Soil salinization severely restricts the development of global industry and agriculture and affects human beings. In the arid area of Northwest China, oasis saline-alkali land threatens the development of agriculture and food security. This paper develops and optimizes an inversion monitoring model for monitoring the soil salt content using unmanned aerial vehicle (UAV) multispectral remote sensing data. Using the multispectral remote sensing data in three research areas, the soil salt inversion models based on the support vector machine regression (SVR), random forest (RF), backpropagation neural network (BPNN), and extreme learning machine (ELM) were constructed. The results show that the four constructed models based on the spectral index can achieve good inversion accuracy, and the red edge band can effectively improve the soil salt inversion accuracy in saline-alkali land with vegetation cover. Based on the obtained results, for bare land, the best model for soil salt inversion is the ELM model, which reaches the determination coefficient (R_v²) of 0.707, the root mean square error RMSE_v of 0.290, and the performance deviation ratio (RPD) of 1.852 on the test dataset. However, for agricultural land with vegetation cover, the best model for soil salinity inversion using the vegetation index is the BPNN model, which achieves R_v² of 0.836, RMSE_v of 0.027, and RPD of 2.100 on the test dataset. This study provides technical support for rapid monitoring and inversion of soil salinization and salinization control in irrigation areas.

Rapid and accurate inversion of soil salinity is a key scientific problem that needs to be solved urgently. Due to the accuracy of UAV multispectral remote sensing inversion of salinity based on back propagation neural network (BPNN) is low, in this study, used the UAV multispectral image and field measurements of 60 soil surface salinity as data sources, 16 salinity indexs were constructed using the extracted spectral reflectance,and performed a grey relation analysis to screen salinity index features after applying a film removal to construct the BPNN salinity inversion model. Particle swarm optimization (PSO), thinking evolutionary algorithm (MEA) and genetic algorithm (GA) were applied to optimize the BPNNinverse model, respectively, and the optimization capabilities of the four algorithms were compared and evaluated to optimize the best optimization algorithm.The results showed that the GRA variable screening can effectively remove the redundant information of spectral parameters and reduce the complexity of salinity inversion model; ThePSO, MEA and GA can effectivelyimprove the robusticity of BPNNinversion model, and GA algorithm has the best optimization effect in terms of inverse model optimization effect, followed by MEA and PSO algorithms; The accuracy of the PSO-BPNN, MEA-BPNN and GA-BPNN inversion models are better than that of the BPNN model, and GA-BPNN is the best salinity inversion model, which achieves R2 of 0.6659, RMSE of 0.0751, and RPD of 2.0211. This approach can effectively solve salinity monitoring accuracy issues of UAV multispectral inversion.

Superabsorbent polymers (SAPs) are type of hydrogels capable to swell and absorb a large amount of water, but easily decomposed and oxidized by the air. We used electron-microscopic imaging in an indoor simulation with sand mulching to test the effects of various SAP concentrations on controlling evaporation and salt formation. The treatments were sand-mulched columns containing 0, 0.1, 0.2, 0.5 and 1.0% SAP. The soil particle pores were from dense to sparse and the corresponding fractal dimension decreased as SAP concentration increased. SAP concentration was correlated negatively with fractal dimension, clay-particle fraction and silt-volume fraction. And it showed a positive correlation with sand volume fraction. SAP concentration significantly affected the particle-size distribution. Water-storage capacity increased in each column layer (five 8-cm layers) at the same infiltration depth. Evaporation decreased the water content of each layer. Sand mulching combined with the SAP decreased evaporation in each layer relative to the control, which retained more water and decreased the accumulation of surface salt in the order 1.0% > 0.5% > 0.2% > 0.1% > 0. Salt migrated at 0–30 cm with sand mulching but 0–25 cm with sand mulching and SAP amendment. The decrease in salt accumulation was most effective at a SAP concentration of 0.2%.

This study aimed to investigate how the combination of texture information and spectral index affects the accuracy of the soil salinity inversion model. Taking the Bianwan Farm in Jiuquan City, Gansu Province, China as the research area, the multi-spectral data and soil salinity data at 0–15 cm, 15–30 cm and 30–50 cm depths in the sampling area under alfalfa coverage were collected, and spectral reflectance and texture features were obtained from a multispectral image. Moreover, the red-edge band was introduced to improve the spectral index, and gray correlation analysis was utilized to screen sensitive features. Five types of alfalfa-covered soil salinity machine learning inversion models based on random forest (RF) and extreme learning machine (ELM) algorithms were constructed, using the salinity index (SIs), vegetation index (VIs), salinity index + vegetation index (SIs + VIs), vegetation index + texture feature (VIs + TFs), and vegetation index + texture index (VIs + TIs). The determination coefficient R², root-mean-square error (RMSE) and mean absolute error (MAE) were used to evaluate each model’s performance. The results show that the VIs model is more accurate than the SIs and SIs +VIs models. Combining texture information with VIs improves the inversion accuracy, and the VIs + TIs model has the best inversion effect. From the perspective of inversion depth, the inversion effect for 0–15 cm soil salinity was significantly better than that for other depths, and was the best inversion depth under alfalfa cover. The average R² of the RF model was 10% higher than that of the ELM. The RF algorithm has high inversion accuracy and stability and performs better than ELM. These findings can serve as a theoretical basis for the efficient inversion of soil salinity and management of saline–alkali lands.