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.
Land suitability maps are useful tools for protecting soil resources. The main objective of this study was to elaborate and assess soil suitability maps for different rainfed and irrigated crops. This study was conducted in the North-East area of Tunisia, three speculations were adopted (Cereals, arboriculture and vegetable crops) in both rainfed and irrigated conditions. Arithmetic multiplication methods were used based on Food and Agriculture Organization (FAO) classification based on Free and Open Source Geographic Information System (QGIS) tools and soil pedological properties, slope, elevation and climatic data. Overall, regardless of rainfed or irrigated conditions, results showed that the studied soils were particularly suitable (S1) for cereals crops and marginal suitable (S3) for arboriculture crops with 20.44 and 23.71%, respectively. More particular, we registered an improvement in soil land suitability under irrigated conditions for cereals with 28.63%. The findings indicated that using the GIS system, the soil in the study area is more suitable for cereals and then for arboriculture under irrigated conditions, which requires some improvement in use strategies and good management of the soil resources. In our study area, where agricultural productivity and environmental and the impact of climate change are in a struggle, classifying land on the basis of soil capacity and suitability could help define the best agricultural practices to apply in order to preserve soil functions could help define the best agricultural practices to be applied in order to preserve soil functions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.