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.

The use of deinking paper sludge (DPS) as a fertilizer instead of sending it to landfill could play a role in reducing greenhouse gases and improving soil properties. The objectives of this study were (1) to evaluate the changes in the physical (permeability and structural stability), chemical (particularly soil pH), and biological (microbial metabolic quotient (qCO₂), microbial biomass soil CO₂ emissions) of a calcareous agricultural soil following two successive annual amendments with three treatments (0, 30, and 60 Mg DPS ha⁻¹—control, DPS30, and DPS60, respectively); and (2) to determine whether the addition of N-fertilizer to these treatments (controlF, DPS30F, and DPS60F, respectively) causes changes to soil fertility. The DPS application increased soil organic matter (+0.80%: DPS60 vs. control; and +0.35%: controlF vs. DPS60F), available phosphorus (+23.14 mg kg⁻¹: DPS60 vs. control; and +14.34 mg kg⁻¹: DPS60F vs. controlF), potassium (+0.6 g kg⁻¹: controlF vs. DPS30F), and calcium (+0.28 g kg⁻¹: DPS60 vs. control). The 60 Mg DPS ha⁻¹ rate improved permeability and structural stability, regardless of the presence or absence of N-fertilizer. On the other hand, the 60 Mg DPS ha⁻¹ rate without N-fertilizer lead to a decrease in total mineralization rate and qCO₂, thereby indicating a reduction in CO₂ emissions. The rate of 60 Mg ha⁻¹ DPS could be effectively used to enhance the permeability and stability (soil restoration) and mitigate CO₂ emissions, whereas the 30 Mg ha⁻¹ rate could be used as fertilizer to improve the fertility of calcareous soils.