.fr/hor/fdi:010091909 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2024-11/010091909.pdf IRD - Base Horizon / Pleins textes 2024-11-13 2025-11-06 fdi:010091909 fre