Machine Learning-Based Soil Moisture Prediction Using Meteorological Data for Enhanced Irrigation Management

¹ Abbes Laghrour University, Khenchela, Algeria
² Laboratoire Systèmes et Applications des Technologies de l’Information et des Télécommunications (SATIT), Abbes Laghrour University, Khenchela, Algeria
³ ECAM-EPMI, LR2E Laboratory, 13 bd de l’Hautil, 95092, Cergy-Pontoise, France
⁴ Electronics Department, Faculty of Technology, Badji Mokhtar-Annaba University, Annaba 23000, Algeria
⁵ Laboratoire des Télécommunications (LT), Institut des Télécommunications, 8 Mai 1945 – Guelma University, Guelma, Algeria

^* e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Irrigation management is critical in smart farming, particularly in Algeria, where palm dates are the principal crop produced and exported. The accuracy of soil moisture metrics is essential for effective irrigation. While sensors are frequently used to get accurate measurements, their dependability can be jeopardised by faults or absence owing to non-installation. This research introduces a machine learning-based prediction approach for estimating soil moisture levels using weather forecasting data. This method is used as an alternative to sensors to provide constant and optimal irrigation techniques in palm date agriculture.