@article {
author = {n, m and a, v and a, e},
title = {Optimization of groundwater monitoring network using Ant Colony Optimization (ACO) algorithm},
journal = {Iranian Water Researches Journal},
volume = {9},
number = {4},
pages = {171-174},
year = {2015},
publisher = {دانشگاه شهرکرد},
issn = {2008-1235},
eissn = {2345-6655},
doi = {},
abstract = {In this paper, using the one of the most robust optimization technique, Ant Colony Optimization Algorithm (ACO) the minimum number of required sampling points was determined in Hashtgerd plain. The ACO technique is based on the minimum distance between the food source and the ant nest. In Hashtgerd plain using ACO about ۳۰% of sampling point were reduced. In this aquifer, the number of sampling points for contamination research where in ۲۵ location and after the application of ACO technique results showed that only ۱۸ sampling points is enough and the ۷ number of sampling points is not necessary and introduced more expenses for the contamination study. In addition, the results of nitrate contamination contour plot before and after reducing the sampling points from ۲۵ to ۱۸ shows a small change in contour maps. The maximum RMSE after reduction ۷ sampling points is about ۰.۳۱۹۸ that shows the minimum error for optimized network. In this paper, using the one of the most robust optimization technique, Ant Colony Optimization Algorithm (ACO) the minimum number of required sampling points was determined in Hashtgerd plain. The ACO technique is based on the minimum distance between the food source and the ant nest. In Hashtgerd plain using ACO about ۳۰% of sampling point were reduced. In this aquifer, the number of sampling points for contamination research where in ۲۵ location and after the application of ACO technique results showed that only ۱۸ sampling points is enough and the ۷ number of sampling points is not necessary and introduced more expenses for the contamination study. In addition, the results of nitrate contamination contour plot before and after reducing the sampling points from ۲۵ to ۱۸ shows a small change in contour maps. The maximum RMSE after reduction ۷ sampling points is about ۰.۳۱۹۸ that shows the minimum error for optimized network. In this paper, using the one of the most robust optimization technique, Ant Colony Optimization Algorithm (ACO) the minimum number of required sampling points was determined in Hashtgerd plain. The ACO technique is based on the minimum distance between the food source and the ant nest. In Hashtgerd plain using ACO about ۳۰% of sampling point were reduced. In this aquifer, the number of sampling points for contamination research where in ۲۵ location and after the application of ACO technique results showed that only ۱۸ sampling points is enough and the ۷ number of sampling points is not necessary and introduced more expenses for the contamination study. In addition, the results of nitrate contamination contour plot before and after reducing the sampling points from ۲۵ to ۱۸ shows a small change in contour maps. The maximum RMSE after reduction ۷ sampling points is about ۰.۳۱۹۸ that shows the minimum error for optimized network. In this paper, using the one of the most robust optimization technique, Ant Colony Optimization Algorithm (ACO) the minimum number of required sampling points was determined in Hashtgerd plain. The ACO technique is based on the minimum distance between the food source and the ant nest. In Hashtgerd plain using ACO about ۳۰% of sampling point were reduced. In this aquifer, the number of sampling points for contamination research where in ۲۵ location and after the application of ACO technique results showed that only ۱۸ sampling points is enough and the ۷ number of sampling points is not necessary and introduced more expenses for the contamination study. In addition, the results of nitrate contamination contour plot before and after reducing the sampling points from ۲۵ to ۱۸ shows a small change in contour maps. The maximum RMSE after reduction ۷ sampling points is about ۰.۳۱۹۸ that shows the minimum error for optimized network. In this paper, using the one of the most robust optimization technique, Ant Colony Optimization Algorithm (ACO) the minimum number of required sampling points was determined in Hashtgerd plain. The ACO technique is based on the minimum distance between the food source and the ant nest. In Hashtgerd plain using ACO about ۳۰% of sampling point were reduced. In this aquifer, the number of sampling points for contamination research where in ۲۵ location and after the application of ACO technique results showed that only ۱۸ sampling points is enough and the ۷ number of sampling points is not necessary and introduced more expenses for the contamination study. In addition, the results of nitrate contamination contour plot before and after reducing the sampling points from ۲۵ to ۱۸ shows a small change in contour maps. The maximum RMSE after reduction ۷ sampling points is about ۰.۳۱۹۸ that shows the minimum error for optimized network.},
keywords = {Optimization,Groundwater Monitoring Network,R,Ant Colony},
title_fa = {بهینهسازی شبکه پایش آب زیرزمینی با استفاده از الگوریتم کلنی مورچگان},
abstract_fa = {در این مطالعه برای بهینهسازی و کمینهکردن نقاط نمونهبرداری در سفره آب زیرزمینی دشت هشتگرد از الگوریتم بهینهسازی کلنی مورچگان استفاده شده است. روش کلنی مورچگان بر مبنای کوتاهترین فاصله بین لانه و منابع غذا ابداع شده است. در دشت هشتگرد با استفاده از الگوریتم بهینهسازی کلنی مورچگان حدود 30% از تعداد نقاط اضافی نمونهبرداری مشخص و حذف شد. در این دشت تعداد نقاط نمونهبرداری آب برای مطالعات آلودگی 25 عدد میباشد که در نهایت بر اساس نتایج این پژوهش تعداد 7 نقطه نمونهبرداری مازاد بوده که هزینه اضافی ایجاد میکند. نتایج به دست آمده از نقشههای ترسیم شده مقدار نیترات با تعداد 25 نمونه و نقشههای ترسیم شده بعد از حذف 7 نقطه دارای تغییرات بسیار ناچیز بوده و مقدار بیشینه RMSE برای حذف 7 چاه 0.3198 به دست آمده است که نشاندهنده حداقل خطا در سیستم است.},
keywords_fa = {خطای انحراف از معیار,بازبینی آب زیرزمینی,بهینهیابی,کلنی مورچگان},
url = {http://iwrj.sku.ac.ir/article_11108.html},
eprint = {http://iwrj.sku.ac.ir/article_11108_8bd051f324e121ff1ff0e41eca5613b7.pdf}
}