Nan Wang

Despite extensive use of Sentinel-2 (S-2) data for mapping soil organic carbon (SOC), how to fully mine the potential of time-series S-2 data still remains unclear. To fill this gap, this study introduced an innovative approach for mining time-series data. Using 200 top soil organic carbon samples as an example, we revealed temporal variation patterns in the correlation between SOC and time-series S-2 data and subsequently identified the optimal monitoring time window for SOC. The integration of environmental covariates with multiple ensemble models enabled precise mapping of SOC in the arid region of southern Xinjiang, China (6109 km²). Our results indicated the following: (a) the correlation between SOC and time-series S-2 data exhibited both interannual and monthly variations, while July to August is the optimal monitoring time window for SOC; (b) adding soil properties and S-2 texture information could greatly improve the accuracy of SOC prediction models. Soil properties and S-2 texture information contribute 8.85% and 61.78% to the best model, respectively; (c) among different ensemble models, the stacking ensemble model outperformed both the weight averaging and sample averaging ensemble models in terms of prediction performance. Therefore, our study proved that mining spectral and texture information from the optimal monitoring time window, integrated with environmental covariates and ensemble models, has a high potential for accurate SOC mapping.

Digital soil organic carbon (SOC) mapping is used for ecological protection and addressing global climate change. Sentinel-1 (S-1) microwave radar remote sensing data offer critical insights into SOC dynamics through tracking variations in soil moisture and vegetation characteristics. Despite extensive studies using S-1 data for SOC mapping, most focus on either single or multi-date periods without achieving satisfactory results. Few studies have investigated the potential of time-series S-1 data for high-accuracy SOC mapping. This study utilized S-1 data from 2017 to 2021 to analyze temporal variations in the correlation between SOC and time-series S-1 data in southern Xinjiang, China. The primary objective was to determine the optimal monitoring period for SOC. Within this period, optimal feature subsets were extracted using variable selection algorithms. The performance of the partial least squares regression, random forest, and convolutional neural network–long short-term memory (CNN-LSTM) models was evaluated using a 10-fold cross-validation approach. The findings revealed the following: (1) The correlation between time-series S-1 data and SOC exhibited both interannual and monthly variations, with the optimal monitoring period from July to October. The data volume was reduced by 73.27% relative to the initial time-series dataset when the optimal monitoring period was determined. (2) Introducing time-series S-1 data into SOC mapping significantly improved CNN-LSTM model performance (R² = 0.80, RPD = 2.24, RMSE = 1.11 g kg⁻¹). Compared to models using single-date (R² = 0.23) and multi-date (R² = 0.33) data, the R² increased by 0.57 and 0.47, respectively. (3) The newly developed vertical–horizontal maximum and mean annual cumulative indices made a significant contribution (17.93%) to mapping SOC. Therefore, integrating the optimal monitoring period, feature selection, and deep learning model offers significant potential for enhancing the accuracy of digital SOC mapping.

Accurate digital soil organic carbon mapping is of great significance for regulating the global carbon cycle and addressing climate change. With the advent of the remote sensing big data era, multi-source and multi-temporal remote sensing techniques have been extensively applied in Earth observation. However, how to fully mine multi-source remote sensing time-series data for high-accuracy digital SOC mapping remains a key challenge. To address this challenge, this study introduced a new idea for mining multi-source remote sensing time-series data. We used 413 topsoil organic carbon samples from southern Xinjiang, China, as an example. By mining multi-source (Sentinel-1/2) remote sensing time-series data from 2017 to 2023, we revealed the temporal variation pattern of the correlation between Sentinel-1/2 time-series data and SOC, thereby identifying the optimal time window for monitoring SOC using Sentinel-1/2 data. By integrating environmental covariates and a super ensemble model, we achieved high-accuracy mapping of SOC in Southern Xinjiang, China. The results showed the following aspects: (1) The optimal time windows for monitoring SOC using Sentinel-1/2 data were July–September and July–August, respectively; (2) the modeling accuracy using multi-source sensor data integrated with environmental covariates was superior to using single-source sensor data integrated with environmental covariates alone. In the optimal model based on multi-source data, the cumulative contribution rate of Sentinel-2 data is 51.71% higher than that of Sentinel-1 data; (3) the stacking super ensemble model’s predictive performance outperformed the weight average and simple average ensemble models. Therefore, mining the optimal time windows of multi-source remote sensing data and environmental covariates, driven a super ensemble model, represents a high-accuracy strategy for digital SOC mapping.

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.

Unsustainable human management has negative effects on cropland soil organic carbon (SOC), causing a decrease in soil health and the emission of greenhouse gas. Due to contiguous fields, large-scale mechanized operations are widely used in the Northeast China Plain, which greatly improves production efficiency while decreasing the soil quality, especially for SOC. Therefore, an up-to-date SOC map is needed to estimate soil health after long-term cultivation to inform better land management. Using Quantile Regression Forest, a total of 396 soil samples from 132 sampling sites at three soil depth intervals and 40 environmental covariates (e.g., Landsat 8 spectral indices, and WorldClim 2 and MODIS products) selected by the Boruta feature selection algorithm were used to map the spatial distribution of SOC in the cropland of the Northeast Plain at a 90 m spatial resolution. The results showed that SOC increased overall from the southern area to the northern area, with an average of 17.34 g kg⁻¹ in the plough layer (PL) and 13.92 g kg⁻¹ in the compacted layer (CL). At the vertical scale, SOC decreased, with depths getting deeper. The average decrease in SOC from PL to CL was 3.41 g kg⁻¹. Climate (i.e., average temperature, daytime and nighttime land surface temperature, and mean temperature of driest quarter) was the dominant controlling factor, followed by position (i.e., oblique geographic coordinate at 105°), and organism (i.e., the average and variance of net primary productivity in the non-crop period). The average uncertainty was 1.04 in the PL and 1.07 in the CL. The high uncertainty appeared in the area with relatively scattered fields, high altitudes, and complex landforms. This study updated the 90 m resolution cropland SOC maps at spatial and vertical scales, which clarifies the influence of mechanized operations and provides a reference for soil conservation policy-making.

The rapid and efficient acquisition of field-scale farmland soil profile moisture-distribution information is very important for achieving precise irrigation and the adjustment and deployment of irrigation strategies in farmland. EM38-MK2 is a portable, non-invasive device that induces electric currents in soil to generate secondary magnetic fields for the rapid measurement of apparent electrical conductivity in the field. In this study, cotton fields were used as experimental objects to obtain soil apparent conductivity data for three periods, which were combined with soil-moisture content data collected simultaneously from soil samples and measured in the laboratory to construct an apparent soil-profile moisture regression model. A simple kriging interpolation method was used to map the distribution of the irrigation volume in the field, considering only the highest irrigation volume in the field as the maximum water-holding capacity in the field. The results showed that EM38 could accurately detect the spatial variation of soil moisture in the field. The R² of the linear fit between measured and predicted soil-water content ranged from 0.51 to 0.89; the RMSE ranged from 0.66 to 1.87; and the R² and RPD of each soil-layer water content model of the single-period model were higher than those of the full-period model. By plotting the distribution of field irrigation, it could be seen that by comparing the predicted field irrigation with the actual irrigation, at least 160 m³ ha⁻¹ of irrigation could be saved in all three periods at an irrigation depth of 40 cm, which is about 30% of the actual irrigation; at an irrigation depth of 60 cm, about 30% and 15% of irrigation could be reduced in July and August, respectively. There are three areas in the study area with high fixed-irrigation volumes located in the northwest corner, near 500 m in the northern half of the study area and 750 m east of the southern half of the study area. The results of this study proved that the use of EM38-MK2 to monitor and evaluate the soil-moisture content of the farmland at different periods can, to a certain extent, guide the irrigation amount needed to achieve efficient and precise irrigation in the field.

Soil salinization is one of the major degradation processes threatening food security and sustainable development. Detailed soil salinity information is increasingly needed to tackle this global challenge for improving soil management. Soil-visible and near-infrared (Vis-NIR) spectroscopy has been proven to be a potential solution for estimating soil-salinity-related information (i.e., electrical conductivity, EC) rapidly and cost-effectively. However, previous studies were mainly conducted at the field, regional, or national scale, so the potential application of Vis-NIR spectroscopy at a global scale needs further investigation. Based on an extensive open global soil spectral library (61,486 samples with both EC and Vis-NIR spectra), we compared four spectral predictive models (PLSR, Cubist, Random Forests, and XGBoost) in estimating EC. Our results indicated that XGBoost had the best model performance (R² of 0.59, RMSE of 1.96 dS m⁻¹) in predicting EC at a global scale, whereas PLSR had a relatively limited ability (R² of 0.39, RMSE of 2.41 dS m⁻¹). The results also showed that auxiliary environmental covariates (i.e., coordinates, elevation, climatic variables) could greatly improve EC prediction accuracy by the four models, and the XGBoost performed best (R² of 0.71, RMSE of 1.65 dS m⁻¹). The outcomes of this study provide a valuable reference for improving broad-scale soil salinity prediction by the coupling of the spectroscopic technique and easily obtainable environmental covariates.

Calibration and reconstruction of time series DMSP-OLS nighttime light images are critical for understanding urbanization processes and the evolution of urban spatial patterns from a unique perspective. In this study, we developed an improved stepwise calibration (ISC) method based on numerical constancy to correct and reconstruct the time series of China’s regional nighttime light data, thus eliminating the drawbacks of the invariant target region method. We evaluated the different calibration methods and quantitatively validated the calibrated nighttime light data using gross domestic product (GDP) and electricity consumption (EC) at municipal, provincial, and national scales. The results indicated that the ISC method demonstrated its advantage in screening stable lit pixels and maintaining the temporal variability of multi-year nighttime light variation. The variation curve of reconstructed multi-year nighttime light obtained by the ISC method based on numerical constancy was more consistent with the actual urban development. The ISC method retained the original data’s most abundant and complete information than other calibration methods. Moreover, the significant advantages of this method in the low-light high-variation regions and high-light low-variation regions offered new possibilities for understanding the development of small- and medium-sized nighttime light centers such as towns and villages from a nighttime light perspective. This is an advantage that other calibration methods do not offer. The correlation between the multi-year nighttime light dataset obtained by the ISC method and the socio-economic data was significantly improved. The correlation coefficients with GDP and EC are 0.9695 and 0.9923, respectively. Last but not least, the ISC method is more straightforward to implement. The new framework developed in this study produces a more accurate and reliable long time series nighttime light dataset and provides quality assurance for subsequent research in socio-economic development, urban development, natural disasters, and other fields.

Due to the importance of soil organic carbon (SOC) in supporting ecosystem services, accurate SOC assessment is vital for scientific research and decision making. However, most previous studies focused on single soil depth, leading to a poor understanding of SOC in multiple depths. To better understand the spatial distribution pattern of SOC in Northeast and North China Plain, we compared three machine learning algorithms (i.e., Cubist, Extreme Gradient Boosting (XGBoost) and Random Forest (RF)) within the digital soil mapping framework. A total of 386 sampling sites (1584 samples) following specific criteria covering all dryland districts and counties and soil types in four depths (i.e., 0–10, 10–20, 20–30 and 30–40 cm) were collected in 2017. After feature selection from 249 environmental covariates by the Genetic Algorithm, 29 variables were used to fit models. The results showed SOC increased from southern to northern regions in the spatial scale and decreased with soil depths. From the result of independent verification (validation dataset: 80 sampling sites), RF (R²: 0.58, 0.71, 0.73, 0.74 and RMSE: 3.49, 3.49, 2.95, 2.80 g kg⁻¹ in four depths) performed better than Cubist (R²: 0.46, 0.63, 0.67, 0.71 and RMSE: 3.83, 3.60, 3.03, 2.72 g kg⁻¹) and XGBoost (R²: 0.53, 0.67, 0.70, 0.71 and RMSE: 3.60, 3.60, 3.00, 2.83 g kg⁻¹) in terms of prediction accuracy and robustness. Soil, parent material and organism were the most important covariates in SOC prediction. This study provides the up-to-date spatial distribution of dryland SOC in Northeast and North China Plain, which is of great value for evaluating dynamics of soil quality after long-term cultivation.

Agricultural fields are essential in providing human beings with paramount food and other materials. Quick and accurate identification of agricultural fields from the remote sensing images is a crucial task in digital and precision agriculture. Deep learning methods have the advantages of fast and accurate image segmentation, especially for extracting the agricultural fields from remote sensing images. This paper proposed a deep neural network with a dual attention mechanism and a multi-scale feature fusion (Dual Attention and Scale Fusion Network, DASFNet) to extract the cropland from a GaoFen-2 (GF-2) image of 2017 in Alar, south Xinjiang, China. First, we constructed an agricultural field segmentation dataset from the GF-2 image. Next, seven evaluation indices were selected to assess the extraction accuracy, including the location shift, to reveal the spatial relationship and facilitate a better evaluation. Finally, we proposed DASFNet incorporating three ameliorated and novel deep learning modules with the dual attention mechanism and multi-scale feature fusion methods. The comparison of these modules indicated their effects and advantages. Compared with different segmentation convolutional neural networks, DASFNet achieved the best testing accuracy in extracting fields with an F1-score of 0.9017, an intersection over a union of 0.8932, a Kappa coefficient of 0.8869, and a location shift of 1.1752 pixels. Agricultural fields can be extracted automatedly and accurately using DASFNet, which reduces the manual record of the agricultural field information and is conducive to further farmland surveys, protection, and management.