High-precision maps of soil organic carbon (SOC) are beneficial for managing soil fertility and understanding the global carbon cycle. Digital soil mapping plays an important role in efficiently obtaining the spatial distribution of SOC, which contributes to precision agriculture. However, traditional soil-forming factors (i.e., terrain or climatic factors) have weak variability in low-relief areas, such as plains, and cannot reflect the spatial variation of soil attributes. Meanwhile, vegetation cover hinders the acquisition of the direct information of farmland soil. Thus, useful environmental variables should be utilized for SOC prediction and the digital mapping of such areas. SOC has an important effect on crop growth status, and remote sensing data can record the apparent spectral characteristics of crops. The normalized difference vegetation index (NDVI) is an important index reflecting crop growth and biomass. This study used NDVI time series data rather than traditional soil-forming factors to map SOC. Honghu City, located in the middle of the Jianghan Plain, was selected as the study region, and the NDVI time series data extracted from Landsat 8 were used as the auxiliary variables. SOC maps were estimated through stepwise linear regression (SLR), partial least squares regression (PLSR), support vector machine (SVM), and artificial neural network (ANN). Ordinary kriging (OK) was used as the reference model, while root mean square error of prediction (RMSE_P) and coefficient of determination of prediction (R²_P) were used to evaluate the model performance. Results showed that SOC had a significant positive correlation in July and August (0.17, 0.29) and a significant negative correlation in January, April, and December (−0.23, −0.27, and −0.23) with NDVI time series data. The best model for SOC prediction was generated by ANN, with the lowest RMSE_P of 3.718 and highest R²_P of 0.391, followed by SVM (RMSE_P = 3.753, R²_P = 0.361) and PLSR (RMSE_P = 4.087, R²_P = 0.283). The SLR model was the worst model, with the lowest R²_P of 0.281 and highest RMSE_P of 3.930. ANN and SVM were better than OK (RMSE_P = 3.727, R²_P = 0.372), whereas PLSR and SLR were worse than OK. Moreover, the prediction results using single-data NDVI or short time series NDVI showed low accuracy. The effect of the terrain factor on SOC prediction represented unsatisfactory results. All these results indicated that the NDVI time series data can be used for SOC mapping in plain areas and that the ANN model can maximally extract additional associated information between NDVI time series data and SOC. This study presented an effective method to overcome the selection of auxiliary variables for digital soil mapping in plain areas when the soil was covered with vegetation. This finding indicated that the time series characteristics of NDVI were conducive for predicting SOC in plains.

Visible and near-infrared reflectance (VIS-NIR) spectroscopy is widely applied to estimate soil organic carbon (SOC). Intense and diverse human activities increase the heterogeneity in the relationships between SOC and VIS-NIR spectra in anthropogenic soil. This fact results in poor performance of SOC estimation models. To improve model accuracy and parsimony, we investigated the performance of two variable selection algorithms, namely competitive adaptive reweighted sampling (CARS) and random frog (RF), coupled with five spectral pretreatments. A total of 108 samples were collected from Jianghan Plain, China, with the SOC content and VIS-NIR spectra measured in the laboratory. Results showed that both CARS and RF coupled with partial least squares regression (PLSR) outperformed PLSR alone in terms of higher model accuracy and less spectral variables. It revealed that spectral variable selection could identify important spectral variables that account for the relationships between SOC and VIS-NIR spectra, thereby improving the accuracy and parsimony of PLSR models in anthropogenic soil. Our findings are of significant practical value to the SOC estimation in anthropogenic soil by VIS-NIR spectroscopy.

Accurate digital mapping of soil organic carbon (SOC) is important in understanding the global carbon cycle and its implications in mitigating climate change. Visible and near-infrared hyperspectral imaging technology provides an alternative for mapping SOC efficiently and accurately, especially at regional and global scales. However, there is a lack of understanding of the impacts of spatial resolution of hyperspectral images and spatial autocorrelation of spectral information on the accuracy of SOC retrievals. In this study, the hyperspectral images (380–1700 nm) with a spatial resolution of 1 m were acquired by Headwall Micro-Hyperspec airborne sensors. Then, hyperspectral images were resampled into three different spatial resolutions of 10 m, 30 m, and 60 m by near neighbor (NN), bilinear interpolation (BI), and cubic convolution (CC) resampling methods. The geographically weighted regression (GWR) model was used to explore the role of spatial autocorrelation in predicting SOC contrast with the partial least squares regression (PLSR) model. Results showed that (1) the hyperspectral images can be used to predict SOC and the spatial autocorrelation can improve the prediction accuracy, as the ratio of performance to interquartile range (RPIQ) values of PLSR and GWR were 1.957 and 2.003; (2) The SOC prediction accuracy decreased with the degradation of spatial resolution, and the RPIQ values of PLSR were from 1.957 to 1.134, and of GWR were from 2.003 to 1.136; (3) Three resampling methods had a much weaker influence than spatial resolution on SOC predictions because the differences of RPIQ values of NN, BI, and CC resampling methods were 0.146, 0.175, and 0.025 in the spatial resolutions of 10 m, 30 m, and 60 m, respectively; (4) Finally, the Global Moran’s I and the Anselin Local Moran’s I proved the existence of the spatial autocorrelation in SOC maps. We hope that this study can offer valuable information for digital soil mapping by satellite hyperspectral images in the near future.

The rapid monitoring and accurate estimation of dynamic changes in soil organic carbon (SOC) can make great efforts in understanding the global carbon cycle. Traditional field survey is the main approach to obtain soil data and measure SOC content. However, the limited number of soil samples and the sampling cost hinder the quality of digital soil mapping. This research aims to explore the sensitive of sampling density in digital soil mapping, and then design a suitable soil sampling plan based on a series of sampling indices. Headwall hyperspectral images (400–1700 nm) were used to estimate the SOC map by partial least squares regression (PLSR) and PLSR kriging (PLSRK). Three traditional soil sampling methods (random, grid, and Latin hypercube sampling) with 10 classes of sampling densities (6.26, 2.79, 1.57, 1.01, 0.69, 0.53, 0.39, 0.30, 0.26, and 0.20 ha⁻¹) were designed. The R², root mean square error (RMSE) and ratio of standard deviation to RMSE (RPD) were used to evaluate the prediction accuracy in digital soil mapping by ordinary kriging. Three new indices, namely, the ratio of sampling efficiency to performance (RSEP), the density of soil samples index and the comprehensive evaluation index of prediction accuracy, were used to select a suitable soil sampling plan. Results showed that (1) the prediction accuracy of PLSRK (RPD = 2.00) was higher by approximately 11.73% than that of PLSR (RPD = 1.79), and the hyperspectral images provided an actual referential SOC map for the study of soil sampling; (2) the grid sampling plan performed better than the random and Latin hypercube sampling methods, and the quality of SOC map improves with the increase of the sampling density, and (3) the computer simulation and field verification indicated that RSEP is one feasible index in designing a suitable soil sampling plan.

Accurate estimation of the water conservation is of great significance for ecological red line planning. The water conservation of the Yellow River Basin has a vital influence on the development of the environment and the supply of ecological services in China. However, the existing methods used to estimate water conservation have many disadvantages, such as requiring numerous parameters, a complex calculation model, and using data that is often difficult acquire. It is often hard to provide sufficiently precise parameters and data, resulting in a large amount of calculation time and the difficulties in the study of large scale and long time series. In this study, a time series of the Normalized Difference Vegetation Index (NDVI) was applied to estimate water conservation in two aspects using the idea of wholeness and stratification, respectively. The overall fitting results can explain nearly 30% of the water conservation by partial least squares regression and nearly 50% of it by a support vector machine. However, the results of a stratified simulation showed that water conservation and the NDVI have a certain stratified heterogeneity among different ecosystem types. The optimal fitting result was achieved in a water/wetland ecosystem with the highest coefficient of determination (R²_P) of 0.768 by the stratified support vector machine (SVM) model, followed by the forest and grassland ecosystem (both R²_P of 0.698). The spatial mapping results showed that this method was most suitable for grassland ecosystem, followed by forest ecosystem. According to the results generated using the NDVI time series data, it is feasible to complete a spatial simulation of water conservation. This research can provide a reference for calculating regional or large-scale water conservation and in ecological red line planning.