Microbially induced calcite precipitation(MICP)is a recently developed technique for microbiological ground improvement that has been applied for mitigating various geotechnical challenges.However,the major challenges...Microbially induced calcite precipitation(MICP)is a recently developed technique for microbiological ground improvement that has been applied for mitigating various geotechnical challenges.However,the major challenges,such as calcite precipitation uniformity,presence of different bacteria,cementation solution optimization for cost reduction,and implementation under non-sterile and uncontrolled field environment are still not fully explored and require detailed investigation before field application.This study aims to address these challenges of MICP to improve the geotechnical properties of sandy soils.Several series of experiments were conducted using poorly graded Narmada River(India)sand,which were subjected to various biotreatment schemes and tested for unconfined compressive strength(UCS),split tensile strength(STS),ultrasonic pulse velocity(UPV),hydraulic conductivity(after 6 d,12 d,and 18 d of treatment),and calcite content.The microstructure of sand was examined through a scanning electron microscope(SEM).Initially,the sand was individually augmented with two non-pathogenic bacterial strains,i.e.Sporosarcina(S.)pasteurii and Bacillus(B.)sphaericus.The stopped-flow injection method was adopted to provide cementation solutions at three different durations(treatment cycle)of 12 h,24 h,and 48 h and three different pore volumes(PVs)of 1,0.75,and 0.5.The pore volume here refers to the porosity which is expressed as a ratio,i.e.a porosity of 50%was used as 0.5.The results showed rock-like behaviors of biocemented sand with the UCS,STS,and UPV enhancement up to 2333 kPa,437 kPa,and 2670 m/s,respectively.The hydraulic conductivity reduction of 96.6%was achieved by 12%of calcite formation after 18 d of treatment using Sporosarcina pasteurii,12-h treatment cycle,and one pore volume of cementation media in each cycle.Overall,a 24-h treatment cycle and 0.5-pore volume cementation solution were found to be the optimal treatment which was effective and economical to achieve heavily cemented,rock-type biocemented sand using both bacteria.展开更多
In abandoned mine sites, i.e., mine sites where mining operations have ended, wide spread contaminations are often evident, but the potential sources and pathways of contamination especially through the subsurface, ar...In abandoned mine sites, i.e., mine sites where mining operations have ended, wide spread contaminations are often evident, but the potential sources and pathways of contamination especially through the subsurface, are difficult to identify due to inadequate and sparse geochemical measurements available. Therefore, it is essential to design and implement a planned monitoring net-work to obtain essential information required for establishing the potential contamination source locations, i.e., waste dumps, tailing dams, pits and possible pathways through the subsurface, and to design a remediation strategy for rehabilitation. This study presents an illustrative application of modeling the flow and transport processes and monitoring network design in a study area hydrogeologically resembling an abandoned mine site in Queensland, Australia. In this preliminary study, the contaminant transport process modeled does not incorporate the reactive geochemistry of the contaminants. The transport process is modeled considering a generic conservative contaminant for the illustrative purpose of showing the potential application of an optimal monitoring design methodology. This study aims to design optimal monitoring network to: 1) minimize the contaminant solute mass estimation error;2) locate the plume boundary;3) select the monitoring locations with (potentially) high concentrations. A linked simulation optimization based methodology is utilized for optimal monitoring network design. The methodology is applied utilizing a recently developed software package CARE-GWMND, developed at James Cook University for optimal monitoring network design. Given the complexity of the groundwater systems and the sparsity of pollutant concentration observation data from the field, this software is capable of simulating the groundwater flow and solute transport with spatial interpolation of data from a sparse set of available data, and it utilizes the optimization algorithm to determine optimum locations for implementing monitoring wells.展开更多
Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually ...Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually happens a long time after the start of contaminant source(s) activities. Usually, limited information is available which also can be erroneous. This study utilizes Self-Organizing Map (SOM) and Gaussian Process Regression (GPR) algorithms to develop surrogate models that can approximate the complex flow and transport processes in a contaminated aquifer. The important feature of these developed surrogate models is that unlike the previous methods, they can be applied independently of any linked optimization model solution for characterizing of unknown groundwater contaminant sources. The performance of the developed surrogate models is evaluated for source characterization in an experimental contaminated aquifer site within the heterogeneous sand aquifer, located at the Botany Basin, New South Wales, Australia. In this study, the measured contaminant concentrations and hydraulic conductivity values are assumed to contain random errors. Simulated responses of the aquifer to randomly specified contamination stresses as simulated by using a three-dimensional numerical simulation model are utilized for initial training of the surrogate models. The performance evaluation results obtained by using different surrogate models are also compared. The evaluation results demonstrate the different capabilities of the developed surrogate models. These capabilities lead to development of an efficient methodology for source characterization based on utilizing the trained and tested surrogate models in an inverse mode. The obtained results are satisfactory and show the potential applicability of the SOM and GPR-based surrogate models for unknown groundwater contaminant source characterization in an inverse mode.展开更多
Droughts occur in all climatic regions around the world costing a large expense to global economies. Reasonably accurate prediction of drought events helps water managers proper planning for utilization of limited wat...Droughts occur in all climatic regions around the world costing a large expense to global economies. Reasonably accurate prediction of drought events helps water managers proper planning for utilization of limited water resources and distribution of available waters to different sectors and avoid catastrophic consequences. Therefore, a means to create a simplistic approach for forecasting drought conditions with easily accessible parameters is highly desirable. This study proposes and evaluates newly developed accurate prediction models utilizing various hydrologic, meteorological, and geohydrology parameters along with the use of Artificial Neural Network (ANN) models with various forecast lead times. The present study develops a multitude of forecasting models to predict drought indices such as the Standard Precipitation Index with a lead-time of up to 6 months, and the Soil Moisture Index with a lead-time of 3 months. Furthermore, prediction models with the capability of approximating surface and groundwater storage levels including the Ross River Dam level have been developed with relatively high accuracy with a lead-time of 3 months. The results obtained from these models were compared to current values, revealing that ANN based approach can be used as a simple and effective predictive model that can be utilized for prediction of different aspects of drought scenarios in a typical study area like Townsville, North Queensland, Australia which had suffered severe recent drought conditions for almost six recent years (2014 to early 2019).展开更多
This paper reviews several recently-developed techniques for the minimum-cost optimal design of water-retaining structures (WRSs), which integrate the effects of seepage. These include the incorporation of uncertainty...This paper reviews several recently-developed techniques for the minimum-cost optimal design of water-retaining structures (WRSs), which integrate the effects of seepage. These include the incorporation of uncertainty in heterogeneous soil parameter estimates and quantification of reliability. This review is limited to methods based on coupled simulation-optimization (S-O) models. In this context, the design of WRSs is mainly affected by hydraulic design variables such as seepage quantities, which are difficult to determine from closed-form solutions or approximation theories. An S-O model is built by integrating numerical seepage modeling responses to an optimization algorithm based on efficient surrogate models. The surrogate models (meta-models) are trained on simulated data obtained from finite element numerical code solutions. The proposed methodology is applied using several machine learning techniques and optimization solvers to optimize the design of WRS by incorporating different design variables and boundary conditions. Additionally, the effects of several scenarios of flow domain hydraulic conductivity are integrated into the S-O model. Also, reliability based optimum design concepts are incorporated in the S-O model to quantify uncertainty in seepage quantities due to uncertainty in hydraulic conductivity estimates. We can conclude that the S-O model can efficiently optimize WRS designs. The ANN, SVM, and GPR machine learning technique-based surrogate models are efficiently and expeditiously incorporated into the S-O models to imitate the numerical responses of simulations of various problems.展开更多
In several parts of the world, disposal of waste materials such as fly ash is a great problem. Application of waste materials as structural fills in foundations is one of the best solutions to disposal problems, becau...In several parts of the world, disposal of waste materials such as fly ash is a great problem. Application of waste materials as structural fills in foundations is one of the best solutions to disposal problems, because wastes can be used in large volumes in such applications. There may be difficulty due to poor load-bearing capacity of fly ash, especially when footing rests on the top of the fly ash fill slope. Inclusion of polymeric reinforcements as horizontal sheets within the fill may be one of the most viable solutions to improving the load-bearing capacity of reinforced fly ash slope, and it is particularly important for the situations where foundations need to be located either on the top of a slope or on slope itself. The present work is aimed at investigating the efficacy of a single layer of reinforcement in improving the lo, ad-bearing capacity when it gets incorporated within the body of a model fly ash embankment slope. An increase in load bearing capacity due to the incorporation of reinforcement in the model slope was found by conducting laboratory tests. Experimental results were compared by numerical values obtained using software GEO5 and PLAXIS.展开更多
Characterization of unknown groundwater contaminant sources in terms of location, magnitude and duration of source activity is a complex problem. In this study, to increase the efficiency and accuracy of source charac...Characterization of unknown groundwater contaminant sources in terms of location, magnitude and duration of source activity is a complex problem. In this study, to increase the efficiency and accuracy of source characterization an alternative methodology to the methodologies proposed earlier is developed. This methodology, Adaptive Surrogate Modeling Based Optimization (ASMBO) uses the capabilities of Self Organizing Map (SOM) algorithm to design the surrogate models and adaptive surrogate models for source characterization. The most important advantage of this methodology is its direct utilization for groundwater contaminant characterization without the necessity of utilizing a linked simulation optimization model. The validation of the SOM based surrogate models and SOM based adaptive surrogate models demonstrates that the quantity and quality of initial sample sizes have crucial role on the accuracy of solutions as the designed monitoring locations. The performance evaluation results of the proposed methodology are obtained using error free and erroneous concentration measurement data. These results demonstrate that the developed methodology could approximate groundwater flow and transport simulation models, and substitute the optimization model for characterization of unknown groundwater contaminant sources in terms of location, magnitude and duration of source activity.展开更多
The Himalayan region has been severely affected by landslides especially during the monsoons. In particular, Kalimpong region in Darjeeling Himalayas has recorded several landslides and has caused significant loss of ...The Himalayan region has been severely affected by landslides especially during the monsoons. In particular, Kalimpong region in Darjeeling Himalayas has recorded several landslides and has caused significant loss of life, property and agricultural land. The study region, Chibo has experienced several landslides in the past which were mainly debris and earth slide. Globally, several types of rainfall thresholds have been used to determine rainfall-induced landslide incidents. In this paper, probabilistic thresholds have been defined as it would provide a better understanding compared to deterministic thresholds which provide binary results, i.e., either landslide or no landslide for a particular rainfall event. Not much research has been carried out towards validation of rainfall thresholds using an effective and robust monitoring system. The thresholds are then validated using a reliable system utilizing Microelectromechanical Systems(MEMS) tilt sensor and volumetric water content sensor installed in the region. The system measures the tilt of the instrument which is installed at shallow depths and is ideal for an early warning system for shallow landslides. The change in observed tilt angles due to rainfall would give an understanding of the applicability of the probabilistic model. The probabilities determined using Bayes' theorem have been calculated using the rainfall parameters and landslide data in 2010-2016. The rainfall values were collected from an automatic rain gauge setup near the Chibo region. The probabilities were validated using the MEMS based monitoring system setup in Chibo for the monsoon season of 2017. This is the first attempt to determine probabilities and validate it with a robust and effective monitoring system in Darjeeling Himalayas. This study would help in developing an early warning system for regions where the installation of monitoring systems may not be feasible.展开更多
Historical mining activities often lead to continuing wide spread contaminants in both groundwater and surface water in previously operational mine site areas. The contamination may continue for many years after closi...Historical mining activities often lead to continuing wide spread contaminants in both groundwater and surface water in previously operational mine site areas. The contamination may continue for many years after closing down the mining activities. The essential first step for sustainable management of groundwater and development of remediation strategies is the unknown contaminant source characterization. In a mining site, there are multiple species of contaminants involving complex geochemical processes. It is difficult to identify the potential sources and pathways incorporating the chemically reactive multiple species of contaminants making the source characterization process more challenging. To address this issue, a reactive transport simulation model PHT3D is linked to a Simulated Annealing based the optimum decision model. The numerical simulation model PHT3D is utilized for numerically simulating the reactive transport process involving multiple species in the former mine site area. The simulation results from the calibrated PHT3D model are illustrated, with and without incorporating the chemical reactions. These comparisons show the utility of using a reactive, geochemical transport process’ simulation model. Performance evaluation of the linked simulation optimization methodology is evaluated for a contamination scenario in a former mine site in Queensland, Australia. These performance evaluation results illustrate the applicability of linked simulation optimization model to identify the source characteristics while using PHT3D as a numerical reactive chemical species’ transport simulation model for the hydro-geochemically complex aquifer study area.展开更多
In this paper,we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree(REPT)as a base classifier with the Bagging(B),Decorate(D),and Random Subspace(RSS)ensemble learning te...In this paper,we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree(REPT)as a base classifier with the Bagging(B),Decorate(D),and Random Subspace(RSS)ensemble learning techniques for spatial prediction of rainfallinduced landslides in the Uttarkashi district,located in the Himalayan range,India.To do so,a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets.Root Mean Square Error(RMSE)and Area Under the receiver operating characteristic Curve(AUC)were used to evaluate the training and validation performances of the models.The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides.The D-REPT model with RMSE=0.351 and AUC=0.907 was identified as the most accurate model,followed by RSS-REPT(RMSE=0.353 and AUC=0.898),B-REPT(RMSE=0.396 and AUC=0.876),and the single REPT model(RMSE=0.398 and AUC=0.836),respectively.The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world.展开更多
文摘Microbially induced calcite precipitation(MICP)is a recently developed technique for microbiological ground improvement that has been applied for mitigating various geotechnical challenges.However,the major challenges,such as calcite precipitation uniformity,presence of different bacteria,cementation solution optimization for cost reduction,and implementation under non-sterile and uncontrolled field environment are still not fully explored and require detailed investigation before field application.This study aims to address these challenges of MICP to improve the geotechnical properties of sandy soils.Several series of experiments were conducted using poorly graded Narmada River(India)sand,which were subjected to various biotreatment schemes and tested for unconfined compressive strength(UCS),split tensile strength(STS),ultrasonic pulse velocity(UPV),hydraulic conductivity(after 6 d,12 d,and 18 d of treatment),and calcite content.The microstructure of sand was examined through a scanning electron microscope(SEM).Initially,the sand was individually augmented with two non-pathogenic bacterial strains,i.e.Sporosarcina(S.)pasteurii and Bacillus(B.)sphaericus.The stopped-flow injection method was adopted to provide cementation solutions at three different durations(treatment cycle)of 12 h,24 h,and 48 h and three different pore volumes(PVs)of 1,0.75,and 0.5.The pore volume here refers to the porosity which is expressed as a ratio,i.e.a porosity of 50%was used as 0.5.The results showed rock-like behaviors of biocemented sand with the UCS,STS,and UPV enhancement up to 2333 kPa,437 kPa,and 2670 m/s,respectively.The hydraulic conductivity reduction of 96.6%was achieved by 12%of calcite formation after 18 d of treatment using Sporosarcina pasteurii,12-h treatment cycle,and one pore volume of cementation media in each cycle.Overall,a 24-h treatment cycle and 0.5-pore volume cementation solution were found to be the optimal treatment which was effective and economical to achieve heavily cemented,rock-type biocemented sand using both bacteria.
文摘In abandoned mine sites, i.e., mine sites where mining operations have ended, wide spread contaminations are often evident, but the potential sources and pathways of contamination especially through the subsurface, are difficult to identify due to inadequate and sparse geochemical measurements available. Therefore, it is essential to design and implement a planned monitoring net-work to obtain essential information required for establishing the potential contamination source locations, i.e., waste dumps, tailing dams, pits and possible pathways through the subsurface, and to design a remediation strategy for rehabilitation. This study presents an illustrative application of modeling the flow and transport processes and monitoring network design in a study area hydrogeologically resembling an abandoned mine site in Queensland, Australia. In this preliminary study, the contaminant transport process modeled does not incorporate the reactive geochemistry of the contaminants. The transport process is modeled considering a generic conservative contaminant for the illustrative purpose of showing the potential application of an optimal monitoring design methodology. This study aims to design optimal monitoring network to: 1) minimize the contaminant solute mass estimation error;2) locate the plume boundary;3) select the monitoring locations with (potentially) high concentrations. A linked simulation optimization based methodology is utilized for optimal monitoring network design. The methodology is applied utilizing a recently developed software package CARE-GWMND, developed at James Cook University for optimal monitoring network design. Given the complexity of the groundwater systems and the sparsity of pollutant concentration observation data from the field, this software is capable of simulating the groundwater flow and solute transport with spatial interpolation of data from a sparse set of available data, and it utilizes the optimization algorithm to determine optimum locations for implementing monitoring wells.
文摘Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually happens a long time after the start of contaminant source(s) activities. Usually, limited information is available which also can be erroneous. This study utilizes Self-Organizing Map (SOM) and Gaussian Process Regression (GPR) algorithms to develop surrogate models that can approximate the complex flow and transport processes in a contaminated aquifer. The important feature of these developed surrogate models is that unlike the previous methods, they can be applied independently of any linked optimization model solution for characterizing of unknown groundwater contaminant sources. The performance of the developed surrogate models is evaluated for source characterization in an experimental contaminated aquifer site within the heterogeneous sand aquifer, located at the Botany Basin, New South Wales, Australia. In this study, the measured contaminant concentrations and hydraulic conductivity values are assumed to contain random errors. Simulated responses of the aquifer to randomly specified contamination stresses as simulated by using a three-dimensional numerical simulation model are utilized for initial training of the surrogate models. The performance evaluation results obtained by using different surrogate models are also compared. The evaluation results demonstrate the different capabilities of the developed surrogate models. These capabilities lead to development of an efficient methodology for source characterization based on utilizing the trained and tested surrogate models in an inverse mode. The obtained results are satisfactory and show the potential applicability of the SOM and GPR-based surrogate models for unknown groundwater contaminant source characterization in an inverse mode.
文摘Droughts occur in all climatic regions around the world costing a large expense to global economies. Reasonably accurate prediction of drought events helps water managers proper planning for utilization of limited water resources and distribution of available waters to different sectors and avoid catastrophic consequences. Therefore, a means to create a simplistic approach for forecasting drought conditions with easily accessible parameters is highly desirable. This study proposes and evaluates newly developed accurate prediction models utilizing various hydrologic, meteorological, and geohydrology parameters along with the use of Artificial Neural Network (ANN) models with various forecast lead times. The present study develops a multitude of forecasting models to predict drought indices such as the Standard Precipitation Index with a lead-time of up to 6 months, and the Soil Moisture Index with a lead-time of 3 months. Furthermore, prediction models with the capability of approximating surface and groundwater storage levels including the Ross River Dam level have been developed with relatively high accuracy with a lead-time of 3 months. The results obtained from these models were compared to current values, revealing that ANN based approach can be used as a simple and effective predictive model that can be utilized for prediction of different aspects of drought scenarios in a typical study area like Townsville, North Queensland, Australia which had suffered severe recent drought conditions for almost six recent years (2014 to early 2019).
文摘This paper reviews several recently-developed techniques for the minimum-cost optimal design of water-retaining structures (WRSs), which integrate the effects of seepage. These include the incorporation of uncertainty in heterogeneous soil parameter estimates and quantification of reliability. This review is limited to methods based on coupled simulation-optimization (S-O) models. In this context, the design of WRSs is mainly affected by hydraulic design variables such as seepage quantities, which are difficult to determine from closed-form solutions or approximation theories. An S-O model is built by integrating numerical seepage modeling responses to an optimization algorithm based on efficient surrogate models. The surrogate models (meta-models) are trained on simulated data obtained from finite element numerical code solutions. The proposed methodology is applied using several machine learning techniques and optimization solvers to optimize the design of WRS by incorporating different design variables and boundary conditions. Additionally, the effects of several scenarios of flow domain hydraulic conductivity are integrated into the S-O model. Also, reliability based optimum design concepts are incorporated in the S-O model to quantify uncertainty in seepage quantities due to uncertainty in hydraulic conductivity estimates. We can conclude that the S-O model can efficiently optimize WRS designs. The ANN, SVM, and GPR machine learning technique-based surrogate models are efficiently and expeditiously incorporated into the S-O models to imitate the numerical responses of simulations of various problems.
文摘In several parts of the world, disposal of waste materials such as fly ash is a great problem. Application of waste materials as structural fills in foundations is one of the best solutions to disposal problems, because wastes can be used in large volumes in such applications. There may be difficulty due to poor load-bearing capacity of fly ash, especially when footing rests on the top of the fly ash fill slope. Inclusion of polymeric reinforcements as horizontal sheets within the fill may be one of the most viable solutions to improving the load-bearing capacity of reinforced fly ash slope, and it is particularly important for the situations where foundations need to be located either on the top of a slope or on slope itself. The present work is aimed at investigating the efficacy of a single layer of reinforcement in improving the lo, ad-bearing capacity when it gets incorporated within the body of a model fly ash embankment slope. An increase in load bearing capacity due to the incorporation of reinforcement in the model slope was found by conducting laboratory tests. Experimental results were compared by numerical values obtained using software GEO5 and PLAXIS.
文摘Characterization of unknown groundwater contaminant sources in terms of location, magnitude and duration of source activity is a complex problem. In this study, to increase the efficiency and accuracy of source characterization an alternative methodology to the methodologies proposed earlier is developed. This methodology, Adaptive Surrogate Modeling Based Optimization (ASMBO) uses the capabilities of Self Organizing Map (SOM) algorithm to design the surrogate models and adaptive surrogate models for source characterization. The most important advantage of this methodology is its direct utilization for groundwater contaminant characterization without the necessity of utilizing a linked simulation optimization model. The validation of the SOM based surrogate models and SOM based adaptive surrogate models demonstrates that the quantity and quality of initial sample sizes have crucial role on the accuracy of solutions as the designed monitoring locations. The performance evaluation results of the proposed methodology are obtained using error free and erroneous concentration measurement data. These results demonstrate that the developed methodology could approximate groundwater flow and transport simulation models, and substitute the optimization model for characterization of unknown groundwater contaminant sources in terms of location, magnitude and duration of source activity.
基金the Department of Science & Technology (DST), New Delhi for funding the research project Landslide hazard assessment and monitoring at Chibo Pashyar, Kalimpong (Grant No. NRDMS/02/31/015(G))
文摘The Himalayan region has been severely affected by landslides especially during the monsoons. In particular, Kalimpong region in Darjeeling Himalayas has recorded several landslides and has caused significant loss of life, property and agricultural land. The study region, Chibo has experienced several landslides in the past which were mainly debris and earth slide. Globally, several types of rainfall thresholds have been used to determine rainfall-induced landslide incidents. In this paper, probabilistic thresholds have been defined as it would provide a better understanding compared to deterministic thresholds which provide binary results, i.e., either landslide or no landslide for a particular rainfall event. Not much research has been carried out towards validation of rainfall thresholds using an effective and robust monitoring system. The thresholds are then validated using a reliable system utilizing Microelectromechanical Systems(MEMS) tilt sensor and volumetric water content sensor installed in the region. The system measures the tilt of the instrument which is installed at shallow depths and is ideal for an early warning system for shallow landslides. The change in observed tilt angles due to rainfall would give an understanding of the applicability of the probabilistic model. The probabilities determined using Bayes' theorem have been calculated using the rainfall parameters and landslide data in 2010-2016. The rainfall values were collected from an automatic rain gauge setup near the Chibo region. The probabilities were validated using the MEMS based monitoring system setup in Chibo for the monsoon season of 2017. This is the first attempt to determine probabilities and validate it with a robust and effective monitoring system in Darjeeling Himalayas. This study would help in developing an early warning system for regions where the installation of monitoring systems may not be feasible.
文摘Historical mining activities often lead to continuing wide spread contaminants in both groundwater and surface water in previously operational mine site areas. The contamination may continue for many years after closing down the mining activities. The essential first step for sustainable management of groundwater and development of remediation strategies is the unknown contaminant source characterization. In a mining site, there are multiple species of contaminants involving complex geochemical processes. It is difficult to identify the potential sources and pathways incorporating the chemically reactive multiple species of contaminants making the source characterization process more challenging. To address this issue, a reactive transport simulation model PHT3D is linked to a Simulated Annealing based the optimum decision model. The numerical simulation model PHT3D is utilized for numerically simulating the reactive transport process involving multiple species in the former mine site area. The simulation results from the calibrated PHT3D model are illustrated, with and without incorporating the chemical reactions. These comparisons show the utility of using a reactive, geochemical transport process’ simulation model. Performance evaluation of the linked simulation optimization methodology is evaluated for a contamination scenario in a former mine site in Queensland, Australia. These performance evaluation results illustrate the applicability of linked simulation optimization model to identify the source characteristics while using PHT3D as a numerical reactive chemical species’ transport simulation model for the hydro-geochemically complex aquifer study area.
文摘In this paper,we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree(REPT)as a base classifier with the Bagging(B),Decorate(D),and Random Subspace(RSS)ensemble learning techniques for spatial prediction of rainfallinduced landslides in the Uttarkashi district,located in the Himalayan range,India.To do so,a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets.Root Mean Square Error(RMSE)and Area Under the receiver operating characteristic Curve(AUC)were used to evaluate the training and validation performances of the models.The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides.The D-REPT model with RMSE=0.351 and AUC=0.907 was identified as the most accurate model,followed by RSS-REPT(RMSE=0.353 and AUC=0.898),B-REPT(RMSE=0.396 and AUC=0.876),and the single REPT model(RMSE=0.398 and AUC=0.836),respectively.The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world.
