Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data

Abstract

Monitoring soil tillage activities, such as plowing and cultivating, is essential for aligning agricultural practices with environmental standards for soil health. Detecting these activities presents significant challenges, especially when relying on remotely sensed data. This paper addresses these challenges within the framework of the Common Agricultural Policy (CAP), which requires EU countries to enhance their environmental monitoring and climate action efforts. We used remote sensing data from Sentinel-1 and Sentinel-2 missions to detect soil tillage practices in 73 test farms in Portugal. Three approaches were explored: a rule-based method and two machine learning techniques based on XGBoost (XGB). One machine learning approach utilized the original imbalanced dataset, while the other employed a SMOTE (Synthetic Minority Oversampling Technique) approach to balance underrepresented soil tillage operations within the training set. Our findings highlight the inherent difficulty in detecting soil tillage operations across all methods, though the XGB-SMOTE approach demonstrated the most promising results, achieving a recall of 67% and an AUC-ROC (area under the receiver operating characteristic curve) of 74%. These results underscore the need for further research to develop a fully automated detection model. This work has potential applications for monitoring compliance with CAP mandates and informing environmental policy to better support sustainable agricultural practices.