One important challenge for groundwater management is the identification of unknown abstraction wells in aquifers. This article proposes a simulation-optimization model for identifying the locations and pumping flow r...
详细信息
One important challenge for groundwater management is the identification of unknown abstraction wells in aquifers. This article proposes a simulation-optimization model for identifying the locations and pumping flow rates of unknown wells in an aquifer. The simulation utilizes the MODFLOW two-dimensional groundwater flow model, whereas the optimization model employs a learning automata algorithm. The locations and flow rates of the unknown wells are determined by minimizing the root mean squared error between simulated and observed groundwater heads at benchmarked points of the aquifer. Identifying the number, location, and pumping flow of unknown wells is achieved through a three-step process. In the first step, a significant number of wells are dispersed throughout the model with a hypothetical flow rate, and then the program is executed to determine their pumping flow rates. Wells with negligible resulting flow rates are then removed. In the second step, the removal of any well that contributes to a decrease in error is accepted. In the third step, each well is relocated to the points within its neighborhood. If this movement results in a lower error, the well is shifted to that point;otherwise, the well remains in its original location. Two hypothetical aquifer examples are used to assess the accuracy of the simulation-optimization model under steady-state and transient conditions. The results demonstrate that the model can accurately identify the locations and discharges of unknown wells with practical run times.
In many applications in order to recognise the relationship between user and computer, the position at which the user looks should be detected. To this end, a salient object should be extracted that is attracted to th...
详细信息
In many applications in order to recognise the relationship between user and computer, the position at which the user looks should be detected. To this end, a salient object should be extracted that is attracted to the attention of the viewer. In this study, a new method is proposed to extract the object saliency map, which is based on learningautomata and sparse algorithms. In the proposed method, after decomposition of an image to its superpixels, eight features (namely three features in red-green-blue colour space, coalition, central bias, rotation feature, brightness, and colour difference) are extracted. Then the extracted features are normalised to zero mean and unit variance. In this study, K-means singular-value decomposition is used to integrate the extracted features. The performance of the proposed method is compared with that of 20 other methods by applying four new databases, including MSRA-100, ECSSD, MSRA-10K, and Pascal-S. The obtained results show that the proposed method has a better performance compared to the other methods with regard to the prediction of the salient object.
暂无评论