Soil organic carbon (SOC) plays an important role in the global carbon cycle and soil fertility supply. Rapid and accurate estimation of SOC content could provide critical information for crop production, soil management and soil carbon pool regulation. Many researchers have confirmed the feasibility and great potential of visible and near-infrared (Vis-NIR) spectroscopy in evaluating SOC content rapidly and accurately. Here, to evaluate the feasibility of different spectral bands variable selection methods for SOC prediction, we collected a total of 330 surface soil samples from the cotton field in the Alar Reclamation area in the southern part of Xinjiang, which is located in the arid region of northwest China. Then, we estimated the SOC content using laboratory Vis-NIR spectral. The Particle Swarm optimization (PSO), Competitive adaptive reweighted sampling (CARS) and Ant colony optimization (ACO) were adopted to select SOC feature bands. The partial least squares regression (PLSR), random forest (RF) and convolutional neural network (CNN) inversion models were constructed by using full-bands (400–2400 nm) spectra (R) and feature bands, respectively. And we also analyzed the effects of spectral feature band selection methods and modeling methods on the prediction accuracy of SOC. The results indicated that: (1) There are significant differences in the feature bands selected using different methods. The feature bands selected methods substantially reduced the spectral variable dimensionality and model complexity. The models built by the feature bands selected by CARS, PSO and ACO methods showed the different potential of improvement in model accuracy compared with the full-band models. (2) The CNN model had the best performance for predicting SOC. The R² of the optimal CNN model is 0.90 in the validation, which was improved by 0.05 and 0.04 in comparison with the PLSR and RF model, respectively. (3) The highest prediction accuracy was archived by the CNN model using the feature bands selected by CARS (validation set R² = 0.90, RMSE = 0.97 g kg⁻¹, RPD = 3.18, RPIQ = 3.11). This study indicated that using the CARS method to select spectral feature bands, combined with the CNN modeling method can well predict SOC content with higher accuracy.

A strong canopy structure is central to maximizing yield. The canopy microenvironment, which is related to crop growth and development, reflects changes in a crop’s microclimate. In this study, with the uniform sowing of winter wheat (Triticun aestivum L.), five planting densities (in 10⁴ plants·ha⁻¹: 123, 156, 204, 278, and 400) were established to examine how the planting density affected filling stage spikes, canopy structures, microenvironments, yields, and yield components. The large-spike Xindong 50 and multi-spike Sangtamu 4 varieties were used. The experiment was conducted over 263 days in the Xinjiang province, in a warm continental arid desert-type climate, with low precipitation. The study aimed to determine the optimal parameters for cultivation on limited land and improve the production potential. For both varieties, from anthesis to filling, increases in planting density were associated with a rapid reduction in the leaf area index of the lower and middle parts of the leaves. Canopy temperature and canopy CO₂ concentration also decreased, whereas relative humidity increased. The number of grains per spike and the thousand-grain weight of both varieties decreased with increased planting density. Yields were maximized at densities of 278 × 10⁴ and 156 × 10⁴ plants·ha⁻¹ for the large- and multi-spike varieties, respectively, indicating that uniform sowing improves plant uniformity, and adjusting planting density optimizes canopy structure and microenvironment. Our study provides valuable data for optimizing planting densities to ensure high yields.

Soil organic matter (SOM) is a key factor for evaluating soil fertility. Rapidly monitoring organic matter content in desert soil can provide a scientific basis for the rational development and utilization of reserve arable land resources. Although spectral inversion accuracy for SOM under laboratory-controlled conditions is high, it is time-consuming and costly compared to the in situ spectroscopic determination method. However, in situ spectroscopy causes losses in accuracy due to interference from external environmental factors (e.g., the surface roughness of soil, changes in weather conditions, atmospheric water vapor, etc.). Therefore, reducing or removing the interference of external environmental factors to improve the accuracy of in situ spectroscopy for estimating SOM is challenging. In this study, visible and near-infrared (Vis-NIR) in situ spectral data were collected from 135 topsoil (0–20 cm) samples in a desert area of northwestern China, and organic matter content was measured. Three spectral pre-processing methods—the standard normal transform (SNV), reciprocal logarithm (log(1/R)) and normalization (NOR)—combined with three feature variable selection methods—the particle swarm algorithm (PSO), ant colony algorithm (ACO) and simulated annealing (SA) algorithm—were used to filter the spectral feature bands of SOM, and then partial least squares regression (PLSR), a back propagation neural network (BPNN) and a convolutional neural network (CNN) were used to construct the estimation models of SOM. The results indicated that the SNV could enhance the spectral information related to SOM and improve the accuracy of model estimation, and it was one of the most effective spectral pretreatment methods. Compared with the model constructed with the full-band spectroscopy method, the feature variable selection method could effectively improve the estimation accuracy of the Vis-NIR in situ spectroscopy model. The most obvious improvement was found with PSO, where R² and RPD were improved by more than 0.34 and 0.16, respectively, and RMSE was reduced by more than 0.29 g kg⁻¹. The accuracy of the CNN model was higher than that of the BPNN and PLSR models, both for the inversion model of SOM built from full-band spectral data and the bands selected by the characteristic variable selection method. SNV-PSO-CNN is the optimal hybrid model for in situ spectral measurement of SOM (R² = 0.71, RPD = 1.88, RMSE = 1.67 g kg⁻¹) and can realize the quantitative in situ spectral inversion of SOM in desert soils.

The root system is the only vital organ for plants to connect with soil moisture and nutrients and obtain feedback information. This research aimed to explore the response of different spike type winter wheat varieties to plant and row spacing configurations. Multi-spike and large-spike winter wheat varieties were used as materials. By setting different plant row configurations and planting densities, the spatial and temporal distribution of root length density, root diameter, root dry weight density, and the main control factors of root growth and development of winter wheat during the whole growth period were studied. The results showed that the root system was the most widely distributed and the root diameter was the largest in the 0–40 cm soil depth, with an average root system diameter of more than 0.5 mm. The root length density and root diameter peaked at the heading stage, decreased at the maturity stage, and the root dry weight density peaked at the jointing stage. The jointing stage and heading stage are the most vigorous periods of root growth in winter wheat, when the center of gravity of root growth in winter wheat is gradually moving down. Therefore, the rapid growth and elongation time of a root system can be effectively prolonged at the jointing stage and heading stage, and the root growth rate can be improved. Promoting root thickening can effectively meet the needs for water and nutrients, for the formation and filling of aboveground plants and grains, in the later stage, which is conducive to the formation of aboveground dry matter production and final yield. The root distribution was greatest in the 0–60 cm soil depth, accounting for 95.13–97.84% of the total root length. After the heading stage occurs, the upper roots begin to decline in large quantities. Thus, the jointing stage and heading stage require fertilization and other farmland management operations to increase root nutrients for the ground parts and dry matter accumulation to provide sufficient nutrients so that the number of effective panicles, grain weight, and the number of spike grains coordinate to achieve the highest grain yield. Results showed that the highest yield can be achieved with the planting pattern X2M1. A comprehensive analysis showed that the genetic characteristics of winter wheat varieties were different, and there were some differences in the correlation between wheat yield and root system at the different growth stages. The correlation between the root parameters and yield of multi-spike winter wheat during the overwintering-jointing stage was obvious. For large-spike type winter wheat in the jointing stage, the yield correlation is most obvious.

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.

Soil salinization is a major obstacle to land productivity, crop yield and crop quality in arid areas and directly affects food security. Soil profile salt data are key for accurately determining irrigation volumes. To explore the potential for using Landsat 8 time-series data to monitor soil salinization, 172 Landsat 8 images from 2013 to 2019 were obtained from the Alar Reclamation Area of Xinjiang, northwest China. The multiyear extreme dataset was synthesized from the annual maximum or minimum values of 16 vegetation indices, which were combined with the soil conductivity of 540 samples from soil profiles at 0~0.375 m, 0~0.75 m and 0~1.00 m depths in 30 cotton fields with varying degrees of salinization as investigated by EM38-MK2. Three remote sensing monitoring models for soil conductivity at different depths were constructed using the Cubist method, and digital mapping was carried out. The results showed that the Cubist model of soil profile electrical conductivity from 0 to 0.375 m, 0 to 0.75 m and 0 to 1.00 m showed high prediction accuracy, and the determination coefficients of the prediction set were 0.80, 0.74 and 0.72, respectively. Therefore, it is feasible to use a multiyear extreme value for the vegetation index combined with a Cubist modeling method to monitor soil profile salinization at a regional scale.