Maize residue cover (MRC) is an important parameter to quantify the degree of crop residue cover in the field and its spatial distribution characteristics. It is also a key indicator of conservation tillage. Rapid and accurate estimation of maize residue cover (MRC) and spatial mapping are of great significance to increasing soil organic carbon, reducing wind and water erosion, and maintaining soil and water. Currently, the estimation of maize residue cover in large areas suffers from low modeling accuracy and poor working efficiency. Therefore, how to improve the accuracy and efficiency of maize residue cover estimation has become a research hotspot. In this study, adaptive threshold segmentation (Yen) and the CatBoost algorithm are integrated and fused to construct a residue coverage estimation method based on multispectral remote sensing images. The maize planting areas in and around Sihe Town in Jilin Province, China, were selected as typical experimental regions, and the unmanned aerial vehicle (UAV) was employed to capture maize residue cover images of sample plots within the area. The Yen algorithm was applied to calculate and analyze maize residue cover. The successive projections algorithm (SPA) was used to extract spectral feature indices from Sentinel-2A multispectral images. Subsequently, the CatBoost algorithm was used to construct a maize residue cover estimation model based on spectral feature indices, thereby plotting the spatial distribution map of maize residue cover in the experimental area. The results show that the image segmentation based on the Yen algorithm outperforms traditional segmentation methods, with the highest Dice coefficient reaching 81.71%, effectively improving the accuracy of maize residue cover recognition in sample plots. By combining the spectral index calculation with the SPA algorithm, the spectral features of the images are effectively extracted, and the spectral feature indices such as NDTI and STI are determined. These indices are significantly correlated with maize residue cover. The accuracy of the maize residue cover estimation model built using the CatBoost model surpasses that of traditional machine learning models, with a maximum determination coefficient (R²) of 0.83 in the validation set. The maize residue cover estimation model constructed based on the Yen and CatBoost algorithms effectively enhances the accuracy and reliability of estimating maize residue cover in large areas using multispectral imagery, providing accurate and reliable data support and services for precision agriculture and conservation tillage.

Heavy metal pollution in farmland soil threatens soil environmental quality. It is an important task to quickly grasp the status of heavy metal pollution in farmland soil in a region. Hyperspectral remote sensing technology has been widely used in soil heavy metal concentration monitoring. How to improve the accuracy and reliability of its estimation model is a hot topic. This study analyzed 440 soil samples from Sihe Town and the surrounding agricultural areas in Yushu City, Jilin Province. Considering the differences between different types of soils, a local regression model of heavy metal concentrations (As and Cu) was established based on projection pursuit (PP) and light gradient boosting machine (LightGBM) algorithms. Based on the estimations, a spatial distribution map of soil heavy metals in the region was drawn. The findings of this study showed that considering the differences between different soils to construct a local regression estimation model of soil heavy metal concentration improved the estimation accuracy. Specifically, the relative percent difference (RPD) of As and Cu element estimations in black soil increased the most, by 0.30 and 0.26, respectively. The regional spatial distribution map of heavy metal concentration derived from local regression showed high spatial variability. The number of characteristic bands screened by the PP method accounted for 10–13% of the total spectral bands, effectively reducing the model complexity. Compared with the traditional machine model, the LightGBM model showed better estimation ability, and the highest determination coefficients (R²) of different soil validation sets reached 0.73 (As) and 0.75 (Cu), respectively. In this study, the constructed PP–LightGBM estimation model takes into account the differences in soil types, which effectively improves the accuracy and reliability of hyperspectral image estimation of soil heavy metal concentration and provides a reference for drawing large-scale spatial distributions of heavy metals from hyperspectral images and mastering soil environmental quality.

Soil organic matter (SOM) is important for the global carbon cycle, and hyperspectral remote sensing has proven to be a promising method for fast SOM content estimation. However, because of the neglect of the spectral response of soil physical properties, the accuracy and spatiotemporal transferability of the SOM prediction model are poor. This study aims to improve the spatiotemporal transferability of the SOM prediction model by alleviating the coupling effect of soil physical properties on spectra. Based on satellite hyperspectral images and soil physical variables, including soil moisture (SM), soil surface roughness (root-mean-square height, RMSH), and soil bulk weight (SBW), a soil spectral correction model was established based on the information unmixing method. Two important grain-producing areas in Northeast China were selected as study areas to verify the performance and transferability of the spectral correction model and SOM content prediction model. The results showed that soil spectral corrections based on fourth-order polynomials and the XG-Boost algorithm had excellent accuracy and generalization ability, with residual predictive deviations (RPDs) exceeding 1.4 in almost all the bands. In addition, when the soil spectral correction strategy was adopted, the accuracy of the SOM prediction model and the generalization ability after the model migration were significantly improved. The SOM prediction accuracy based on the XG-Boost-corrected spectrum was the highest, with a coefficient of determination (R²) of 0.76, a root-mean-square error (RMSE) of 5.74 g/kg, and an RPD of 1.68. The prediction accuracy, R² value, RMSE, and RPD of the model after the migration were 0.72, 6.71 g/kg, and 1.53, respectively. Compared with the direct migration prediction of the model, adopting the soil spectral correction model based on fourth-order polynomials and XG-Boost reduced the RMSE of the SOM prediction results by 57.90% and 60.27%, respectively. This performance comparison highlighted the advantages for considering soil physical properties in regional-scale SOM predictions.

Soil organic matter (SOM) is important for the global carbon cycle, and hyperspectral remote sensing has proven a promising method for fast SOM content estimation. However, soil physical properties significantly affect the sensitivity of satellite hyperspectral imaging to SOM, leading to poor generalization ability of the estimation model. This study aims to improve the spatiotemporal transferability of the SOM prediction model by alleviating the coupling effect of soil physical properties on the spectra. Based on satellite hyperspectral images and soil physical variables, including soil moisture (SM), soil surface roughness (root mean squared height, RMSH), and soil bulk weight (SBW), a soil spectral correction strategy was established based on the information unmixing method. Two important grain-producing areas in Northeast China were selected as study areas to verify the performance and transferability of the spectral correction model and SOM content prediction model. The results showed that soil spectral corrections based on fourth-order polynomials and the XG-Boost algorithm had excellent accuracy and generalization ability, with residual predictive deviations (RPD) exceeding 1.4 in almost all bands. In addition, when the soil spectral correction strategy was adopted, the accuracy of the SOM prediction model and the generalization ability after model migration were significantly improved. The SOM prediction accuracy based on the XG-Boost corrected spectrum was the highest, with a coefficient of determination (R2) of 0.76, root mean square error (RMSE) of 5.74 g/kg, and RPD of 1.68. The prediction accuracy, R2, RMSE, and RPD of the model after migration were 0.72, 6.71 g/kg, and 1.53, respectively. Compared with the direct migration prediction of the model, adopting the soil spectral correction strategy based on fourth-order polynomials and XG-Boost reduced the RMSE of the SOM prediction results by 57.90% and 60.27%, respectively. The performance comparison highlighted the advantages of considering soil physical properties in regional-scale SOM prediction.

Soil salinization poses a significant threat to sustainable agricultural development and ecological security worldwide, resulting in considerable crop losses annually. The advent of drone-based hyperspectral remote sensing offers promising solutions for monitoring soil salinity, due to its high spatial resolution and versatile data acquisition capabilities. However, soil moisture alters both the scattering and absorption characteristics of electromagnetic radiation, thereby modifying soil spectral reflectance and masking salinity-related diagnostic spectral features, which can reduce the accuracy of conventional salinity estimation models. This study evaluates six spectral transformation methods—raw reflectance data (Ref), first derivative (FDR), Piecewise Direct Standardization (PDS), Orthogonal Signal Correction (OSC), FDR + PDS, and FDR + OSC—in conjunction with three machine learning algorithms: K-Nearest Neighbors (KNN), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP). A Stacking ensemble model integrating these base learners was further developed to improve soil salinity inversion under moisture interference. The results demonstrated that the Stacking model achieved the highest accuracy and stability among the evaluated models. Additional comparisons with XGBoost and Random Forest (RF) further confirmed the competitive performance of the proposed Stacking framework. The FDR + OSC–Stacking combination achieved the best validation performance, with $R_p^2$ = 0.87, RMSEP = 0.67 mS·cm⁻¹, and RPD = 2.93. Compared with the Ref–Stacking model, $R_p^2$ increased by 0.32 (from 0.55 to 0.87), while RMSEP decreased by 0.58 mS·cm⁻¹ (from 1.25 to 0.67 mS·cm⁻¹). The results showed that PDS had limited effectiveness in correcting moisture-related spectral variation, whereas OSC more effectively mitigated moisture interference while preserving spectral information relevant to salinity estimation. Among the machine learning models evaluated, the Stacking ensemble model achieved better predictive performance than MLP, SVR, and KNN. Furthermore, the FDR + OSC–Stacking combination provided the best performance among the evaluated modeling frameworks and was successfully applied to UAV hyperspectral imagery for spatial mapping of EC_1:5. These findings demonstrate the potential of combining appropriate spectral correction with Stacking for UAV-based soil salinity assessment and provide useful technical support for site-specific salinity management in precision agriculture.

Dry soil spectral reflectance provides a stable baseline for characterizing soil optical properties and supporting the retrieval of soil attributes from remote sensing. However, despite the large number of studies on soil spectral reflectance, most existing research primarily focuses on empirical relationships between spectra and soil properties. The representation and prediction of dry soil reflectance as a baseline condition, particularly under the influence of environmental factors, remain insufficiently explored, and the generalizability of existing models still needs improvement. Therefore, this study collects 700 dry soil samples with laboratory-measured spectral reflectance from Northeast China and quantitatively analyzes the contribution of environmental covariates (soil properties, parent material, and geographical location) using the SHAP method. Then, an environmental and edaphic-factor-driven smooth dry soil reflectance model (EEDSR) model covering 400–2500 nm is developed based on gradient boosting regression (GBR), and its accuracy is evaluated using global ISRIC soil datasets. Our results indicate the following: (1) the reflectance of dry soil is closely related to the soil properties in the VIS to SWIR range. The reflectance of dry soil of 400–2500 nm is positively correlated with clay percentage, longitude, and parent material but negatively correlated with latitude, sand percentage and silt percentage. And its correlation with other variables (such as soil organic matter, pH, and EC) varies with wavelength. (2) The EEDSR model exhibited high predictive accuracy across the 400–2500 nm spectral range (R² = 0.93, RMSE = 0.018). Additionally, incorporating parent material (PM) and geographical factors into the predictor set enhanced the accuracy of dry soil reflectance prediction by 13.4%. (3) The spatial consistency between the predicted soil reflectance in Northeast China and the satellite observations indicates that the EEDSR model has good performance in predicting soil reflectance, as the bias of reflectance gradually increasing from west to east is consistent with the precipitation distribution in Northeast China. (4) The generalization ability of the EEDSR model was confirmed by global ISRIC datasets (R = 0.94), outperforming the deep learning-based Soil Optical Generative Model (SOGM) (R = 0.27). Overall, this study presents an efficient and interpretable framework for modeling dry soil spectral reflectance, providing a robust reference for soil reflectance prediction and remote sensing-based soil property retrieval.