Search

Soil texture is a key physical property that affects the soil's ability to retain moisture and nutrients. As a result, it is of extreme importance to conduct remote sensing monitoring of soil texture. Songnen Plain is located in the black soil belt of Northeast China. The development of satellite imagery in remote sensing technology enables the rapid monitoring of large areas. This study aimed to map the surface soil texture of cultivated land in Songnen Plain using Sentinel-2 images and Random Forest (RF) algorithm. We conducted this study by collecting 354 topsoil (0–20 cm) samples in Songnen Plain and evaluating the effectiveness of the bands and spectral indices of Sentinel-2 images and RF algorithm in predicting soil texture (sand, silt, and clay fractions). The results demonstrated that the 16 covariates were moderately and highly correlated with soil texture. And, Band11 of Sentinel-2 images could be used as the corresponding band of soil texture. For sand fraction, the Sentinel-2 images and RF algorithm's Coefficient of Determination (R2) and Root Mean Square Error (RMSE) were 0.77 and 10.48%, respectively, and for silt fraction, they were 0.75 and 9.38%. Sand fraction decreased from southwest to northeast in Songnen Plain, while silt and clay fractions increased. We found that the Songnen Plain was affected by water erosion and wind erosion, in the northeast and southwest, respectively, providing reference for the implementation of Conservation Tillage policies. The outcome of the study can provide reference for future soil texture mapping with a high resolution. [ABSTRACT FROM AUTHOR]

Fast and accurate SOM estimation and spatial mapping are significant for cultivated land planning and management, crop growth monitoring, and soil carbon pool estimation. It is a key problem to construct a fast and efficient estimation model based on hyperspectral remote sensing image data to realize the inversion mapping of SOM in large areas. In order to solve the problem that the estimation accuracy is not high due to the influence of hyperspectral image quality and soil sample quantity during the estimation model construction, this study explored a method for constructing an estimation model of SOM contents based on a new stacking ensemble learning algorithm and hyperspectral images. Surface soil samples in Huangzhong County of Qinghai Province were collected, and their ZY1-02D hyperspectral remote sensing images were investigated. As input data, a feature band dataset was constructed using the Pearson correlation coefficient and successive projections algorithm. Based on the dataset, a new SOM estimation model under the stacking ensemble learning framework combined with heterogeneous models was developed by optimizing the combination of base and meta-learners. Finally, the spatial distribution map of SOM was plotted based on the result of the model over the study area. The result suggested that the input data quality of the estimation model is improved by constructing a feature band dataset. The multi-class ensemble learning estimation model with the combination strategy of the base and meta-learners has better predictive effects and stability than the single-algorithm and single-level ensemble models with homogeneous learners. The coefficient of determination is 0.829, the residual prediction deviation is 2.85, and the predictive set root mean square error is 1.953. The results can provide new ideas for estimating SOM content using hyperspectral images and ensemble learning algorithms, and serve as a reference for mapping large-scale SOM spatial distribution using space-borne hyperspectral images. [ABSTRACT FROM AUTHOR]

• Hydrothermal conditions and DEM play great effect on digital soil color class mapping. • Stepwise classification improves the accuracy of soil color mapping. • Soil color has an obvious relationship with SOM. Soil color is the most readily available soil property, soil scientists often use the Munsell system to describe soil color and to quickly understand the physical, chemical, and biological properties of soil through soil color variation. Currently, soil color mapping studies often rely on indirect acquisition of Munsell color data from soil spectral information. As a result, there may be some discrepancies between the mapped colors and the colors perceived by humans. In this study, we collected 880 dry and 827 moist Munsell samples from the Northeast China to test the method developed for soil color mapping. We selected a set of covariates (climate, topography, evapotranspiration, regolith thickness, and remote sensing images) for digital soil color mapping, these covariates were related to soil formation or organic matter accumulation processes. Finally, the dry and moist topsoil color mapping with 30-m resolution was obtained for cropland in Northeast China. These covariates all played positive roles in the soil classification process, among which annual temperature mean (MAT), mean annual precipitation (MAP), land surface temperature (LST), and mean annual potential evapotranspiration (MAPET) had the highest contribution. We summarized the difficulties that usually occur in soil color mapping, and put forward a 'stepwise classification' method. According to the three-dimensional attributes of the Munsell system, the measured color data were divided into seven color groups (four dry and three moist color groups). Among all color groups, the highest accuracy of mapping validation was 0.69 and the lowest was 0.58. The kappa coefficient, usually affected by classification bias, was small (0.3). The color differences between measured and predicted colors were found to be 1.21 (dry color) and 1.36 (moist color). Compared to direct classification, the stepwise classification method improved classification accuracy and reduced mapping color differences. Our soil color mapping for two cases of dry and moist corresponded well with spectral color maps. The correlation between soil organic matter (SOM) content and soil color (dry and moist) was analyzed in 807 samples. The darker the soil color was, the higher the SOM content was. In summary, soil color holds the potential to serve as a surrogate for assessing cropland quality, particularly in evaluating SOM. [ABSTRACT FROM AUTHOR]