Mapping and monitoring land use (LU) changes is one of the most effective ways to understand and manage land transformation. The main objectives of this study were to classify LU using supervised classification methods and to assess the effectiveness of various machine learning methods. The current investigation was conducted in the Nord-Est area of Tunisia, and an optical satellite image covering the study area was acquired from Sentinel-2. For LU mapping, we tested three machine learning models algorithms: Random Forest (RF), K-Dimensional Trees K-Nearest Neighbors (KDTree-KNN) and Minimum Distance Classification (MDC). According to our research, the RF classification provided a better result than other classification models. RF classification exhibited the best values of overall accuracy, kappa, recall, precision and RMSE, with 99.54%, 0.98%, 0.98%, 0.98% and 0.23%, respectively. However, low precision was observed for the MDC method (RMSE = 1.15). The results were more intriguing since they highlighted the value of the bare soil index as a covariate for LU mapping. Our results suggest that Sentinel-2 combined with RF classification is efficient for creating a LU map.

In Tunisia, the agricultural sector faces multiple challenges that affect both productivity and farmers’ livelihoods. Although agroecology is increasingly recognized as a pathway to sustainable agriculture, the extent of its adoption by farmers remains unclear. This study assesses the agroecological performance of 50 farms in the Sbikha delegation of the Kairouan governorate (Central Tunisia), using the Tool for Agroecological Performance Evaluation (TAPE), developed by the FAO. This tool assesses how existing cropping systems align with the 10 principles of agroecology and explores their potential for further transition. The results reveal a modest level of agroecological adoption, averaging only 41%. Several factors influence this outcome, including limited farmer knowledge and technical capacity, a weak institutional and organizational framework, and low diversification of cropping systems. Furthermore, three types of farms were identified based on their production systems: farms specializing in fruit trees, farms specializing in cereal and vegetable crops, and farms specializing in olive and vegetable crops. Among these, fruit tree farms exhibit a higher level of agroecological transition, averaging 51%. This increased diversification enhances resilience to market fluctuations. To accelerate the agroecological transition, several key measures should be implemented. Updating land property titles would improve access to credit by enabling farmers to provide the necessary guarantees. Additionally, targeted training programs and awareness-raising initiatives could strengthen technical capacities, thereby facilitating the adoption of agroecological practices. These interventions would enhance farmers’ economic resilience, support sustainable agricultural production, and promote equitable rural development.