Due to its complicated matrix effects, rapid quantitative analysis of chromium in agricultural soils is difficult without the concentration gradient samples by laser-induced breakdown spectroscopy. To improve the anal...Due to its complicated matrix effects, rapid quantitative analysis of chromium in agricultural soils is difficult without the concentration gradient samples by laser-induced breakdown spectroscopy. To improve the analysis speed and accuracy, two calibration models are built with the support vector machine method： one considering the whole spectra and the other based on the segmental spectra input. Considering the results of the multiple linear regression analysis, three segmental spectra are chosen as the input variables of the support vector regression （SVR） model. Compared with the results of the SVR model with the whole spectra input, the relative standard error of prediction is reduced from 3.18% to 2.61% and the running time is saved due to the decrease in the number of input variables, showing the robustness in rapid soil analysis without the concentration gradient samples.展开更多
This research is concentrated on the longitudinal vibration of a tapered pipe pile considering the vertical support of the surrounding soil and construction disturbance.First,the pile-soil system is partitioned into f...This research is concentrated on the longitudinal vibration of a tapered pipe pile considering the vertical support of the surrounding soil and construction disturbance.First,the pile-soil system is partitioned into finite segments in the vertical direction and the Voigt model is applied to simulate the vertical support of the surrounding soil acting on the pile segment.The surrounding soil is divided into finite ring-shaped zones in the radial direction to consider the construction disturbance.Then,the shear complex stiffness at the pile-soil interface is derived by solving the dynamic equilibrium equation for the soil from the outermost to innermost zone.The displacement impedance at the top of an arbitrary pile segment is obtained by solving the dynamic equilibrium equation for the pile and is combined with the vertical support of the surrounding soil to derive the displacement impedance at the bottom of the upper adjacent segment.Further,the displacement impedance at the pile head is obtained based on the impedance function transfer technique.Finally,the reliability of the proposed solution is verified,followed by a sensitivity analysis concerning the coupling effect of the pile parameters,construction disturbance and the vertical support of the surrounding soil on the displacement impedance of the pile.展开更多
Hybrid data assimilation （DA） is a method seeing more use in recent hydrology and water resources research. In this study, a DA method coupled with the support vector machines （SVMs） and the ensemble Kalman filter...Hybrid data assimilation （DA） is a method seeing more use in recent hydrology and water resources research. In this study, a DA method coupled with the support vector machines （SVMs） and the ensemble Kalman filter （EnKF） technology was used for the prediction of soil moisture in different soil layers： 0-5 cm, 30 cm, 50 cm, 100 cm, 200 cm, and 300 cm. The SVM methodology was first used to train the ground measurements of soil moisture and meteorological parameters from the Meilin study area, in East China, to construct soil moisture statistical prediction models. Subsequent observations and their statistics were used for predictions, with two approaches： the SVM predictor and the SVM-EnKF model made by coupling the SVM model with the EnKF technique using the DA method. Validation results showed that the proposed SVM-EnKF model can improve the prediction results of soil moisture in different layers, from the surface to the root zone.展开更多
Soil diagnostic horizons, which each have a set of quantified properties, play a key role in soil classification. However, they are difficult to predict, and few attempts have been made to map their spatial occurrence...Soil diagnostic horizons, which each have a set of quantified properties, play a key role in soil classification. However, they are difficult to predict, and few attempts have been made to map their spatial occurrence. We evaluated and compared four machine learning algorithms, namely, the classification and regression tree(CART), random forest(RF), boosted regression trees(BRT), and support vector machine(SVM), to map the occurrence of the soil mattic horizon in the northeastern Qinghai-Tibetan Plateau using readily available ancillary data. The mechanisms of resampling and ensemble techniques significantly improved prediction accuracies(measured based on area under the receiver operator characteristic curve score(AUC)) and produced more stable results for the BRT(AUC of 0.921 ± 0.012, mean ± standard deviation) and RF(0.908 ± 0.013) algorithms compared to the CART algorithm(0.784 ± 0.012), which is the most commonly used machine learning method. Although the SVM algorithm yielded a comparable AUC value(0.906 ± 0.006) to the RF and BRT algorithms, it is sensitive to parameter settings, which are extremely time-consuming.Therefore, we consider it inadequate for occurrence-distribution modeling. Considering the obvious advantages of high prediction accuracy, robustness to parameter settings, the ability to estimate uncertainty in prediction, and easy interpretation of predictor variables, BRT seems to be the most desirable method. These results provide an insight into the use of machine learning algorithms to map the mattic horizon and potentially other soil diagnostic horizons.展开更多
The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and...The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and soil informatization management. A total of 92 brown soil samples were collected from the orchard of Qixia County, Yantai City, Shandong Province. After drying and grinding, the hyperspectrum of the soil was measured in the laboratory using ASD FieldSpec3. The TN contents of brown soil were measured by Kjeldahl method. The sensitive wavelengths were selected by multiple linear stepwise regression method. The hyperspectral estimation model of TN was established by Random Forest (RF) and Support Vector Machines (SVM). The models were validated by independent samples. The best estimation model was obtained. The sensitive wavelengths were 956 nm, 995 nm, 1020 nm, 1410 nm, 1659 nm and 2020 nm. The coefficients of determination (R2) of the two estimation models were 0.8011 and 0.8283, the root mean square errors (RMSE) were 0.022 and 0.025, and relative errors (RE) were 0.1422 and 0.1639, respectively. Random Forest model and Support Vector Machines model are feasible in estimating TN contents, but the Support Vector Machines model is better.展开更多
A finite difference numerical method was adopted to evaluate the pile lateral behavior of pile supported embankment. A published case history was used to verify the proposed methodology. By simulating the case history...A finite difference numerical method was adopted to evaluate the pile lateral behavior of pile supported embankment. A published case history was used to verify the proposed methodology. By simulating the case history, the determination of parameters needed were verified. Then three embankments constructed on different ground conditions with different soil-pile relative stiffnesses were analyzed to study pile lateral behaviors including pile deflection and bending moment. The results show that pile deflections and bending moments induced by soil lateral deformation and embankment vertical load are different for piles at different positions under the same embankment. The relative stiffness between pile and soil affected by the properties of different reinforcing piles such as concrete pile and deep mixing method pile exert important effects on the pile lateral behavior and the pile's failure modes. Consequently, it is necessary to consider the different piles lateral behaviors and possible failure modes at different positions and the different piles proprieties with different reinforcing methods in the embankment stability analysis.展开更多
The applicability, transferability, and scalability of visible/near-infrared(VNIR)-derived soil total carbon(TC) models are still poorly understood. The objectives of this study were to: i) compare models of three mul...The applicability, transferability, and scalability of visible/near-infrared(VNIR)-derived soil total carbon(TC) models are still poorly understood. The objectives of this study were to: i) compare models of three multivariate statistical methods, partial least squares regression(PLSR), support vector machine(SVM), and random forest methods, to predict soil logarithm-transformed TC(logTC) using five fields(local scale) and a pooled(regional-scale) VNIR spectral dataset(a total of 560 TC spectral datasets), ii)assess the model transferability among fields, and iii) evaluate their up-and downscaling behaviors in Florida, USA. The transferability and up-and downscaling of the models were limited by the following factors: i) the spectral data domain, ii) soil attribute domain,iii) methods that describe the internal model structure of VNIR-TC relationships, and iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R^2> 0.86,bias < 0.01%, root mean squared error(RMSE) = 0.09%, residual predication deviation(RPD) > 2.70%, and ratio of prediction error to interquartile range(RPIQ) > 4.54. The PLSR method performed substantially better than the SVM method to scale and transfer the TC models. This could be attributed to the tendency of SVM to overfit models, while the asset of the PLSR method was its robustness when the models were validated with independent datasets, transferred, and/or scaled. The upscaled soil TC models performed somewhat better in terms of model fit(R2), RPD, and RPIQ, whereas the downscaled models showed less bias and smaller RMSE based on PLSR. We found no universal trend indicating which of the four limiting factors mentioned above had the most impact that constrained the transferability and scalability of the models. Given that several factors can impinge on the empirically derived soil spectral prediction models, as demonstrated by this study, more focus on their applicability and scalability is needed.展开更多
The use of a crop model like STICS for appropriate management decision support requires a good knowledge of all the parameters of the model. Among them, the soil parameters are difficult to know at each point of inter...The use of a crop model like STICS for appropriate management decision support requires a good knowledge of all the parameters of the model. Among them, the soil parameters are difficult to know at each point of interest and costly techniques may be used to measure them. It is therefore important to know which soil parameters need to be determined. It can be stated that those which affect significantly the output variable deserve an accurate determination while those which slightly affect the model output variable do not. This paper demonstrates how a global sensitivity analysis method based on variance decomposition can be applied on soil parameters in order to divide them in the two categories. The Extended FAST method applied to the crop model STICS and a set of 13 soil parameters first allows to calculate the part of variance explained by each soil parameter (giving global sensitivity indices of the soil parameters) and the coefficient of variation of the output variables (measuring the effect of the parameter uncertainty on each variable). These metrics are therefore used for deciding on the importance of the parameter value measurement. Different output variables (Leaf Area Index and chlorophyll content) are evaluated at different stages of interest while others (crop yield, grain protein content, soil mineral nitrogen) are evaluated at harvest. The analysis is applied on two different annual crops (wheat and sugar beet), two contrasted weather and two types of soil depth. When the uncertainty of the output generated by the soil parameters is large (coefficient of variation > 1/3), only the parameters having a significant global sensitivity indices (higher than 10%) are retained. The results show that the number of soil parameters which deserve an accurate determination can be significantly reduced by the use of this relevant method for appropriate management decision support.展开更多
Universal Soil Loss Equation (USLE) is the most comprehensive technique available to predict the long term average annual rate of erosion on a field slope. USLE was governed by five factors include soil erodibility fa...Universal Soil Loss Equation (USLE) is the most comprehensive technique available to predict the long term average annual rate of erosion on a field slope. USLE was governed by five factors include soil erodibility factor (K), rainfall and runoff erodibility index (R), crop/vegetation and management factor (C), support practice factor (P) and slope length-gradient factor (LS). In the past, K, R and LS factors are extensively studied. But the impacts of factors C and P to outfall Total Suspended Solid (TSS) and % reduction of TSS are not fully studied yet. Therefore, this study employs Buffer Zone Calculator as a tool to determine the sediment removal efficiency for different C and P factors. The selected study areas are Santubong River, Kuching, Sarawak. Results show that the outfall TSS is increasing with the increase of C values. The most effective and efficient land use for reducing TSS among 17 land uses investigated is found to be forest with undergrowth, followed by mixed dipt. forest, forest with no undergrowth, cultivated grass, logging 30, logging 10^6, wet rice, new shifting agriculture, oil palm, rubber, cocoa, coffee, tea and lastly settlement/cleared land. Besides, results also indicate that the % reduction of TSS is increasing with the decrease of P factor. The most effective support practice to reduce the outfall TSS is found to be terracing, followed by contour-strip cropping, contouring and lastly not implementing any soil conservation practice.展开更多
基金Supported by the National High-Technology Research and Development Program of China under Grant Nos 2014AA06A513 and 2013AA065502the National Natural Science Foundation of China under Grant No 61378041the Anhui Province Outstanding Youth Science Fund of China under Grant No 1508085JGD02
文摘Due to its complicated matrix effects, rapid quantitative analysis of chromium in agricultural soils is difficult without the concentration gradient samples by laser-induced breakdown spectroscopy. To improve the analysis speed and accuracy, two calibration models are built with the support vector machine method： one considering the whole spectra and the other based on the segmental spectra input. Considering the results of the multiple linear regression analysis, three segmental spectra are chosen as the input variables of the support vector regression （SVR） model. Compared with the results of the SVR model with the whole spectra input, the relative standard error of prediction is reduced from 3.18% to 2.61% and the running time is saved due to the decrease in the number of input variables, showing the robustness in rapid soil analysis without the concentration gradient samples.
基金National Natural Science Foundation of China under Grand No.51808190the Central Government Guides Local Science and Technology Development Fund Projects under Grand No.XZ202301YD0019C+2 种基金the Foundation of Key Laboratory of Soft Soils and Geoenvironmental Engineering(Zhejiang University)Ministry of Education under Grand No.2022P04the Central University Basic Research Fund of China under Grand No.B220202017。
文摘This research is concentrated on the longitudinal vibration of a tapered pipe pile considering the vertical support of the surrounding soil and construction disturbance.First,the pile-soil system is partitioned into finite segments in the vertical direction and the Voigt model is applied to simulate the vertical support of the surrounding soil acting on the pile segment.The surrounding soil is divided into finite ring-shaped zones in the radial direction to consider the construction disturbance.Then,the shear complex stiffness at the pile-soil interface is derived by solving the dynamic equilibrium equation for the soil from the outermost to innermost zone.The displacement impedance at the top of an arbitrary pile segment is obtained by solving the dynamic equilibrium equation for the pile and is combined with the vertical support of the surrounding soil to derive the displacement impedance at the bottom of the upper adjacent segment.Further,the displacement impedance at the pile head is obtained based on the impedance function transfer technique.Finally,the reliability of the proposed solution is verified,followed by a sensitivity analysis concerning the coupling effect of the pile parameters,construction disturbance and the vertical support of the surrounding soil on the displacement impedance of the pile.
基金supported by the National Basic Research Program of China (the 973 Program,Grant No.2010CB951101)the Program for Changjiang Scholars and Innovative Research Teams in Universities,the Ministry of Education,China (Grant No. IRT0717)
文摘Hybrid data assimilation （DA） is a method seeing more use in recent hydrology and water resources research. In this study, a DA method coupled with the support vector machines （SVMs） and the ensemble Kalman filter （EnKF） technology was used for the prediction of soil moisture in different soil layers： 0-5 cm, 30 cm, 50 cm, 100 cm, 200 cm, and 300 cm. The SVM methodology was first used to train the ground measurements of soil moisture and meteorological parameters from the Meilin study area, in East China, to construct soil moisture statistical prediction models. Subsequent observations and their statistics were used for predictions, with two approaches： the SVM predictor and the SVM-EnKF model made by coupling the SVM model with the EnKF technique using the DA method. Validation results showed that the proposed SVM-EnKF model can improve the prediction results of soil moisture in different layers, from the surface to the root zone.
基金supported by the National Natural Science Foundation of China (Nos. 41501229, 41371224, 41130530, and 91325301)the China Postdoctoral Science Foundation (No. 2015M581876)
文摘Soil diagnostic horizons, which each have a set of quantified properties, play a key role in soil classification. However, they are difficult to predict, and few attempts have been made to map their spatial occurrence. We evaluated and compared four machine learning algorithms, namely, the classification and regression tree(CART), random forest(RF), boosted regression trees(BRT), and support vector machine(SVM), to map the occurrence of the soil mattic horizon in the northeastern Qinghai-Tibetan Plateau using readily available ancillary data. The mechanisms of resampling and ensemble techniques significantly improved prediction accuracies(measured based on area under the receiver operator characteristic curve score(AUC)) and produced more stable results for the BRT(AUC of 0.921 ± 0.012, mean ± standard deviation) and RF(0.908 ± 0.013) algorithms compared to the CART algorithm(0.784 ± 0.012), which is the most commonly used machine learning method. Although the SVM algorithm yielded a comparable AUC value(0.906 ± 0.006) to the RF and BRT algorithms, it is sensitive to parameter settings, which are extremely time-consuming.Therefore, we consider it inadequate for occurrence-distribution modeling. Considering the obvious advantages of high prediction accuracy, robustness to parameter settings, the ability to estimate uncertainty in prediction, and easy interpretation of predictor variables, BRT seems to be the most desirable method. These results provide an insight into the use of machine learning algorithms to map the mattic horizon and potentially other soil diagnostic horizons.
文摘The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and soil informatization management. A total of 92 brown soil samples were collected from the orchard of Qixia County, Yantai City, Shandong Province. After drying and grinding, the hyperspectrum of the soil was measured in the laboratory using ASD FieldSpec3. The TN contents of brown soil were measured by Kjeldahl method. The sensitive wavelengths were selected by multiple linear stepwise regression method. The hyperspectral estimation model of TN was established by Random Forest (RF) and Support Vector Machines (SVM). The models were validated by independent samples. The best estimation model was obtained. The sensitive wavelengths were 956 nm, 995 nm, 1020 nm, 1410 nm, 1659 nm and 2020 nm. The coefficients of determination (R2) of the two estimation models were 0.8011 and 0.8283, the root mean square errors (RMSE) were 0.022 and 0.025, and relative errors (RE) were 0.1422 and 0.1639, respectively. Random Forest model and Support Vector Machines model are feasible in estimating TN contents, but the Support Vector Machines model is better.
基金Project (50678115) supported by the National Natural Science Foundation of ChinaProject (07JCZDJC09800) supported by Tianjin Natural Science Foundation
文摘A finite difference numerical method was adopted to evaluate the pile lateral behavior of pile supported embankment. A published case history was used to verify the proposed methodology. By simulating the case history, the determination of parameters needed were verified. Then three embankments constructed on different ground conditions with different soil-pile relative stiffnesses were analyzed to study pile lateral behaviors including pile deflection and bending moment. The results show that pile deflections and bending moments induced by soil lateral deformation and embankment vertical load are different for piles at different positions under the same embankment. The relative stiffness between pile and soil affected by the properties of different reinforcing piles such as concrete pile and deep mixing method pile exert important effects on the pile lateral behavior and the pile's failure modes. Consequently, it is necessary to consider the different piles lateral behaviors and possible failure modes at different positions and the different piles proprieties with different reinforcing methods in the embankment stability analysis.
基金supported by the Pedometrics, Landscape Analysis, and GIS Laboratory, Soil and Water Sciences Department, University of Florida, USA
文摘The applicability, transferability, and scalability of visible/near-infrared(VNIR)-derived soil total carbon(TC) models are still poorly understood. The objectives of this study were to: i) compare models of three multivariate statistical methods, partial least squares regression(PLSR), support vector machine(SVM), and random forest methods, to predict soil logarithm-transformed TC(logTC) using five fields(local scale) and a pooled(regional-scale) VNIR spectral dataset(a total of 560 TC spectral datasets), ii)assess the model transferability among fields, and iii) evaluate their up-and downscaling behaviors in Florida, USA. The transferability and up-and downscaling of the models were limited by the following factors: i) the spectral data domain, ii) soil attribute domain,iii) methods that describe the internal model structure of VNIR-TC relationships, and iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R^2> 0.86,bias < 0.01%, root mean squared error(RMSE) = 0.09%, residual predication deviation(RPD) > 2.70%, and ratio of prediction error to interquartile range(RPIQ) > 4.54. The PLSR method performed substantially better than the SVM method to scale and transfer the TC models. This could be attributed to the tendency of SVM to overfit models, while the asset of the PLSR method was its robustness when the models were validated with independent datasets, transferred, and/or scaled. The upscaled soil TC models performed somewhat better in terms of model fit(R2), RPD, and RPIQ, whereas the downscaled models showed less bias and smaller RMSE based on PLSR. We found no universal trend indicating which of the four limiting factors mentioned above had the most impact that constrained the transferability and scalability of the models. Given that several factors can impinge on the empirically derived soil spectral prediction models, as demonstrated by this study, more focus on their applicability and scalability is needed.
文摘The use of a crop model like STICS for appropriate management decision support requires a good knowledge of all the parameters of the model. Among them, the soil parameters are difficult to know at each point of interest and costly techniques may be used to measure them. It is therefore important to know which soil parameters need to be determined. It can be stated that those which affect significantly the output variable deserve an accurate determination while those which slightly affect the model output variable do not. This paper demonstrates how a global sensitivity analysis method based on variance decomposition can be applied on soil parameters in order to divide them in the two categories. The Extended FAST method applied to the crop model STICS and a set of 13 soil parameters first allows to calculate the part of variance explained by each soil parameter (giving global sensitivity indices of the soil parameters) and the coefficient of variation of the output variables (measuring the effect of the parameter uncertainty on each variable). These metrics are therefore used for deciding on the importance of the parameter value measurement. Different output variables (Leaf Area Index and chlorophyll content) are evaluated at different stages of interest while others (crop yield, grain protein content, soil mineral nitrogen) are evaluated at harvest. The analysis is applied on two different annual crops (wheat and sugar beet), two contrasted weather and two types of soil depth. When the uncertainty of the output generated by the soil parameters is large (coefficient of variation > 1/3), only the parameters having a significant global sensitivity indices (higher than 10%) are retained. The results show that the number of soil parameters which deserve an accurate determination can be significantly reduced by the use of this relevant method for appropriate management decision support.
文摘Universal Soil Loss Equation (USLE) is the most comprehensive technique available to predict the long term average annual rate of erosion on a field slope. USLE was governed by five factors include soil erodibility factor (K), rainfall and runoff erodibility index (R), crop/vegetation and management factor (C), support practice factor (P) and slope length-gradient factor (LS). In the past, K, R and LS factors are extensively studied. But the impacts of factors C and P to outfall Total Suspended Solid (TSS) and % reduction of TSS are not fully studied yet. Therefore, this study employs Buffer Zone Calculator as a tool to determine the sediment removal efficiency for different C and P factors. The selected study areas are Santubong River, Kuching, Sarawak. Results show that the outfall TSS is increasing with the increase of C values. The most effective and efficient land use for reducing TSS among 17 land uses investigated is found to be forest with undergrowth, followed by mixed dipt. forest, forest with no undergrowth, cultivated grass, logging 30, logging 10^6, wet rice, new shifting agriculture, oil palm, rubber, cocoa, coffee, tea and lastly settlement/cleared land. Besides, results also indicate that the % reduction of TSS is increasing with the decrease of P factor. The most effective support practice to reduce the outfall TSS is found to be terracing, followed by contour-strip cropping, contouring and lastly not implementing any soil conservation practice.
