Optimized and Explainable Feature Selection for Soil Moisture Prediction Across Sites

Bamory Ahmed Toru Koné, Bamory Ahmed Toru Koné, Rima Grati, Rima Grati, Bassem Bouaziz, Bassem Bouaziz, Khouloud Boukadi, Khouloud Boukadi, Massimo Mecella

2025

Abstract

Accurate soil moisture prediction is critical for improving agricultural practices and managing water supplies. While feature selection techniques have proven useful in enhancing machine learning models’ performance in predicting soil moisture, their adaptation to different soil conditions remains limited. To address this gap, this study presents a novel multisite feature selection framework that draws on meteorological and soil data from three distinct locations with mineral, calcareous, and organic soils. The framework identifies soil-specific features through targeted selection processes and then uses SHAP, an explainable AI technique, to assess their global importance and influence. Furthermore, cross-site validation is performed to assess the transferability and generalizability of selected features, giving insight into their resilience across different environments. The proposed approach, which combines explainable AI and cross-site validation, provides a complete approach to understanding and improving feature relevance for soil moisture prediction. Overall, this study establishes the foundation for building more generalizable and robust predictive models, which will improve their applicability in a variety of agricultural and environmental scenarios.

Paper Citation

in Harvard Style

Koné B., Grati R., Bouaziz B., Boukadi K. and Mecella M. (2025). Optimized and Explainable Feature Selection for Soil Moisture Prediction Across Sites. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 213-222. DOI: 10.5220/0013646000003967

in Bibtex Style

@conference{data25,
author={Bamory Koné and Rima Grati and Bassem Bouaziz and Khouloud Boukadi and Massimo Mecella},
title={Optimized and Explainable Feature Selection for Soil Moisture Prediction Across Sites},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={213-222},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013646000003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Optimized and Explainable Feature Selection for Soil Moisture Prediction Across Sites
SN - 978-989-758-758-0
AU - Koné B.
AU - Grati R.
AU - Bouaziz B.
AU - Boukadi K.
AU - Mecella M.
PY - 2025
SP - 213
EP - 222
DO - 10.5220/0013646000003967
PB - SciTePress