Texture features have been consistently overlooked in digital soil mapping, especially in soil salinization mapping. This study aims to clarify how to leverage texture information for monitoring soil salinization through remote sensing techniques. We propose a novel method for estimating soil salinity content (SSC) that combines spectral and texture information from unmanned aerial vehicle (UAV) images. Reflectance, spectral index, and one-dimensional (OD) texture features were extracted from UAV images. Building on the one-dimensional texture features, we constructed two-dimensional (TD) and three-dimensional (THD) texture indices. The technique of Recursive Feature Elimination (RFE) was used for feature selection. Models for soil salinity estimation were built using three distinct methodologies: Random Forest (RF), Partial Least Squares Regression (PLSR), and Convolutional Neural Network (CNN). Spatial distribution maps of soil salinity were then generated for each model. The effectiveness of the proposed method is confirmed through the utilization of 240 surface soil samples gathered from an arid region in northwest China, specifically in Xinjiang, characterized by sparse vegetation. Among all texture indices, TDT_eI₁ has the highest correlation with SSC (|r| = 0.86). After adding multidimensional texture information, the R² of the RF model increased from 0.76 to 0.90, with an improvement of 18%. Among the three models, the RF model outperforms PLSR and CNN. The RF model, which combines spectral and texture information (SOTT), achieves an R² of 0.90, RMSE of 5.13 g kg⁻¹, and RPD of 3.12. Texture information contributes 44.8% to the soil salinity prediction, with the contributions of TD and THD texture indices of 19.3% and 20.2%, respectively. This study confirms the great potential of introducing texture information for monitoring soil salinity in arid and semi-arid regions.

The rapid and efficient acquisition of field-scale farmland soil profile moisture-distribution information is very important for achieving precise irrigation and the adjustment and deployment of irrigation strategies in farmland. EM38-MK2 is a portable, non-invasive device that induces electric currents in soil to generate secondary magnetic fields for the rapid measurement of apparent electrical conductivity in the field. In this study, cotton fields were used as experimental objects to obtain soil apparent conductivity data for three periods, which were combined with soil-moisture content data collected simultaneously from soil samples and measured in the laboratory to construct an apparent soil-profile moisture regression model. A simple kriging interpolation method was used to map the distribution of the irrigation volume in the field, considering only the highest irrigation volume in the field as the maximum water-holding capacity in the field. The results showed that EM38 could accurately detect the spatial variation of soil moisture in the field. The R² of the linear fit between measured and predicted soil-water content ranged from 0.51 to 0.89; the RMSE ranged from 0.66 to 1.87; and the R² and RPD of each soil-layer water content model of the single-period model were higher than those of the full-period model. By plotting the distribution of field irrigation, it could be seen that by comparing the predicted field irrigation with the actual irrigation, at least 160 m³ ha⁻¹ of irrigation could be saved in all three periods at an irrigation depth of 40 cm, which is about 30% of the actual irrigation; at an irrigation depth of 60 cm, about 30% and 15% of irrigation could be reduced in July and August, respectively. There are three areas in the study area with high fixed-irrigation volumes located in the northwest corner, near 500 m in the northern half of the study area and 750 m east of the southern half of the study area. The results of this study proved that the use of EM38-MK2 to monitor and evaluate the soil-moisture content of the farmland at different periods can, to a certain extent, guide the irrigation amount needed to achieve efficient and precise irrigation in the field.