AbstractThis study demonstrates the influence of climate change-induced sea level rise on multiob... more AbstractThis study demonstrates the influence of climate change-induced sea level rise on multiobjective saltwater intrusion management strategies in coastal aquifers. Three metamodels were develop...
Meta-model based coupled simulation-optimization methodology is an effective tool in developing s... more Meta-model based coupled simulation-optimization methodology is an effective tool in developing sustainable saltwater intrusion management strategies for coastal aquifers. Such management strategies largely depend on the accuracy, reliability, and computational feasibility of meta-models and the numerical simulation model. However, groundwater models are associated with a certain amount of uncertainties, e.g. parameter uncertainty and uncertainty in prediction. This study addresses uncertainties related to input parameters of the groundwater flow and transport system by using a set of randomized input parameters. Three meta-models are compared to characterize responses of water quality in coastal aquifers due to groundwater extraction patterns under parameter uncertainty. The ensemble of the best meta-model is then coupled with a multi-objective optimization algorithm to develop a saltwater intrusion management model. Uncertainties in hydraulic conductivity, compressibility, bulk de...
The present study evaluates the application of the hybrid machine learning methods to detect chan... more The present study evaluates the application of the hybrid machine learning methods to detect changes of land use with a focus on agricultural lands through remote sensing data processing. Two spectral images by Landsat 8 were applied to train and test the machine learning model. Feed forward neural network classifier was utilized as the machine learning model in which two evolutionary algorithms including particle swarm optimization and invasive weed optimization were applied for the training process. Moreover, three conventional training methods including Levenberg–Marquardt back propagation (LM), Scaled conjugate gradient backpropagation (SCG) and BFGS quasi-Newton backpropagation (BFG) were used for comparing the robustness and reliability of the evolutionary algorithms. Based on the results in the case study, evolutionary algorithms are not a reliable method for detecting changes through the remote sensing analysis in terms of accuracy and computational complexities. Either BFG ...
The present study proposes a novel framework to optimize the reservoir operation through linking ... more The present study proposes a novel framework to optimize the reservoir operation through linking mesohabitat hydraulic modeling and metaheuristic optimization to mitigate environmental impact at downstream of the reservoir. Environmental impact function was developed by mesohabitat hydraulic simulation. Then, the developed function was utilized in the structure of the reservoir operation optimization. Different metaheuristic algorithms including practice swarm optimization, invasive weed optimization, differential evolution and biogeography-based algorithm were used to optimize reservoir operation. Root mean square error (RMSE) and reliability index were utilized to measure the performance of algorithms. Based on the results in the case study, the proposed method is robust for mitigating downstream environmental impacts and sustaining water supply by the reservoir. RMSE for mesohabitats is 8% that indicates the robustness of proposed method to mitigate environmental impacts at downs...
Reference evapotranspiration (ET0) is an important driver in managing scarce water resources and ... more Reference evapotranspiration (ET0) is an important driver in managing scarce water resources and making decisions on real-time and future irrigation scheduling. Therefore, accurate prediction of ET0 is crucial in water resources management. In this study, the prediction of ET0 was performed employing several optimization algorithms tuned Fuzzy Inference System (FIS) and Fuzzy Tree (FT) models, for the first time, whose generalization capability was tested using data from other stations. The FISs and FTs were developed through parameter tuning using Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Pattern Search (PS), and their combinations. The FT was developed by combining several fuzzy objects that received ranked meteorological variables. A total of 50 FIS and FT models were developed and the model ranking was performed utilizing Shannon’s Entropy (SE). Evaluation outcomes revealed the superiority of the hybrid PSO-GA tuned Sugeno type 1 FT model (with R = 0.929, NRMSE ...
Journal of Water Supply: Research and Technology-Aqua, 2022
Balancing the benefits and environmental degradations of the reservoirs is a challenging issue in... more Balancing the benefits and environmental degradations of the reservoirs is a challenging issue in the reservoir management. The present study proposes and evaluates an integrated framework to optimize reservoir operation in which hydropower loss and economic loss of irrigation supply are minimized while ecological degradations at downstream river are alleviated. The ecohydraulic simulation was utilized in the structure of the reservoir operation optimization. Reservoir operation losses and environmental degradations were minimized in three hydrological conditions including dry years, normal years and wet years. Moreover, the cropping pattern optimization was applied to mitigate the economic loss of irrigation supply as the main responsibility of the reservoir in the study area. Particle swarm optimization was applied in the reservoir operation optimization. Based on the results in the case study, reliability indices of hydropower production and farmers’ revenue are 15–25 and 30–60%,...
Journal of the Institution of Engineers India Civil Engineering Division, 2000
This paper presents the three-dimensional simulation of transient seawater intrusion resulting fr... more This paper presents the three-dimensional simulation of transient seawater intrusion resulting from some plausible stress scenarios. The density dependent miscible fluid flow and solute transport model is used to simulate the phenomenon of seawater intrusion in coastal aquifers. A miscible fluid flow model of seawater intrusion consists of a variable density fluid flow equation, and an advective-dispersive solute transport equation to describe the salt transport. The flow and solute transport equations are coupled with a density coupling term which brings nonlinearity into the whole mathematical system. Because of the density coupling term, the simultaneous solution of the flow and transport equations are difficult. A nonlinear optimization based solution methodology is used to solve the finite difference discretized governing equations. The simulations carried out in this study demonstrate the viability of using a planned strategy of spatially varying withdrawals from the aquifer to manage seawater intrusion.
Often, when pollution is first detected in groundwater, very few spatiotemporal pollutant concent... more Often, when pollution is first detected in groundwater, very few spatiotemporal pollutant concentration measurements are available. The contaminant concentration measurement data initially available are generally sparse and insufficient for accurate source characterization. This requires development of a contaminant monitoring plan and its field implementation to collect more data. The location of scientifically chosen monitoring points and the number of measurements are important considerations in improving the source-characterization process, especially in a complex contamination scenario. In order to improve the efficiency of source characterization, a feedback-based methodology is implemented, integrating sequential-monitoring-network design and a source identification method. The simulated annealing (SA) optimization algorithm is used to solve the models for optimal source identification and the monitoring-network-design optimization. This sequence is repeated a few times to improve the accuracy of source characterization. The methodology is based on the premise that concentration measurements from a sequence of implemented monitoring networks provide feedback information on the actual concentration in the site. This additional information, obtained as feedback from monitoring networks designed and implemented based on intermediate source characterization, can result in sequential improvement in the resulting source characterization. The performance of this methodology is evaluated by application to a contaminated aquifer site in New South Wales, Australia, where source location, source-activity initiation time and source-flux (mass per unit time) release history are considered as unknown variables. The performance evaluation results demonstrate potential applicability of the proposed sequential methodology.RésuméSouvent, lorsque la pollution est d’abord détectée dans les eaux souterraines, très peu de mesures de concentrations réparties dans le temps et l’espace sont disponibles. Les données de mesure de concentration des contaminants initialement disponibles sont généralement éparses et insuffisantes pour une caractérisation précise de la source. Cela nécessite le développement d’un plan de surveillance des contaminants et de sa mise en œuvre sur le terrain pour recueillir davantage de données. L’emplacement des points de contrôle choisis scientifiquement et le nombre de mesures sont importants à prendre en considération pour améliorer le processus de caractérisation de la source, en particulier dans un scénario de contamination complexe. Afin d’améliorer l’efficacité de la caractérisation de la source, une méthodologie basée sur la rétroaction est mise en œuvre, intégrant la conception séquentielle d’un réseau de suivi et une méthode d’identification de la source. L’algorithme d’optimisation du recuit simulé (SA) est utilisé pour résoudre les modèles d’identification optimale de la source et l’optimisation de la conception du réseau de suivi. Cette séquence est répétée plusieurs fois afin d’améliorer la précision de la caractérisation de la source. La méthodologie est fondée sur la prémisse selon laquelle les mesures de concentration d’une séquence de réseaux de surveillance implantés fournissent des informations en retour sur la concentration réelle sur le site. Cette information additionnelle, obtenue comme retour d’information des réseaux de suivi conçus et mis en œuvre sur la base de la caractérisation intermédiaire de la source, peut avoir comme résultat une amélioration séquentielle dans la caractérisation de la source résultante. La performance de cette méthodologie est évaluée avec une application sur un aquifère contaminé en Nouvelles Galles du Sud, en Australie, où l’emplacement de la source, le temps d’initiation de l’activité de la source et l’historique d’émission du flux depuis la source (masse par unité de temps) sont considérés comme des variables inconnues. Les résultats de l’évaluation de la performance démontrent l’applicabilité potentielle de la méthodologie séquentielle proposée.ResumenCuando se detecta la primera contaminación del agua subterránea, a menudo están disponibles muy pocas mediciones espacio-temporales de la concentración de los contaminantes. Los datos de medición de concentración de contaminantes inicialmente disponibles son generalmente escasos e insuficientes para una caracterización precisa de la fuente. Esto requiere el desarrollo de un plan de monitoreo de contaminantes y su aplicación en el campo para recolectar más datos. La ubicación de los puntos de control científicamente seleccionados y el número de mediciones son consideraciones importantes para mejorar del proceso de la caracterización de la fuente, especialmente en un escenario complejo de contaminación. Con el fin de mejorar la eficiencia de la caracterización de la fuente, se implementa una metodología basada en la retroalimentación integrando el diseño de la red de monitoreo secuencial y un…
AbstractThis study demonstrates the influence of climate change-induced sea level rise on multiob... more AbstractThis study demonstrates the influence of climate change-induced sea level rise on multiobjective saltwater intrusion management strategies in coastal aquifers. Three metamodels were develop...
Meta-model based coupled simulation-optimization methodology is an effective tool in developing s... more Meta-model based coupled simulation-optimization methodology is an effective tool in developing sustainable saltwater intrusion management strategies for coastal aquifers. Such management strategies largely depend on the accuracy, reliability, and computational feasibility of meta-models and the numerical simulation model. However, groundwater models are associated with a certain amount of uncertainties, e.g. parameter uncertainty and uncertainty in prediction. This study addresses uncertainties related to input parameters of the groundwater flow and transport system by using a set of randomized input parameters. Three meta-models are compared to characterize responses of water quality in coastal aquifers due to groundwater extraction patterns under parameter uncertainty. The ensemble of the best meta-model is then coupled with a multi-objective optimization algorithm to develop a saltwater intrusion management model. Uncertainties in hydraulic conductivity, compressibility, bulk de...
The present study evaluates the application of the hybrid machine learning methods to detect chan... more The present study evaluates the application of the hybrid machine learning methods to detect changes of land use with a focus on agricultural lands through remote sensing data processing. Two spectral images by Landsat 8 were applied to train and test the machine learning model. Feed forward neural network classifier was utilized as the machine learning model in which two evolutionary algorithms including particle swarm optimization and invasive weed optimization were applied for the training process. Moreover, three conventional training methods including Levenberg–Marquardt back propagation (LM), Scaled conjugate gradient backpropagation (SCG) and BFGS quasi-Newton backpropagation (BFG) were used for comparing the robustness and reliability of the evolutionary algorithms. Based on the results in the case study, evolutionary algorithms are not a reliable method for detecting changes through the remote sensing analysis in terms of accuracy and computational complexities. Either BFG ...
The present study proposes a novel framework to optimize the reservoir operation through linking ... more The present study proposes a novel framework to optimize the reservoir operation through linking mesohabitat hydraulic modeling and metaheuristic optimization to mitigate environmental impact at downstream of the reservoir. Environmental impact function was developed by mesohabitat hydraulic simulation. Then, the developed function was utilized in the structure of the reservoir operation optimization. Different metaheuristic algorithms including practice swarm optimization, invasive weed optimization, differential evolution and biogeography-based algorithm were used to optimize reservoir operation. Root mean square error (RMSE) and reliability index were utilized to measure the performance of algorithms. Based on the results in the case study, the proposed method is robust for mitigating downstream environmental impacts and sustaining water supply by the reservoir. RMSE for mesohabitats is 8% that indicates the robustness of proposed method to mitigate environmental impacts at downs...
Reference evapotranspiration (ET0) is an important driver in managing scarce water resources and ... more Reference evapotranspiration (ET0) is an important driver in managing scarce water resources and making decisions on real-time and future irrigation scheduling. Therefore, accurate prediction of ET0 is crucial in water resources management. In this study, the prediction of ET0 was performed employing several optimization algorithms tuned Fuzzy Inference System (FIS) and Fuzzy Tree (FT) models, for the first time, whose generalization capability was tested using data from other stations. The FISs and FTs were developed through parameter tuning using Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Pattern Search (PS), and their combinations. The FT was developed by combining several fuzzy objects that received ranked meteorological variables. A total of 50 FIS and FT models were developed and the model ranking was performed utilizing Shannon’s Entropy (SE). Evaluation outcomes revealed the superiority of the hybrid PSO-GA tuned Sugeno type 1 FT model (with R = 0.929, NRMSE ...
Journal of Water Supply: Research and Technology-Aqua, 2022
Balancing the benefits and environmental degradations of the reservoirs is a challenging issue in... more Balancing the benefits and environmental degradations of the reservoirs is a challenging issue in the reservoir management. The present study proposes and evaluates an integrated framework to optimize reservoir operation in which hydropower loss and economic loss of irrigation supply are minimized while ecological degradations at downstream river are alleviated. The ecohydraulic simulation was utilized in the structure of the reservoir operation optimization. Reservoir operation losses and environmental degradations were minimized in three hydrological conditions including dry years, normal years and wet years. Moreover, the cropping pattern optimization was applied to mitigate the economic loss of irrigation supply as the main responsibility of the reservoir in the study area. Particle swarm optimization was applied in the reservoir operation optimization. Based on the results in the case study, reliability indices of hydropower production and farmers’ revenue are 15–25 and 30–60%,...
Journal of the Institution of Engineers India Civil Engineering Division, 2000
This paper presents the three-dimensional simulation of transient seawater intrusion resulting fr... more This paper presents the three-dimensional simulation of transient seawater intrusion resulting from some plausible stress scenarios. The density dependent miscible fluid flow and solute transport model is used to simulate the phenomenon of seawater intrusion in coastal aquifers. A miscible fluid flow model of seawater intrusion consists of a variable density fluid flow equation, and an advective-dispersive solute transport equation to describe the salt transport. The flow and solute transport equations are coupled with a density coupling term which brings nonlinearity into the whole mathematical system. Because of the density coupling term, the simultaneous solution of the flow and transport equations are difficult. A nonlinear optimization based solution methodology is used to solve the finite difference discretized governing equations. The simulations carried out in this study demonstrate the viability of using a planned strategy of spatially varying withdrawals from the aquifer to manage seawater intrusion.
Often, when pollution is first detected in groundwater, very few spatiotemporal pollutant concent... more Often, when pollution is first detected in groundwater, very few spatiotemporal pollutant concentration measurements are available. The contaminant concentration measurement data initially available are generally sparse and insufficient for accurate source characterization. This requires development of a contaminant monitoring plan and its field implementation to collect more data. The location of scientifically chosen monitoring points and the number of measurements are important considerations in improving the source-characterization process, especially in a complex contamination scenario. In order to improve the efficiency of source characterization, a feedback-based methodology is implemented, integrating sequential-monitoring-network design and a source identification method. The simulated annealing (SA) optimization algorithm is used to solve the models for optimal source identification and the monitoring-network-design optimization. This sequence is repeated a few times to improve the accuracy of source characterization. The methodology is based on the premise that concentration measurements from a sequence of implemented monitoring networks provide feedback information on the actual concentration in the site. This additional information, obtained as feedback from monitoring networks designed and implemented based on intermediate source characterization, can result in sequential improvement in the resulting source characterization. The performance of this methodology is evaluated by application to a contaminated aquifer site in New South Wales, Australia, where source location, source-activity initiation time and source-flux (mass per unit time) release history are considered as unknown variables. The performance evaluation results demonstrate potential applicability of the proposed sequential methodology.RésuméSouvent, lorsque la pollution est d’abord détectée dans les eaux souterraines, très peu de mesures de concentrations réparties dans le temps et l’espace sont disponibles. Les données de mesure de concentration des contaminants initialement disponibles sont généralement éparses et insuffisantes pour une caractérisation précise de la source. Cela nécessite le développement d’un plan de surveillance des contaminants et de sa mise en œuvre sur le terrain pour recueillir davantage de données. L’emplacement des points de contrôle choisis scientifiquement et le nombre de mesures sont importants à prendre en considération pour améliorer le processus de caractérisation de la source, en particulier dans un scénario de contamination complexe. Afin d’améliorer l’efficacité de la caractérisation de la source, une méthodologie basée sur la rétroaction est mise en œuvre, intégrant la conception séquentielle d’un réseau de suivi et une méthode d’identification de la source. L’algorithme d’optimisation du recuit simulé (SA) est utilisé pour résoudre les modèles d’identification optimale de la source et l’optimisation de la conception du réseau de suivi. Cette séquence est répétée plusieurs fois afin d’améliorer la précision de la caractérisation de la source. La méthodologie est fondée sur la prémisse selon laquelle les mesures de concentration d’une séquence de réseaux de surveillance implantés fournissent des informations en retour sur la concentration réelle sur le site. Cette information additionnelle, obtenue comme retour d’information des réseaux de suivi conçus et mis en œuvre sur la base de la caractérisation intermédiaire de la source, peut avoir comme résultat une amélioration séquentielle dans la caractérisation de la source résultante. La performance de cette méthodologie est évaluée avec une application sur un aquifère contaminé en Nouvelles Galles du Sud, en Australie, où l’emplacement de la source, le temps d’initiation de l’activité de la source et l’historique d’émission du flux depuis la source (masse par unité de temps) sont considérés comme des variables inconnues. Les résultats de l’évaluation de la performance démontrent l’applicabilité potentielle de la méthodologie séquentielle proposée.ResumenCuando se detecta la primera contaminación del agua subterránea, a menudo están disponibles muy pocas mediciones espacio-temporales de la concentración de los contaminantes. Los datos de medición de concentración de contaminantes inicialmente disponibles son generalmente escasos e insuficientes para una caracterización precisa de la fuente. Esto requiere el desarrollo de un plan de monitoreo de contaminantes y su aplicación en el campo para recolectar más datos. La ubicación de los puntos de control científicamente seleccionados y el número de mediciones son consideraciones importantes para mejorar del proceso de la caracterización de la fuente, especialmente en un escenario complejo de contaminación. Con el fin de mejorar la eficiencia de la caracterización de la fuente, se implementa una metodología basada en la retroalimentación integrando el diseño de la red de monitoreo secuencial y un…
Uploads
Papers