جستجوی مقالات مرتبط با کلیدواژه « nsga-ii » در نشریات گروه « آب و خاک »

The use of coupled simulation-optimization models to extract the optimal role curve of dams is one of the effective strategies for optimal management of reservoirs. In certain optimization techniques, historical data of the inflow to the reservoir is usually used to extract the optimal role curve of the dam. It is possible that in the coming years, with the change of the inflow to dams, the parameters based on which the optimal role curve was extracted may no longer work and the results may be unexpected. The objective of this research is to provide a solution for extracting the optimal role curve in real time so that by changing the inflow to the dam in the future without re-executing the optimization algorithm and using artificial intelligence techniques in the shortest time, the optimal role curve compatible with the new conditions can be obtained. In this research, the integration of the NSGA-II multi-objective algorithm and the WEAP simulation model is used to derive optimal policies based on historical data. Then, using the support vector machine method and the results obtained from the output of the optimization algorithm, a new structure is developed so that the optimal role curve can be obtained in real time and based on new inputs. The results indicate that the average error of the optimal role curve extracted from support vector machines is less than 2.5% compared to the role curve obtained from the NSGA-II algorithm in the calibration and validation stages. Therefore, the developed support vector machine model has the ability to quickly provide optimal operation policies in such a way that provides the possibility of optimal management of the system in real time, according to the new data of the inflow to the dam.

The occurrence of hydraulic problems during the repair of reservoirs in water distribution networks (WDN) is inevitable. In such cases, one of the reliable methods for water supply is emergency connection between pressure zones. However, the original design based on separated zone, loses its effectiveness and in some places, the WDN will face to increase and decrease in allowable pressure and even flow interruption. Therefore, in this study, the network analysis and determination of optimal 24-hour rule curve of pressure reduce valve (PRV) during an emergency connection between pressure zones, has been taken to reduce hydraulic difficulties. First, a computer model based on VB programming language was developed in which the network is analyzed by using slope matrix method. By linking mentioned model with the code that prepared for optimization by NSGA-II, the optimal rule curve of PRV in Ezgele WDN was determined. The results showed that in the case which lower zone reservoir become out of service and connecting node 12 of the higher zone with node 41 of the lower zone, it is necessary to install a pressure reduce valve on the outlet pipe of the higher reservoir. The optimal rule curve which was calculated during the day showed that the operating range of the pressure reduce valve is between 8 and 25 meters. The results also showed that when the higher zone reservoir is out of service during the maximum consumption, despite the connection between two zones, nodes 13 and 37 faces to absolute flow interruption and about 28% of the network suffers from pressure deficiencies in comparison to minimum allowable pressure.

Quantitative and qualitative management of urban runoff in part of Karaj city has been investigated using optimization of Low Impact Development (LID) methods under base period and climate change conditions. CanESM2 was employed with the base period (1985-2005) and future period (2020-2040) under the RCP2.6 and RCP8.5 scenarios to investigate climate change impacts. Hydraulic and hydrological modeling was performed by Storm Water Management Model (SWMM) and was combined with Multi-objective Particle Swarm Optimization Algorithm (MOPSO) and Non-dominated Sorting Genetic Algorithm (NSGA-II). Thirty-seven sub-catchments and five types of LIDS are introduced to the algorithms. Eight scenarios were defined to compare and evaluate the algorithms. Under the base period conditions, by applying NSGA-II and MOPSO algorithms, the flood volume in the catchment will decrease by 21.2% and 20.3%, total suspended solids (TSS) will increase by 59.1% and 58.4%, total nitrogen (TN) will increase by 16.6% and 12.7%, and lead (Pb) concentration will increase by 29.7% and 28.7%, respectively. Solution of the algorithms under climate change conditions gave similar flood values as the base conditions. In RCP2.6 scenario, TSS will decrease by 59.5% and 55.2%, respectively, and in RCP8.5 scenario, TSS will decrease by 59.6% and 55.8%, respectively. In RCP2.6 scenario, TN will decrease by 17.4% and 13.4%, respectively, and in RCP8.5 scenario, TN will decrease by 17.6% and 13.5%, respectively. Pb in RCP2.6 scenario will decrease by 30.1% and 29.7%, respectively, and in RCP8.5 scenario, Pb will decrease by 30.9% and 30.4%, respectively.

Increasing the water productivity by cropping pattern optimization is one of the best ways for development in agriculture. In this study, in order to maximize farmers' income and minimize blue water footprint of wheat, barley, alfalfa, and maize, the NSGA-II multi-objective optimization algorithm and United Nations commission on sustainable development’s indicator has been used in four cropping pattern scenarios in the 56 cities of the eastern provinces of Iran. The results showed that in some scenarios it was not possible to fully achieve these goals in the multi-objective model. The results also showed that the production of 50, 75 and 100% of the current values causes a low, moderate and severe water stress in the study region, that on average, save 55, 40 and 30 % of the region's water resources, respectively. Implementation of this model in the study area would increase revenue, reduce water consumption and, consequently make more environmental sustainability.

Irregular withdrawals from water resources followed by the increase of the area of under cultivation lands and the construction of Marun and Jarahi Dams on upstream rivers of the Shadegan Wetland have led to severe hydrological changes as well as increased salinity of the wetland inflow in some periods. The aim of this study is to develop a simulator-optimizer coupling model for proper planning and management of resource allocation to the upstream of Shadegan Wetland. In addition to maximizing the supply of basin demands during the operation period, this model tries to decrease the salinity of inflow to Shadegan Wetland. Due to the importance of the wetland as a seasonal habitat for birds and also one of the important tourist attractions and Importance of Protecting the Ecosystem, the development of a quantitative-qualitative optimization model for optimal use of available water resources is the aim of this study. First, based on current conditions, the prepared model is developed as a reference scenario for a future 30-year period (2021 to 2050). To achieve the best system efficiency in terms of quality and quantity, the optimization is performed by means of the NSGA-II algorithm. The results indicate that the optimizer model performs appropriately in supplying various demands and also decreasing the salinity of the inflow to Shadegan Wetland compared to the reference scenario so that in addition to supplying the demands with more than 92% reliability in the whole system, it is expected that the salinity of the river at the entrance to Shadegan Wetland to be reduced by about 50%., especially in low water months. The coupling model proposed in this research is applicable for other study areas with quantitative-qualitative exploitation approach and is able to detect critical points of rivers in terms of quantity and quality. This model has also the capability of providing optimal solutions for improving river conditions as well as downstream ecosystems.

The main objective of this research is to optimize the type and location of Best Management Practices (BMPs) to reduce the amount of nutrients entering the lake Zrebar in order to improve lake conditions. In this regard, Simulation-Optimization approach derived from the integration of the SWAT model and a spatial optimization model of BMPs based on multi-objective genetic algorithm (NSGA-II) was used. In this approach, the optimal model of management practices was determined with respect to three maximizing the net profit of the agricultural sector, minimizing the nitrogen loads and minimizing the phosphor loads. In this research, a wide range of BMPs was investigated and the optimal spatial pattern of the management practices such as fertilizer, irrigation and tillage managements were determined. Results showed that by applying the selected management practices with the optimal spatial pattern, the total amount of phosphorus and nitrogen in the basin outlet decreased by 2.8% and 22.1% respectively and consequently the concentration of nitrate in the lake will be greatly reduced. Also the net income of the agricultural sector decreased by 16.4%. The results indicated that applying the selected management practices with the optimal spatial pattern can help to improve the environmental condition of the lake.

Conceptual rainfall-runoff (RR) models, aiming at predicting stream flow from the knowledge of precipitation over a catchment, evapotranspiration, tempreture, and topography of the basin, have become basic and effective tools for flow regime simulation. Calibration of RR models, e.g. WetSpa which has been developed in Belgium, is a process in which parameter adjustment are made so as to match the dynamic behaviour of the RR model to the observed behaviour of the catchment. This research presents an application of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Particle Swarm Optimization (PSO) for multi-objective calibration of WetSpa in Karoon river basin, Iran to optimize 11 global parameters of the WetSpa model. The objective functions are Nash–Sutcliffe and logarithmic Nash–Sutcliffe efficiencies in order to improve the model's performance. Results showed that the evolutionary NSGA-II and PSO algorithms are capable of locating optimal parameter sets in the search space. The measured correlation coefficient in the calibration process was 0.69 and 0.71 for the NSGA-II and PSO algorithms, respectively. Moreover RMSE values were calculated as 119.8 and 152.3 m3/s for the algorithms. The WetSpa model then was applied for a period of 1-year flood simulation in the basin and the results were analysed. Finally a sensitivity analysis was conducted on the global parameters in which the surface runoff coefficient was the most sensitive parameter with more than 40% influence on the results.