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.

Treated wastewater (TWW) is considered as an alternative for agricultural irrigation. The aim of this study was to understand the medium- and long-term effects of TWW on soil physicochemical parameters. Two perimeters (P₁ and P₂)receiving TWW for 38 and 20 years, respectively, in Tunisiawere selected for study. In each perimeter, two water types were adopted: TWW and groundwater (GW). Soil physicochemical traits (pH, EC, and concentrations of Na⁺, K⁺, Ca²⁺, and Mg²⁺) were measured up to 100 cm, and three indexes were calculated: sodium adsorption ratio (SAR), cation ratio of structural stability (CROSS), and cation exchange capacity (CEC). Overall, all soil parameters were significantly affected in the irrigation area using GW. However, in the case of TWW, only the pH was found to be affected, increasing by 4.7% from P₁ to P₂. Moreover, compared to GW, TWW enhanced the soil salinity by 127%, particularly at deeper subsoils. More interestingly, the results revealed an accumulation of Mg²⁺, Ca²⁺, and K⁺ and a depletion of Na⁺ at the soil surface. Notably, TWW showed the lowest CROSS and SAR indexes, indicating the benefits of applying TWW even after long-term use in improving soil physicochemical parameters such as sodicity and structural stability. Our results provide valuable information for decision-makers to use wastewater in irrigated marginal soils.

Understanding the relationship between durum wheat genotypes and soil biochemistry under salt stress plays a key role in breeding for yield superior genotypes. Thus, microbial biomass carbon (MBC) and nitrogen (MBN), the activity of three selected enzymes including dehydrogenase (D-ase), alkaline phosphatase (Alk-ase) and protease (P-ase), and available phosphorus (available P) and nitrogen (available N) were assessed. Two landraces and two improved varieties were tested under two salinity levels of water irrigation (0.3 and 12 dS m–1). Soil sampling was carried out at five durum wheat growth stages. The soil biota-genotype interaction seems to affect the biological (MBC, MBN, and enzymatic activities) and chemical (available P and N) traits. The microbial activity of rhizospheric soil was higher at the tillering and flowering stages. Under saline conditions, ‘Maali’ (improved variety) and ‘Agili Glabre’ (landrace) showed the best belowground inputs (e.g., MBC, MBN, enzymatic activities, available P and N) and grain yield (GY) performance. Under the same conditions, four soil biochemical indicators of GY of tolerant genotypes (i.e., ‘Maali’ and ‘Agili Glabre’) were determined as: available N, P-ase, available P, Alk-ase, and D-ase. Stepwise analysis revealed that predictive variables depended on growth stages. Overall, MBC, available N, Alk-ase, and P-ase were the variables that contributed mostly to predicting GY in saline environments. In conclusion, the results suggested a specific interaction between plant genotype roots and soil microbes to overcome salt stress. Thus, soil biological components should acquire more importance in plant salinity tolerance studies. Highlights - Salt-tolerant durum wheat genotypes showed greater microbial activities in the rhizosphere. - Microbial enzymatic changes depended on the interaction plant genotype × soil salinity. - The MBC/MBN ratio and dehydrogenase strongly correlated with grain yield under salinity. - MBC, available N, and alkaline phosphatase as predictors of grain yield at 12 dS m–1. - Tillering and flowering could be key stages of durum wheat salinity tolerance.

The improvement of soil fertility properties is a priority for meeting sustainable development goals and world food security. One potential benefit of using paper sludge in agriculture is the reduction of waste and associated environmental impacts. By using paper sludge as a soil amendment, it is possible to divert away this material from landfills and instead use it to improve soil fertility and support the growth of crops. However, it is important to note that paper sludge may contain contaminants harmful to plants and soil health, of which earthworm viability serves as a key indicator. The present investigation aimed to evaluate changes in soil properties after the application of raw and composted de-inking paper sludge for two years. Accordingly, a field study was conducted in Manouba, a semi-arid region of Tunisia with a clay loam soil. The raw de-inking sludge (DS) and composted de-inking paper sludge (DSC) were applied at 30 and 60 t ha⁻¹ and 20 and 40 t ha⁻¹, respectively. Soil treatments were compared to unamended soils (C), to determine the optimal sludge treatment and rate for increasing the soil quality. Soil chemical (soil organic matter SOM, total carbon TC, and nitrogen TN, nutrient soil contents organic matter fractioned), physical (porosity and structural stability), and biological parameters (earthworms viability) were assessed. The results showed an increase of soil OM in the DS and DSC amended soils with the lowest rates (30 and 20 t ha⁻¹). The humic fraction was found to be the dominant form. TC and TN were improved in the DS and DSC amended soils with the highest rates: 60 (DS2) and 40 t ha⁻¹ (DSC2). Phosphorus and potassium were also increased in a dose-dependent manner. However, the soil porosity decreased in all treatments. The composted de-inking sludge was toxic for epigeic species, which could be explained by the use of litter while composting. Overall, the application of DS and DSC at low rates (30 and 20 t ha⁻¹, respectively) might be a promising alternative for improving soil quality and at the same time ensuring the proper management of these wastes.

This study evaluated the effects of de-inking paper sludge (DPS) and sewage sludge (SS) application on soil properties, and durum wheat growth and yield. A pot experiment was performed on Calcaric cambisol (clCM) and Cromic Luvisol (coLV) soils. Three DPS rates (0, 30, and 60 Mg ha⁻¹) were studied with and without nitrogen fertilizer (280 kg NH₄NO₃ ha⁻¹). DPS was also mixed with SS at two rates (5 and 10 Mg ha⁻¹) to highlight the benefits of organic nitrogen compared to mineral nitrogen. DPS improved total organic carbon and nitrogen, mineral nitrogen, and soils cation exchange capacity, the 30% rate provided the greatest improvement in both soils. DPS increased grain and root P, K, Ca, and Mg contents in both soils. It also increased wheat straw N, P, Mg, and Ca for the same soil compared to the control. Mixed DPS treatments with nitrogen fertilizer enhanced grain yield by up to 38% and increased root biomass in the studied soils. Thus, DPS is a potential source of organic matter and a liming agent for acid soils when appropriate supplemental fertilizer is provided.