The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Wenjiao Shi - One of the best experts on this subject based on the ideXlab platform.
-
systematic comparison of five machine learning models in classification and interpolation of Soil Particle size fractions using different transformed data
Hydrology and Earth System Sciences, 2020Co-Authors: Mo Zhang, Wenjiao ShiAbstract:Abstract. Soil texture and Soil Particle size fractions (PSFs) play an increasing role in physical, chemical, and hydrological processes. Many previous studies have used machine-learning and log-ratio transformation methods for Soil texture classification and Soil PSF interpolation to improve the prediction accuracy. However, few reports have systematically compared their performance with respect to both classification and interpolation. Here, five machine-learning models – K-nearest neighbour (KNN), multilayer perceptron neural network (MLP), random forest (RF), support vector machines (SVM), and extreme gradient boosting (XGB) – combined with the original data and three log-ratio transformation methods – additive log ratio (ALR), centred log ratio (CLR), and isometric log ratio (ILR) – were applied to evaluate Soil texture and PSFs using both raw and log-ratio-transformed data from 640 Soil samples in the Heihe River basin (HRB) in China. The results demonstrated that the log-ratio transformations decreased the skewness of Soil PSF data. For Soil texture classification, RF and XGB showed better performance with a higher overall accuracy and kappa coefficient. They were also recommended to evaluate the classification capacity of imbalanced data according to the area under the precision–recall curve (AUPRC). For Soil PSF interpolation, RF delivered the best performance among five machine-learning models with the lowest root-mean-square error (RMSE; sand had a RMSE of 15.09 %, silt was 13.86 %, and clay was 6.31 %), mean absolute error (MAE; sand had a MAD of 10.65 %, silt was 9.99 %, and clay was 5.00 %), Aitchison distance (AD; 0.84), and standardized residual sum of squares (STRESS; 0.61), and the highest Spearman rank correlation coefficient (RCC; sand was 0.69, silt was 0.67, and clay was 0.69). STRESS was improved by using log-ratio methods, especially for CLR and ILR. Prediction maps from both direct and indirect classification were similar in the middle and upper reaches of the HRB. However, indirect classification maps using log-ratio-transformed data provided more detailed information in the lower reaches of the HRB. There was a pronounced improvement of 21.3 % in the kappa coefficient when using indirect methods for Soil texture classification compared with direct methods. RF was recommended as the best strategy among the five machine-learning models, based on the accuracy evaluation of the Soil PSF interpolation and Soil texture classification, and ILR was recommended for component-wise machine-learning models without multivariate treatment, considering the constrained nature of compositional data. In addition, XGB was preferred over other models when the trade-off between the accuracy and runtime was considered. Our findings provide a reference for future works with respect to the spatial prediction of Soil PSFs and texture using machine-learning models with skewed distributions of Soil PSF data over a large area.
-
comparison of additive and isometric log ratio transformations combined with machine learning and regression kriging models for mapping Soil Particle size fractions
Geoderma, 2020Co-Authors: Zong Wang, Wenjiao Shi, Wei Zhou, Tianxiang YueAbstract:Abstract Digital Soil mapping approaches relating to the Soil Particle size fractions (psf) face the challenge around how to establish the statistical or geostatistical models from large sets of environmental variables, especially in a situation with sparse Soil profile data. Recently, many machine learning (ML) models have sprung up with advantages over statistical models. However, few studies focused on the comprehensive comparative analyses between ML and geostatistical models in the Soil psf mapping. And the exploration of optimal combination of data transformation and model simulation was even less. Therefore, two transformed methods such as additive log-ratio (ALR) and isometric log-ratio (ILR) transformations combine with two ML models such as boosted regression tree (BRT), random forest (RF) and a classic geostatistical model of regression kriging (RK) were implemented to map Soil psf in the Heihe River basin, China. A total of 640 samples and thirteen scorpan factors were collected and used for the comprehensive comparative analysis. Results showed that the scorpan factors such as temperature, precipitation, elevation, Soil type, Soil organic carbon, vegetation types and normalized difference vegetation index had important impacts on the Soil psf mapping. ILR transformation was better than ALR transformation with advantage of improving stability of data distributions and ML models could also improve the mapping performance in comparison with RK models for better handling candidate factors. For these ML models, the RF models had better accuracy performance than the BRT models. In contrast, ILR transformation combined with RF model (ILR_RF) had the best performance, with the lowest root mean square error values (sand, 15.35%; silt, 14.20%; and clay, 6.66%), Aitchison distance value (0.86), standardized residual sum of squares value (0.60), and the highest concordance correlation coefficient value (0.73) and coefficient of determination value (56.69%) for clay content. In addition, ILR_RF had a relatively higher right ratio of Soil texture type (68.44%) and better predict performance for most Soil texture types. The predicted maps generated from ILR_RF presented more reasonable and smoother transitions. In the future, more ML models should be explored and more variables related to Soil psf should be introduced into the models to improve the predictive performance.
-
robust variogram estimation combined with isometric log ratio transformation for improved accuracy of Soil Particle size fraction mapping
Geoderma, 2018Co-Authors: Zong Wang, Wenjiao ShiAbstract:Abstract Mapping Soil Particle-size fractions (psf) plays an important role in regional hydrological, ecological, geological, agricultural and environmental studies. To map Soil compositional data like Soil psf, interpolators such as compositional kriging and the combination of log-ratio transformations with ordinary kriging or cokriging were developed. In addition, robust estimators were proposed for these interpolators to improve the variogram models. However, few studies have focused on how to choose log-ratio transformation, kriging, cokriging, or robust variogram estimation methods based on data characteristics to achieve optimal performance when mapping Soil psf by comprehensive comparative analysis. Here, we selected different compositional kriging, log-ratio kriging, log-ratio cokriging and log-ratio cokriging methods combined with a robust variogram estimator to improve the accuracy of spatial predictions of Soil psf when using 262 Soil samples from the upper reaches of the Heihe River in China. In this study, a comprehensive comparative analysis of Soil psf maps generated by using different interpolators is presented, and appropriate methods for mapping psf based on the characteristics of the available data are explored. The results show that using isometric log-ratio (ILR) transformation with different interpolators can achieve relatively better performance than the other log-ratio transformation methods. In addition, combining the interpolators with robust variogram estimators significantly improve the prediction accuracy compared with using standard estimators, which presented reasonable and smooth transitions when mapping Soil psf. Combining ILR cokriging with a robust variogram estimator had the best accuracy, with the lowest root mean squared error (sand, 10.50%; silt, 11.24%; clay, 7.32%), an Aitchison's distance of 0.76, a standardized residual sum of squares of 0.70 and a relatively higher rate of correctly predicting Soil texture types 90.04%. In the future, guideline for using log-ratio transformation methods with linear regression, a generalized linear model or random forest should be developed and combined with ancillary variables to improve the interpolators.
Zong Wang - One of the best experts on this subject based on the ideXlab platform.
-
comparison of additive and isometric log ratio transformations combined with machine learning and regression kriging models for mapping Soil Particle size fractions
Geoderma, 2020Co-Authors: Zong Wang, Wenjiao Shi, Wei Zhou, Tianxiang YueAbstract:Abstract Digital Soil mapping approaches relating to the Soil Particle size fractions (psf) face the challenge around how to establish the statistical or geostatistical models from large sets of environmental variables, especially in a situation with sparse Soil profile data. Recently, many machine learning (ML) models have sprung up with advantages over statistical models. However, few studies focused on the comprehensive comparative analyses between ML and geostatistical models in the Soil psf mapping. And the exploration of optimal combination of data transformation and model simulation was even less. Therefore, two transformed methods such as additive log-ratio (ALR) and isometric log-ratio (ILR) transformations combine with two ML models such as boosted regression tree (BRT), random forest (RF) and a classic geostatistical model of regression kriging (RK) were implemented to map Soil psf in the Heihe River basin, China. A total of 640 samples and thirteen scorpan factors were collected and used for the comprehensive comparative analysis. Results showed that the scorpan factors such as temperature, precipitation, elevation, Soil type, Soil organic carbon, vegetation types and normalized difference vegetation index had important impacts on the Soil psf mapping. ILR transformation was better than ALR transformation with advantage of improving stability of data distributions and ML models could also improve the mapping performance in comparison with RK models for better handling candidate factors. For these ML models, the RF models had better accuracy performance than the BRT models. In contrast, ILR transformation combined with RF model (ILR_RF) had the best performance, with the lowest root mean square error values (sand, 15.35%; silt, 14.20%; and clay, 6.66%), Aitchison distance value (0.86), standardized residual sum of squares value (0.60), and the highest concordance correlation coefficient value (0.73) and coefficient of determination value (56.69%) for clay content. In addition, ILR_RF had a relatively higher right ratio of Soil texture type (68.44%) and better predict performance for most Soil texture types. The predicted maps generated from ILR_RF presented more reasonable and smoother transitions. In the future, more ML models should be explored and more variables related to Soil psf should be introduced into the models to improve the predictive performance.
-
robust variogram estimation combined with isometric log ratio transformation for improved accuracy of Soil Particle size fraction mapping
Geoderma, 2018Co-Authors: Zong Wang, Wenjiao ShiAbstract:Abstract Mapping Soil Particle-size fractions (psf) plays an important role in regional hydrological, ecological, geological, agricultural and environmental studies. To map Soil compositional data like Soil psf, interpolators such as compositional kriging and the combination of log-ratio transformations with ordinary kriging or cokriging were developed. In addition, robust estimators were proposed for these interpolators to improve the variogram models. However, few studies have focused on how to choose log-ratio transformation, kriging, cokriging, or robust variogram estimation methods based on data characteristics to achieve optimal performance when mapping Soil psf by comprehensive comparative analysis. Here, we selected different compositional kriging, log-ratio kriging, log-ratio cokriging and log-ratio cokriging methods combined with a robust variogram estimator to improve the accuracy of spatial predictions of Soil psf when using 262 Soil samples from the upper reaches of the Heihe River in China. In this study, a comprehensive comparative analysis of Soil psf maps generated by using different interpolators is presented, and appropriate methods for mapping psf based on the characteristics of the available data are explored. The results show that using isometric log-ratio (ILR) transformation with different interpolators can achieve relatively better performance than the other log-ratio transformation methods. In addition, combining the interpolators with robust variogram estimators significantly improve the prediction accuracy compared with using standard estimators, which presented reasonable and smooth transitions when mapping Soil psf. Combining ILR cokriging with a robust variogram estimator had the best accuracy, with the lowest root mean squared error (sand, 10.50%; silt, 11.24%; clay, 7.32%), an Aitchison's distance of 0.76, a standardized residual sum of squares of 0.70 and a relatively higher rate of correctly predicting Soil texture types 90.04%. In the future, guideline for using log-ratio transformation methods with linear regression, a generalized linear model or random forest should be developed and combined with ancillary variables to improve the interpolators.
De Wang - One of the best experts on this subject based on the ideXlab platform.
-
changes of Soil Particle size distribution in tidal flats in the yellow river delta
PLOS ONE, 2015Co-Authors: Junbao Yu, Huifeng Wu, Mo Zhou, Guangmei Wang, Chao Zhan, Bo Guan, Yunzhao Li, De WangAbstract:Background The tidal flat is one of the important components of coastal wetland systems in the Yellow River Delta (YRD). It can stabilize shorelines and protect coastal biodiversity. The erosion risk in tidal flats in coastal wetlands was seldom been studied. Characterizing changes of Soil Particle size distribution (PSD) is an important way to quantity Soil erosion in tidal flats. Method/Principal findings Based on the fractal scale theory and network analysis, we determined the fractal characterizations (singular fractal dimension and multifractal dimension) Soil PSD in a successional series of tidal flats in a coastal wetland in the YRD in eastern China. The results showed that the major Soil texture was from silt loam to sandy loam. The values of fractal dimensions, ranging from 2.35 to 2.55, decreased from the low tidal flat to the high tidal flat. We also found that the percent of Particles with size ranging between 0.4 and 126 mu m was related with fractal dimensions. Tide played a great effort on Soil PSD than vegetation by increasing Soil organic matter (SOM) content and salinity in the coastal wetland in the YRD. Conclusions/Significance Tidal flats in coastal wetlands in the YRD, especially low tidal flats, are facing the risk of Soil erosion. This study will be essential to provide a firm basis for the coast erosion control and assessment, as well as wetland ecosystem restoration.
-
multifractal characteristics of Soil Particle size distribution under different land use types on the loess plateau china
Catena, 2008Co-Authors: De Wang, Bojie Fu, Wenwu Zhao, Huifeng Hu, Yafeng WangAbstract:Soil Particle-size distribution (PSD) is one of the most important physical attributes due to its great influence on Soil properties related to water movement, productivity, and Soil erosion. The multifractal measures were useful tools in characterization of PSD in Soils with different taxonomies. Land-use type largely influences PSD in a Soil, but information on how this occurs for different land-use types is very limited. In this paper, multifractal Renyi dimension was applied to characterize PSD in Soils with the same taxonomy and different land-use types. The effects of land use on the multifractal parameters were then analyzed. The study was conducted on the hilly-gullied regions of the Loess Plateau, China. A Calcic Cambisols Soil was sampled from five land-use types: woodland, shrub land, grassland, terrace farmland and abandoned slope farmland with planted trees (ASFP). The result showed that: (1) entropy dimension (D-1) and entropy dimension/capacity dimension ratio (D-1/D-0) were significantly positively correlated with finer Particle content and Soil organic matter. (2) D-0, D-1 and D-1/D-0 were significantly influenced by land use. Land use could explain 24.6-58.5% of variability of D-0, D-1/D-0 and D-1, which may be potential parameters to reflect Soil physical properties and Soil quality influenced by land use. (c) 2007 Elsevier B.V All rights reserved.
Hua Yuan - One of the best experts on this subject based on the ideXlab platform.
-
a Soil Particle size distribution dataset for regional land and climate modelling in china
Geoderma, 2012Co-Authors: Wei Shangguan, Aizhong Ye, Hua YuanAbstract:article i nfo We developed a multi-layer Soil Particle-size distribution dataset (sand, silt and clay content), based on USDA (United States Department of Agriculture) standard for regional land and climate modelling in China. The 1:1,000,000 scale Soil map of China and 8595 Soil profiles from the Second National Soil Survey served as the starting point for this work. We reclassified the inconsistent Soil profiles into the proper Soil type of the map as much as possible because the Soil classification names of the map units and profiles were not quite the same. The sand, silt and clay maps were derived using the polygon linkage method, which linked Soil profiles and map polygons considering the distance between them, the sample sizes of the profiles, and Soil classification information. For comparison, a Soil type linkage was also generated by linking the map units and Soil profiles with the same Soil type. The quality of the derived Soil fractions was reliable. Overall, the map polygon linkage offered better results than the Soil type linkage or the Harmonized World Soil Database. The dataset, with a 1- km resolution, can be applied to land and climate modelling at a regional scale.
-
a Soil Particle size distribution dataset for regional land and climate modelling in china
Geoderma, 2012Co-Authors: Wei Shangguan, Yongjiu Dai, Baoyuan Liu, Hua YuanAbstract:Abstract We developed a multi-layer Soil Particle-size distribution dataset (sand, silt and clay content), based on USDA (United States Department of Agriculture) standard for regional land and climate modelling in China. The 1:1,000,000 scale Soil map of China and 8595 Soil profiles from the Second National Soil Survey served as the starting point for this work. We reclassified the inconsistent Soil profiles into the proper Soil type of the map as much as possible because the Soil classification names of the map units and profiles were not quite the same. The sand, silt and clay maps were derived using the polygon linkage method, which linked Soil profiles and map polygons considering the distance between them, the sample sizes of the profiles, and Soil classification information. For comparison, a Soil type linkage was also generated by linking the map units and Soil profiles with the same Soil type. The quality of the derived Soil fractions was reliable. Overall, the map polygon linkage offered better results than the Soil type linkage or the Harmonized World Soil Database. The dataset, with a 1-km resolution, can be applied to land and climate modelling at a regional scale.
Ming Hung Wong - One of the best experts on this subject based on the ideXlab platform.
-
dynamics thermodynamics and mechanism of perfluorooctane sulfonate pfos sorption to various Soil Particle size fractions of paddy Soil
Ecotoxicology and Environmental Safety, 2020Co-Authors: Xiaoting Chen, Lei Xiang, Quanying Cai, Ming Hung Wong, Haiming Zhao, Xiangyun ZhangAbstract:Abstract Soil is an important sink for perfluorooctane sulfonate (PFOS) that is a typical persistent organic pollutant with high toxicity. Understanding of PFOS sorption to various Particle-size fractions of Soil provides an insight into the mobility and bioavailability of PFOS in Soil. This study evaluated kinetics, isotherms, and mechanisms of PFOS sorption to six Soil Particle-size fractions of paddy Soil at environmentally relevant concentrations (0.01–1 μg/mL). The used Soil Particle-size fractions included coarse sand (120.4–724.4 mm), fine sand (45.7–316.2 mm), coarse silt (17.3–79.4 mm), fine silt (1.9–39.8 mm), clay (0.5–4.4 mm), and humic acid fractions (8.2–83.7 mm) labeled as F1~F6, respectively. PFOS sorption followed pseudo-second-order kinetics related to film diffusion and intraParticle diffusion, with speed-limiting phase acted by the latter. PFOS sorption isotherm data followed Freundlich model, with generally convex isotherms in larger size fractions (F1~F3) but concave isotherms in smaller size fractions (F4 and F5) and humic acid fraction (F6). Increasing organic matter content, Brunner−Emmet−Teller surface area, and smaller size fractions were conducive to PFOS sorption. Hydrophobic force, divalent metal ion-bridging effect, ligand exchange, hydrogen bonding, and protein-like interaction played roles in PFOS sorption. But hydrophobic force controlled the PFOS sorption, because its relevant organic matter governed the contribution of the Soil fractions to the overall PFOS sorption. The larger size fractions dominated the PFOS sorption to the original Soil because of their high mass percentages (~80%). This likely caused greater potential risks of PFOS migration into groundwater and bioaccumulation in crops at higher temperatures and ce values, based on their convex isotherms with an exothermic physical process.
-
sorption mechanism kinetics and isotherms of di n butyl phthalate to different Soil Particle size fractions
Journal of Agricultural and Food Chemistry, 2019Co-Authors: Lei Xiang, Xiaodan Wang, Xiaohong Chen, Quanying Cai, Dongmei Zhou, Ming Hung WongAbstract:Di- n-butyl phthalate (DBP) is a prevalent pollutant in agricultural Soils due to use of plastic film. This study focused on sorption mechanism, kinetics, and isotherms of DBP to six paddy Soil Particle-size fractions (i.e., coarse sand, fine sand, coarse silt, fine silt, clay, and humic acid fractions). DBP sorption involved in both boundary layer diffusion and intraParticle diffusion, following pseudo-second-order kinetics. DBP sorption was a spontaneous physical process, which fit the Freundlich model. Hydrophobic and ionic interaction relevant to the organic matter content, cation exchange capacity, surface area, and pore volume of Soil fractions played key roles in DBP sorption. DBP was strongly adsorbed to humic acid and the sorption was reversely associated with Soil Particle sizes. DBP may exhibit higher mobility and bioavailability in a Soil-crop system at lower temperature (15 °C), due to the lower log Koc values.
