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.

Addressing the gaps between theory, research and practice, this paper explores a hybrid mindset of participatory action research (PAR), geoprospective and participatory geographical information system (PGIS). This approach brings together stakeholders, policy-makers and researchers – in an agricultural peri-urban region of Portugal, the Lezíria do Tejo region – to anticipate the possible changes in agricultural territories, while taking spatial dynamics into account. It uses a four-step methodology which integrates qualitative and quantitative approaches to select stakeholders’ interview areas, implement prospective workshops to engage and explore the stakeholders’ interests and encourage actions towards finding solutions for long-term agricultural sustainability in this region. The results from our study highlight that more participative approaches such as the ones developed here must be implemented towards decision-making, since they help to dispel the distrust between stakeholders, strengthen community cohesion and also contribute to build common solutions drawing upon various perspectives. From a PAR perspective, this work contributes to bridge the gap between academia and practitioners, as is shown by a willingness of the practitioners to actively participate in the research under progress.