Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effect...Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide more reliable references for soil conservation policy-making.展开更多
Soil classification is the foundation for exchange and extension of research findings in soil science and for modern management of soil resources. This study explained database and research methodology to create a cro...Soil classification is the foundation for exchange and extension of research findings in soil science and for modern management of soil resources. This study explained database and research methodology to create a cross-reference system for translating the Genetic Soil Classification of China (GSCC) into the Chinese Soil Taxonomy (CST). With the help of the CST keys, each of the 2 540 soil species in GSCC has been interpreted to its corresponding soil order, suborder, great group, and sub-group in CST. According to the methodology adopted, the assigned soil species have been linked one another to their corresponding polygons in the 1:1000000 digital soil map of China. Referencibility of each soil species between the GSCC and CST systems was determined statistically on the basis of distribution area of each soil species at a high taxon level of the two systems. The soils were then sorted according to their maximum referencibility and classified into three categories for discussion. There were 19 soil great groups in GSCC with maximum referencibility > 90% and 22 great groups between 60%-90%. These soil great groups could serve as cross-reference benchmarks. There were 19 great groups in GSCC with maximum referencibility < 60%, which could be used as cross-reference benchmarks until new and better results were available. For these soils, if the translation was made at a lower soil taxon level or on a regional basis, it would improve their referencibility enabling them to serve as new cross-reference benchmarks.展开更多
Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not avail...Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not available for those situations with limited samples.To solve the problem,this paper proposed a case-based method which could formalize the covariate selection knowledge contained in practical DSM applications.The proposed method trained Random Forest(RF)classifiers with DSM cases extracted from the practical DSM applications and then used the trained classifiers to determine whether each one potential covariate should be used in a new DSM application.In this study,we took topographic covariates as examples of covariates and extracted 191 DSM cases from 56 peer-reviewed journal articles to evaluate the performance of the proposed case-based method by Leave-One-Out cross validation.Compared with a novices’commonly-used way of selecting DSM covariates,the proposed case-based method improved more than 30%accuracy according to three quantitative evaluation indices(i.e.,recall,precision,and F1-score).The proposed method could be also applied to selecting the proper set of covariates for other similar geographical modeling domains,such as landslide susceptibility mapping,and species distribution modeling.展开更多
Soil management matters in semiarid lands are key to have acceptable yields and to preserve diversity. After the major agricultural intensification underwent in the semiarid lands of Monegros, NE Spain, custom tailore...Soil management matters in semiarid lands are key to have acceptable yields and to preserve diversity. After the major agricultural intensification underwent in the semiarid lands of Monegros, NE Spain, custom tailored tools are needed to reconcile agriculture with habitats conservation. The objectives of this study were to quantify the effect of soil properties of two distinctly colored soils, white patches （WP） and dark patches （DP）, dominant in the arid landscape of the central Ebro Basin, Spain on winter cereal grain yield and to prove that superficial soil color could be used as a visual diagnostic criterion for evaluation of agricultural practices in arid lands. Significant differences between WP and DP soils were found in gypsum, carbonate contents, available water holding capacity and infiltration rate. The grain yield ranged from 51 to 5 713 kg ha-1. Significantly lower yields （P 〈 0.01） and precipitation-use efficiency （P 〈 0.05） were attained in the WP soils for the three seasons studied. This difference increased with the average rainfall due to the significantly lower soil water infiltration （P 〈 0.01） and water holding capacity （P 〈 0.05） found in the gypseous soils. Our results show that mapping the soil surface color at farm scale can be a low=cost tool for optimizing agricultural practices and recovering the natural vegetation. This approach can be advantageous in similar arid or semiarid environments around the world.展开更多
基金the National Natural Science Foundation of China(U1901601)the National Key Research and Development Program of China(2022YFB3903503)。
文摘Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide more reliable references for soil conservation policy-making.
基金Project supported by the National Natural Science Foundation of China (No. 40471081)the Frontal Field Project of the Chinese Academy of Sciences (No. ISSASIP0201) the Key Innovation Project of Chinese Academy of Sciences (No.KZCX3-SW-427).
文摘Soil classification is the foundation for exchange and extension of research findings in soil science and for modern management of soil resources. This study explained database and research methodology to create a cross-reference system for translating the Genetic Soil Classification of China (GSCC) into the Chinese Soil Taxonomy (CST). With the help of the CST keys, each of the 2 540 soil species in GSCC has been interpreted to its corresponding soil order, suborder, great group, and sub-group in CST. According to the methodology adopted, the assigned soil species have been linked one another to their corresponding polygons in the 1:1000000 digital soil map of China. Referencibility of each soil species between the GSCC and CST systems was determined statistically on the basis of distribution area of each soil species at a high taxon level of the two systems. The soils were then sorted according to their maximum referencibility and classified into three categories for discussion. There were 19 soil great groups in GSCC with maximum referencibility > 90% and 22 great groups between 60%-90%. These soil great groups could serve as cross-reference benchmarks. There were 19 great groups in GSCC with maximum referencibility < 60%, which could be used as cross-reference benchmarks until new and better results were available. For these soils, if the translation was made at a lower soil taxon level or on a regional basis, it would improve their referencibility enabling them to serve as new cross-reference benchmarks.
基金supported by grants from the National Natural Science Foundation of China(41431177 and 41871300)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD),China+4 种基金the Innovation Project of State Key Laboratory of Resources and Environmental Information System(LREIS),China(O88RA20CYA)the Outstanding Innovation Team in Colleges and Universities in Jiangsu Province,ChinaSupports to A-Xing Zhu through the Vilas Associate Awardthe Hammel Faculty Fellow Awardthe Manasse Chair Professorship from the University of Wisconsin-Madison。
文摘Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping(DSM).The statistical or machine learning methods for selecting DSM covariates are not available for those situations with limited samples.To solve the problem,this paper proposed a case-based method which could formalize the covariate selection knowledge contained in practical DSM applications.The proposed method trained Random Forest(RF)classifiers with DSM cases extracted from the practical DSM applications and then used the trained classifiers to determine whether each one potential covariate should be used in a new DSM application.In this study,we took topographic covariates as examples of covariates and extracted 191 DSM cases from 56 peer-reviewed journal articles to evaluate the performance of the proposed case-based method by Leave-One-Out cross validation.Compared with a novices’commonly-used way of selecting DSM covariates,the proposed case-based method improved more than 30%accuracy according to three quantitative evaluation indices(i.e.,recall,precision,and F1-score).The proposed method could be also applied to selecting the proper set of covariates for other similar geographical modeling domains,such as landslide susceptibility mapping,and species distribution modeling.
基金Supported by the Project of Spanish Government(No.AGL2009-08931)
文摘Soil management matters in semiarid lands are key to have acceptable yields and to preserve diversity. After the major agricultural intensification underwent in the semiarid lands of Monegros, NE Spain, custom tailored tools are needed to reconcile agriculture with habitats conservation. The objectives of this study were to quantify the effect of soil properties of two distinctly colored soils, white patches （WP） and dark patches （DP）, dominant in the arid landscape of the central Ebro Basin, Spain on winter cereal grain yield and to prove that superficial soil color could be used as a visual diagnostic criterion for evaluation of agricultural practices in arid lands. Significant differences between WP and DP soils were found in gypsum, carbonate contents, available water holding capacity and infiltration rate. The grain yield ranged from 51 to 5 713 kg ha-1. Significantly lower yields （P 〈 0.01） and precipitation-use efficiency （P 〈 0.05） were attained in the WP soils for the three seasons studied. This difference increased with the average rainfall due to the significantly lower soil water infiltration （P 〈 0.01） and water holding capacity （P 〈 0.05） found in the gypseous soils. Our results show that mapping the soil surface color at farm scale can be a low=cost tool for optimizing agricultural practices and recovering the natural vegetation. This approach can be advantageous in similar arid or semiarid environments around the world.
