The phenomenon of soil salinization in semi-arid regions is getting amplified and accentuated by both anthropogenic practices and climate change. Land salinization mapping and monitoring using conventional strategies are insufficient and difficult. Our work aims to study the potential of synthetic aperture radar (SAR) for mapping and monitoring of the spatio-temporal dynamics of soil salinity using interferometry. Our contribution in this paper consists of a statistical relationship that we establish between field salinity measurement and InSAR coherence based on an empirical analysis. For experimental validation, two sites were selected: 1) the region of Mahdia (central Tunisia) and 2) the plain of Tadla (central Morocco). Both sites underwent three ground campaigns simultaneously with three Radarsat-2 SAR image acquisitions. The results show that it is possible to estimate the temporal change in soil electrical conductivity (EC) from SAR images through the InSAR technique. It has been shown that the radar signal is more sensitive to soil salinity in HH polarization using a small incidence angle. However, for the HV polarization, a large angle of incidence is more suitable. This is, under considering the minimal influence of roughness and moisture surfaces, for a given InSAR coherence.
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.
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.