Net primary productivity (NPP) of vegetation is considered an important indicator for ecological stability and is the main object for analyzing the factors influencing the terrestrial carbon cycle. Recent studies have made clear the changes in the NPP of vegetation and its influencing factors at various scales. However, the variations in NPP based on different land cover types under various natural conditions, along with their driving factors, remain not well understood. In this study, spatial overlay analysis was used to investigate the link among climatic, soil moisture (SM), and topographic parameters and NPP of various land cover types after analyzing the spatial and temporal trends of NPP in the Songnen Plain from 2001 to 2020. Additionally, the contribution of each influence factor to the NPP of different land cover types was calculated using the elastic net regression model. The elastic net regression model eliminates the multicollinearity among the influencing factors while maintaining the model stability, and the R2 of all lands is greater than 0.62, which can effectively quantify the contribution of each influencing factor to NPP. The results show a continuously increasing trend of the overall NPP in the research area over the selected 20 years, and NPP increased most significantly in forest land (FOR). Precipitation (PRE) and NPP showed high correlations in all the different land cover types, while the correlations between NPP and other influencing factors were significantly different. In addition, we found that perennials led to a more significant degree of NPP enhancement, and the effect of topographic conditions on NPP was mainly reflected in differences in moisture conditions due to surface runoff. From the results of the modeling calculations, the cumulative contribution of PRE to NPP ranks first in all land types and is the most vital influencing factor of NPP in the Songnen Plain. SM was an important influence, but the contribution of NPP was greater in land classes with shallow root systems. The results of the study revealed the positive transformation relationship of NPP among land cover types in ecologically fragile areas, which provides a reference for ecological restoration and rationalization of land use structure in zones such as intertwined agricultural and pastoral zones.
Soil organic carbon (SOC) is important in the global carbon cycle. Accurate estimation of SOC content in cultivated land is a prerequisite for evaluating the carbon sequestration potential and quality of soils. However, existing SOC prediction studies based on hyperspectral remote sensing neglect the spectral response of the physical properties of surface soil, leading to inadequate model generalization. With the exponential growth of remote sensing data, the development of pixel-level soil spectral correction methods based on multi-source remote sensing data has become an interesting and challenging topic. This method aims to minimize the effect of soil physical properties on spectra, thus addressing the poor spatiotemporal transferability of SOC prediction models due to uncertain variations in surface soil physical properties. In this study, a soil spectral correction strategy is constructed using satellite hyperspectral image (HSI) and synthetic aperture radar (SAR) images through multi-order polynomial regression and convolutional neural networks. This strategy considers soil physical variables such as soil moisture (SM) content and root mean square height (RMSH) of soil surface roughness. The soil spectral correction model and SOC content prediction model were established using 80 soil samples collected from Site 1. Afterward, the performance and transferability of both models were verified using the remaining 25 samples from Site 1 and 50 samples from Site 2. The results showed that: 1) The effect of SM and RMSH on the soil pixel spectrum can be significantly reduced after correcting HSI using soil spectral correction strategy. The correlation coefficients between the corrected pixel spectrum and the ground-based spectrum increase by over 60 % compared with those between the original spectrum and the ground-based spectrum. 2) Soil spectral correction improves the prediction accuracy and mapping capability of HSI for SOC content, with the highest RP2 of 0.743 and RMSEP of 3.455 g/kg at Site 1. 3) Compared with the original HSI-based SOC prediction model, the soil spectral correction strategy based on multi-order polynomial and convolutional neural network reduced the RMSEP of SOC prediction results at Site 2 by 5.082 g/kg and 5.454 g/kg, and the RP2 increased by 0.390 and 0.409, respectively. 4) When predicting SOC content from raw HIS, SM and RMSH contribute to more than 60 % of the bias, with SM having a larger bias than RMSH. The findings of this study emphasize the influence of soil physical properties on SOC prediction and contribute to the existing research on SOC mapping using HSI and SAR data.
Lithology classification is important in mineral resource exploration, engineering geological exploration, and disaster monitoring. Traditional laboratory methods for the qualitative analysis of rocks are limited by sampling conditions and analytical techniques, resulting in high costs, low efficiency, and the inability to quickly obtain large-scale geological information. Hyperspectral remote sensing technology can classify and identify lithology using the spectral characteristics of rock, and is characterized by fast detection, large coverage area, and environmental friendliness, which provide the application potential for lithological mapping at a large regional scale. In this study, ZY1-02D hyperspectral images were used as data sources to construct a new two-layer extreme gradient boosting (XGBoost) lithology classification model based on the XGBoost decision tree and an improved greedy search algorithm. A total of 153 spectral bands of the preprocessed hyperspectral images were input into the first layer of the XGBoost model. Based on the tree traversal structural characteristics of the leaf nodes in the XGBoost model, three built-in XGBoost importance indexes were split and combined. The improved greedy search algorithm was used to extract the spectral band variables, which were imported into the second layer of the XGBoost model, and the bat algorithm was used to optimize the modeling parameters of XGBoost. The extraction model of rock classification information was constructed, and the classification map of regional surface rock types was drawn. Field verification was performed for the two-layer XGBoost rock classification model, and its accuracy and reliability were evaluated based on four indexes, namely, accuracy, precision, recall, and F1 score. The results showed that the two-layer XGBoost model had a good lithological classification effect, robustness, and adaptability to small sample datasets. Compared with the traditional machine learning model, the two-layer XGBoost model shows superior performance. The accuracy, precision, recall, and F1 score of the verification set were 0.8343, 0.8406, 0.8350, and 0.8157, respectively. The variable extraction ability of the constructed two-layer XGBoost model was significantly improved. Compared with traditional feature selection methods, the GREED-GFC method, when applied to the two-layer XGBoost model, contributes to more stable rock classification performance and higher lithology prediction accuracy, and the smallest number of extracted features. The lithological distribution information identified by the model was in good agreement with the lithology information verified in the field.
Heavy metal pollution poses a huge challenge to the soil environment. With the increasing pollution level, the traditional monitoring methods cannot quickly obtain information on large-area pollution. Therefore, a large-scale mapping method with high precision is urgently needed to effectively control heavy metal pollution. This study explored a method for mapping soil heavy metal concentrations through hyperspectral images. On this basis, a new Stacked AdaBoost ensemble learning algorithm was constructed to construct the inversion model of soil heavy metal contents. The characteristic spectral bands of heavy metals were extracted as model input variables using Pearson's correlation coefficient and successive projections algorithm. With three sets of heavy metal content data, the prediction accuracy and mapping outcomes of various machine learning methods were compared. Furthermore, the potential sources of heavy metal pollution in the study area were analyzed based on the Moran's index. The results showed that the Stacked AdaBoost model was relatively stable with higher accuracy than traditional machine learning models. For Cr, Cu, and As, the determination coefficients (R2) of the verification set were 0.66, 0.61, and 0.74, respectively. Afterward, the results of this model were used to map the heavy metal concentration over the study area. The mapping results suggested that the heavy metal conditions of soils in the Ganhetan area were caused by nature and human activities. The As pollution in agricultural soils was the most serious, with an exceedance rate of 38.66%. Industrial areas were potential sources of soil heavy metal pollution in the study area. In summary, the Stacked AdaBoost ensemble learning model provides detailed and reliable data for agricultural ecological protection and industrial pollution control, allowing the effective management of heavy metal pollution sources.
Evapotranspiration (ET) is a vital constituent of the hydrologic cycle. Researching changes in ET is necessary for understanding variability in the hydrologic cycle. Although some studies have clarified the changes and influencing factors of ET on a regional or global scale, these variables are still unclear for different land cover types due to the range of possible water evaporation mechanisms and conditions. In this study, we first investigated spatiotemporal trends of ET in different land cover types in the Xiliao River Plain from 2000 to 2019. The correlation between meteorological, NDVI, groundwater depth, and topographic factors and ET was compared through spatial superposition analysis. We then applied the ridge regression model to calculate the contribution rate of each influencing factor to ET for different land cover types. The results revealed that ET in the Xiliao River Plain has shown a continuously increasing trend, most significantly in cropland (CRO). The correlation between ET and influencing factors differed considerably for different land cover types, even showing an opposite result between regions with and without vegetation. Only precipitation (PRCP) and NDVI had a positive impact on ET in all land cover types. In addition, we found that vegetation can deepen the limited depth of land absorbing groundwater, and the influence of topographic conditions may be mainly reflected in the water condition difference caused by surface runoff. The ridge regression model eliminates multicollinearity among influencing factors; R2 in all land cover types was over 0.6, indicating that it could be used to effectively quantify the contribution of various influencing factors to ET. According to the results of our model calculations, NDVI had the greatest impact on ET in grass (GRA), cropland (CRO), paddy (PAD), forest (FOR), and swamp (SWA), while PRCP was the main influencing factor in bare land (BAR) and sand (SAN). These findings imply that we should apply targeted measures for water resources management in different land cover types. This study emphasizes the importance of comprehensively considering differences among various hydrologic cycles according to land cover type in order to assess the contributions of influencing factors to ET.
Abstract Mineralized indicator minerals are an important geological and mineral exploration indicator. Rapid extraction of mineralized indicator minerals from hyperspectral remote sensing images using ensemble learning model has important geological significance for mineral resources exploration. In this study, two mineralized indicator minerals, limonite and chlorite, exposed at the surface of Qinghai Gouli area were used as the research objects. Sparrow search algorithm (SSA) was combined with random forest (RF) and gradient boosting decision tree (GBDT) ensemble learning models, respectively, to construct hyperspectral mineralized indicative mineral information extraction models in the study area. Youden index (YD) and ore deposit coincidence (ODC) were applied to evaluate the performance of different models in the mineral information extraction. The results indicate that the optimization of SSA parameter algorithm is obvious, and the accuracy of both the integrated learning models after parameter search has been improved substantially, among which the SSA-GBDT model has the best performance, and the YD and the ODC can reach 0.661 and 0.727, respectively. Compared with traditional machine learning model, integrated learning model has higher reliability and stronger generalization performance in hyperspectral mineral information extraction and application, with YD greater than 0.6. In addition, the distribution of mineralized indicative minerals extracted by the ensemble learning model after parameter optimization is basically consistent with the distribution pattern of the fracture tectonic spreading characteristics and known deposits (points) in the area, which is in line with the geological characteristics of mineralization in the study area. Therefore, the classification and extraction model of minerals based on hyperspectral remote sensing technology, combined with the SSA optimization algorithm and ensemble learning model, is an efficient mineral exploration method.
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 Soil organic matter content (SOMC) is a key factor in improving the soil fertility of arable land. Determining how to quickly and accurately grasp SOMC on a regional scale has become an important task for farmland quality monitoring. Hyperspectral imaging remote sensing technology can enable large-scale SOMC estimation, owing to its large-scale and fine spectral resolution. Enhancing the accuracy and reliability of SOM estimation models based on hyperspectral satellite remote sensing has emerged as a prominent topic of study. In this study, feature spectral indices such as difference indices (DI), ratio indices, and normalized indices were extracted using the correlation coefficient method and used as variables to construct a regression model for SOM, with a split-sample regression method employed to account for the complexity of soil types and map the corresponding spatial distribution of SOM. The results showed that the SOM estimation model, built using these feature spectral indices from hyperspectral satellite imagery, achieved high predictive accuracy, with R ² values approaching 0.80 for most soil types. This demonstrates that the model effectively captures variations in SOM content across diverse soil backgrounds, highlighting its robustness and adaptability. The DI 499/576 combinations, in particular, contributed significantly to prediction accuracy, demonstrating their importance as key spectral parameters for SOM estimation. Furthermore, among the three sets of feature model variables derived from the split-sample regression strategy, the enhanced vegetation indices and Soil-Adjusted Total Vegetation Index exhibited distinct contributions to different soil sample groups. This variation reveals the specific responsiveness of these indices to soil properties, which further enhances model performance in varied soil contexts. This study provides innovative methods for large-scale SOMC estimation, particularly by utilizing hyperspectral indices to enhance model accuracy across various soil types, demonstrating substantial practical significance.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)