Desert Soil Salinity Inversion Models Based on Field In Situ Spectroscopy in Southern Xinjiang, China

Abstract

Soil salinization is prominent environmental issue in arid and semi-arid regions, such as Xinjiang in Northwest China. Salinization severely restricts economic and agricultural development and would lead to ecosystem degradation. Finding a method of rapidly and accurately determining soil salinity (SS) is one of the main challenges in salinity evaluation, saline soil development, and utilization. In situ visible and near infrared (Vis-NIR) spectroscopy has proven to be a promising technique for detecting soil properties since it can realize real-time, rapid detection of SS. However, it still remains challenging whether Vis-NIR in situ spectroscopy can invert SS with high accuracy due to the interference of environmental factors (e.g., light, water vapor, solar altitude angle, etc.) on the spectral in the field. To fill this knowledge gap, we collected Vis-NIR in situ spectral and lab-measured SS data from 135 surface soil samples in the Kongterik Pasture Nature Reserve (KPNR) in the desert oasis ecotone of southern Xinjiang, China. We used genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA) algorithms to select the feature bands of SS. Subsequently, we combined extreme learning machines (ELM), back-propagation neural networks (BPNN), and convolutional neural networks (CNN) to build inversion models of SS. The results showed that different feature bands selection methods could improve the Vis-NIR in situ spectral prediction model accuracy. Either SS inversion models were built using full-band spectral data or feature-band spectral data. Compared with the full-band (401–2400 nm) spectral modeling, the validation set R2 of ELM, BPNN, and CNN models built selected feature bands selected by PSO, GA, and SA, respectively, were improved by more than 0.06. The accuracy of predicting SS varied widely among modeling methods. The accuracy of CNN model was obviously higher than that of BPNN and ELM models. The optimal hybrid model for predicting SS constructed in this study is SA-CNN model (R2 = 0.79, RMSE = 9.41 g kg−1, RPD = 1.81, RPIQ = 2.37). This study showed that the spectral feature bands selection methods can reduce the influence of environmental factors on in situ spectroscopy and significantly enhance the inversion accuracy of SS. The present study provided that estimating SS using in situ Vis-NIR spectral is feasible.

Improving the Accuracy of Soil Organic Carbon Estimation: CWT-Random Frog-XGBoost as a Prerequisite Technique for In Situ Hyperspectral Analysis

“…Although the ACO algorithm had the highest number of feature bands, the average improvement capability (an improvement of 0.45) was lower than that of the PSO algorithm (an improvement of 0.48), which may be due to the interference of redundant information in the feature bands selected by the ACO algorithm. In contrast, Wang et al concluded that the accuracy improvement of SA was superior to that of PSO, which may be attributable to the fact that the initial temperature level affected the rate of convergence; therefore a reasonable selection of initial parameters is needed [47]. The feature bands based on the SPA algorithm were mainly distributed in the 400 to 607 nm range.…”

“…Among the three nonlinear machine learning models, XGBoost had a better anti-fitting function considering the complexity of the model, which improved the generalizability of the model. BPNN has a strong nonlinear mapping ability, which is attributable to its self-learning, self-organization, and self-adaptation ability, which could effectively make up for the deficiency of the linear model [47]. Compared with the first two models, RF is only a tree model.…”

Soil Salinity Mapping of Croplands in Arid Areas Based on the Soil–Land Inference Model

“…Land surface cover data: We selected the normalized difference vegetation Index (NDVI) as an environmental variable to characterize surface vegetation cover [44][45][46]. Saltaffected soils with crust formation have high reflectance in the near-infrared (NIR) band and have been widely used in remote sensing studies of soil salinization [47][48][49][50]. Therefore, we chose it as an environmental variable for inferring soil salinity.…”

Spatio-Temporal Variation Analysis of Soil Salinization in the Ougan-Kuqa River Oasis of China

“…In order to accurately estimate soil salinity, Mohamed et al [13] used the joint data to predict soil salinity and used the BPNN to select features that can help farmers in areas affected by soil salinization to better manage planting procedures and improve their land quality. Wang et al [14] used the CNN and SVM to predict soil salinity, which shows that the models have great potential for measuring. In light of this, feature selection algorithms emerge as a vital tool for identifying and choosing critical environmental covariates with a significant impact on salinity.…”