تخمین پارامترهای کیفی آبخوان دشت گیلان با استفاده از آزمون گاما و مدل-های ماشین بردار پشتیبان و شبکه عصبی مصنوعی
محورهای موضوعی : آلودگی های محیط زیست (آب، خاک و هوا)محمد عیسی زاده 1 , سید مصطفی بی آزار 2 , افشین اشرف زاده 3 , رضوان خانجانی 4
1 - دکتری رشته مهندسی منابع آب دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران.
2 - دکتری رشته علوم و مهندسی آب -منابع آب، دانشکده کشاورزی دانشگاه تبریز، تبریز، ایران. *(مسوول مکاتبات)
3 - استادیار گروه مهندسی منابع آب دانشکده کشاورزی، دانشگاه گیلان، گیلان، ایران.
4 - کارشناسی ارشد، مدیریت دولتی دانشگاه پیام نور گیلان، گیلان، ایران.
کلید واژه: آزمون گاما, تخمین پارامترهای کیفی, دشت گیلان, شبکه عصبی مصنوعی, ماشین بردار پشتیبان,
چکیده مقاله :
زمینه و هدف: اطلاع از نحوه توزیع پارامترهای کیفی و کمی از مهم ترین پارامترهای اولیه مدیریت جامع منابع آب زیرزمینی می باشد. بنابراین در این تحقیق سعی گردید، مدل و ترکیب ورودی مناسب جهت تخمین پارامترهای کیفی هدایت الکتریکی (EC)، یون کلسیم (Ca) و یون سدیم (Na) آب خوان های دشت گیلان تعیین گردد. روش بررسی: در این تحقیق از داده های 132 چاهک مشاهداتی در دوره آماری 1381 تا 1393 و مدل های شبکه عصبی مصنوعی (ANN) و ماشین بردار پشتیبان (SVM) استفاده گردیده است. در رویکرد اول، تخمین ها به ازای پنج ترکیب مختلف حاصل از پارامترهای تراز آب، فاصله از دریا، مجموع بارش های شش ماه و مختصات چاهک های مشاهداتی انجام گرفته است. در رویکرد دوم، تخمین ها براساس ترکیب پارامترهای کیفی منتخب آزمون گاما با ترکیب های ورودی برتر بخش اول صورت گرفته است. یافتهها: مقایسه نتایج بخش اول نشان داد که مدل SVM در تخمین هر یک از پارامترهای Ca، Na و EC عملکرد بهتری نسبت به مدل ANN داشته است. مقادیر خطای ماشین بردار پشتیبان برای تخمین متغیرهای Ca، Na و EC در دوره تست به ترتیب برابر با (meq/l) 218/1، (meq/l) 867/0 و (µmos/cm) 742/175 بوده است و این مقادیر برای مدل شبکه عصبی مصنوعی به ترتیب برابر با (meq/l) 268/1، (meq/l) 933/0 و (µmos/cm) 448/186 می باشد. نتایج این بخش نشان داد اضافه شدن ورودی فاصله از دریا در کلیه موارد باعث بهبود نتایج مدل ها گردیده است. در بخش دوم با استفاده از آزمون گاما از بین نه پارامتر کیفی اندازه گیری شده ، بهترین ترکیب پارامترهای کیفی برای تخمین هر یک سه پارامتر Ca، Na و EC تعیین گردید. نتایج تخمین ها در بخش دوم نشان داد که هر یک از دو مدل ANN و SVM عملکرد بسیار مناسبی در تخمین هر سه پارامتر کیفی داشته اند. مقدار خطای مدل ANN برای متغیرهای Ca، Na و EC در دوره صحت سنجی به ترتیب برابر با (meq/l) 662/0، (meq/l) 305/0 و (µmos/cm) 346/47 بوده است و این مقادیر برای مدل SVM به ترتیب برابر با (meq/l) 671/0، (meq/l) 356/0 و (µmos/cm) 412/55 می باشد. البته در این بخش نتایج مدل ANN نسبت به مدل SVM بهتر بوده است. بحث و نتیجهگیری: نتایج نشان داد که هر یک از دو مدل SVM و ANN توانایی بسیار زیادی در تخمین پارامترهای کیفی آب خوان ها دارند. همچنین عملکرد مدل SVM نسبت به مدل ANN، به ازای تعداد ورودی کمتر بهتر است و در تعداد ورودی بیشتر برعکس می باشد. نتایج بخش دوم نشان داد که آزمون گاما می تواند به صورت کاملا کابردی و دقیق در تعیین ترکیب های ورودی موثر مورد استفاده قرار گیرد.
Abstract Background and Objective: Having information about qualitative and quantitative parameters distribution of groundwater supplies is one of most important parameters in integrated groundwater management. Thus, in this study it has been attempted to determine a proper model and input combination for estimation of quality parameters including electrical conductivity (EC), calcium (Ca) and sodium (Na) ions in aquifers of Guilans plain. Method: In this study, the data from 132 observation wells during 2001 to 2013 were used and artificial neural network (ANN) and support vector model (SVM) were applied. In the first approach, estimations were conducted according to five different combinations, including water level, distance from see, total precipitation of six months and coordinates of observation wells. In the second approach, estimations were conducted based on combination of the selected qualitative parameters of gamma test with combinations of the best input in the first part. Findings: Comparison of the results from the first part indicated that SVM model outperformed the ANN mode in the estimation of Ca, Na and EC parameters. Support vector machine error values for estimating Ca, Na and EC variables at the test period were 1.218 (meq/l), 0.867(meq/l), and 175.742 (µmos/cm), while for artificial neural network these values were 1.268 (meq/l), 0.933 (meq/l), and 186/448 (µmos/cm) respectively. The results from this part showed that adding the distance from see input improves the estimation of models in all cases. In the second part, using gamma test for measuring the nine quality parameters, the best combination of quality parameters was determined to estimate the three parameters: Ca, Na and EC. The results from the second part show that both ANN and SVM models have an excellent performance in the estimation of the three qualitative parameters. ANN model error values in estimating Ca, Na and EC variables in validation period were 0.662 (meq/l), 0.305(meq/l), and 47.346 (µmos/cm), while these values were 0.671 (meq/l), 0.356 (meq/l), and 55.412 (µmos/cm) for SVM model respectively. Obviously, the results from ANN model in this section were better than those from SVM model. Discussion and Conclusion:Results showed that both ANN and SVM models have a great ability in predicting qualitative parameters in the aquifers. Also, in less inputs, the results of SVM model are better than those of ANN model and in more inputs it is vice versa. Results of the second section showed that gamma test is fully practical and accurate in determining the effective input combinations.
1- Parmer, K.S., Bhardwaj, R., 2013.Wavelet and statistical analysis of river water quality parameters, Journal of Applied Mthematics and Computation. Vol. 219, PP.10172-10182.
2- Diamantopoulou, M.J., Antonopoulos, V.Z., Papamichail, D.M., 2005. The use of a neural network technique for the prediction of water quality parameters of Axios River in Northern Greece. Journal of Eur Water, Vol. 11, PP. 55–62.
3- Mcknight, U.S., Funder, S., Rasmussen, J.J., Finkel, M., Binning, P.J., Bjerg, P.L., 2010. An integrated model for assessing the risk of TCE groundwater contamination to human receptors and surface water ecosystems. Journal of Ecological Engineering, Vol. 36, PP 1126-1137.
4- Gholami, V., Jafari, M., 2001. Investigating Effective Factors in Groundwater Salinity to Provide Regional Modeling in Mazandaran Shores, Civil Engineering and Environmental Engineering Journal of Tabriz University, Vol. 23, pp 81-87,[In persian]
5- Mehrdadi, N., Nabi Bid HindI, G., Baghand, A., Zare Abyaneh, H., Abbasi Maedeh, p., 2012. Projection of changes in the electrical conductivity parameter in underground water in Tehran using artificial neural network , Civil engineering and environmental engineering Journal of Tabriz University, Vol 10, pp13-25 [In Pearsian].
6- Mirzavand, M, Ghasemiye, H, Akbari. M., Sadatinejad, S., 2015. Simulaytion of Underground Water Quality Changes with Artificial Neural Network Model (Case Study: Kashan Aquifer), Civil Engineering Journal and Environment Engineering Journal of Tabriz University, Vol. 68, pp159-171, [In Persian].
7- Nadiri, A., Vahedi, F., Asghari Moghadam, A., Kadkhodaee, A., 2015, Use of Artificial Intellighence Model Supervised to predicte groundwater level, Civil Engineering and Environmental Engineering Journal of Tabriz University. Vol. 46, pp101-112 [In Persian].
8- Dehgani, R., Pourhaghi, A., Kheyraei, M., 1395. Compersian of Adaptive Neuro-Fuzzy Inference System Techniques, Artificial Neural Network and Gene Experssion Planning in estimating Groundwater Hardness (Case Study: Mazandaran Plain). New finding in applied geology. 10(19), 51-62, [In Persian].
9- Cho, K.H., Sthiannopkao, S., Pachepsky, Y.A., Kim, K.W., Kim, J.H., 2011. Prediction of contamination potential of groundwater arsenic in Cambodia, Laos and Thailand using artificial neural network. Journal of Water Research, Vol. 45, PP. 5535-5544.
10- Alagha, J.S., Said, M.A.M., Mogheir, Y., 2014. Modeling of nitrate concentration in groundwater using artificial intelligence approach- acase study of Gaza coastal aquifer. Vol.186, PP.35-45.
11- Kheradpisheh, Z., Talebi, A., Rafati L., Ghaneian, M.T., Ehrampoush, M.H., 2015. Groundwater quality assessment using artificial neural network: A case study of Bahabad plain. Yazd, Iran. Journal of Desert, Vol. 20, PP. 65-71.
12- Khaki, M., Yusoff, I., Islami N., 2015. Application of the Artificial Neural Network and Neuro-fuzzy System for Assessment of Groundwater Quality. Journal of Clean Soil Air Water, Vol. 43, PP. 551-560.
13- Gong, Y., Zhang, Y., Lan, S., Wang, H., 2016. A Comparative Study of Artificial Neural Networks, Support Vector Machines and Adaptive Neuro Fuzzy Inference System for Forecasting Groundwater Levels near Lake Okeechobee, Florida. Water Resources Management, Vol. 30, PP. 375-391.
14- Ehteshami, M., Dolatabadi Farahani, N., Tavassoli S., 2016. Simulation of nitrate contamination in groundwater using artificial neural networks. Modeling Earth Systems and Environment, Vol. 28, PP. 2-10.
15- Arabgol, R., Sartaj, M., Asghari, A., 2016. Prediction Nitrate Concentration and Its Spatial Distribution in Groundwater Resources Using Support Vector Machines (SVMS) Model. Journal of Environmental Modeling & Assessment, Vol. 21, PP. 71-82.
16- 16-Dawson, C.W., Abrahart, R.J., Shamseldin, A.Y. and Wibly, R.L., 2006. Flood estimation at ungauged sites using artificial neural networks. Journal of Hydrology, Vol. 319, PP. 391-409.
17- Coulibaly, P., Anctil, F., Bobée, B., 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology, Vol. 230, PP. 244-257.
18- ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. 2000. Artificial neural networks in hydrology. I preliminary concepts. Journal of Hydrologic Engineering, Vol.5, PP.115-123.
19- Dibike, Y., Velickov, S., Solomatine, D., Abbott, M., 2001. Model induction with of support vector machines: Introduction and applications. Journal of Computing in Civil Engineering, Vol. 15, PP. 208- 216.
20- Yoon, H., Jun, S.C., Hyun Y., Bae, G.O., Lee, K.K., 2011. A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. Journal of Hydrology, Vol. 396, PP. 128-138.
21- Isazadeh, M., Biazar, S. M., Ashrafzadeh, A., 2017. Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters. Environmental Earth Sciences, 76(17), 610.
22- Kavzoglu, T., Colkesen, I., 2009. A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, Vol. 11, PP. 352-359.
23- Ashrafzadeh, A., Malik, A., Jothiprakash, V., Ghorbani, M. A., Biazar, S. M., 2018. Estimation of daily pan evaporation using neural networks and meta-heuristic approaches. ISH Journal of Hydraulic Engineering, 1-9.
24- Durrant, P.J., 2001. Win_Gamma TM A non-linear data analysis and modeling tool with applications to flood prediction. PhD Thesis, Department of Computer Science, Cardiff University Wales, UK.
25- Evans, D., Jone, A., 2002 A proof of the gamma test. Proceedings of Royal Society, Series A, Vol. 458, PP. 2759-2799.
26- Misra, D., Oommen, T., Agarwal, A., and Mishra, S.K., 2009. Application and analysis of Support Vector machine based simulation for runoff and sediment yield. Journal of Biosystems Engineering, Vol.103, PP. 527-535.
_||_
1- Parmer, K.S., Bhardwaj, R., 2013.Wavelet and statistical analysis of river water quality parameters, Journal of Applied Mthematics and Computation. Vol. 219, PP.10172-10182.
2- Diamantopoulou, M.J., Antonopoulos, V.Z., Papamichail, D.M., 2005. The use of a neural network technique for the prediction of water quality parameters of Axios River in Northern Greece. Journal of Eur Water, Vol. 11, PP. 55–62.
3- Mcknight, U.S., Funder, S., Rasmussen, J.J., Finkel, M., Binning, P.J., Bjerg, P.L., 2010. An integrated model for assessing the risk of TCE groundwater contamination to human receptors and surface water ecosystems. Journal of Ecological Engineering, Vol. 36, PP 1126-1137.
4- Gholami, V., Jafari, M., 2001. Investigating Effective Factors in Groundwater Salinity to Provide Regional Modeling in Mazandaran Shores, Civil Engineering and Environmental Engineering Journal of Tabriz University, Vol. 23, pp 81-87,[In persian]
5- Mehrdadi, N., Nabi Bid HindI, G., Baghand, A., Zare Abyaneh, H., Abbasi Maedeh, p., 2012. Projection of changes in the electrical conductivity parameter in underground water in Tehran using artificial neural network , Civil engineering and environmental engineering Journal of Tabriz University, Vol 10, pp13-25 [In Pearsian].
6- Mirzavand, M, Ghasemiye, H, Akbari. M., Sadatinejad, S., 2015. Simulaytion of Underground Water Quality Changes with Artificial Neural Network Model (Case Study: Kashan Aquifer), Civil Engineering Journal and Environment Engineering Journal of Tabriz University, Vol. 68, pp159-171, [In Persian].
7- Nadiri, A., Vahedi, F., Asghari Moghadam, A., Kadkhodaee, A., 2015, Use of Artificial Intellighence Model Supervised to predicte groundwater level, Civil Engineering and Environmental Engineering Journal of Tabriz University. Vol. 46, pp101-112 [In Persian].
8- Dehgani, R., Pourhaghi, A., Kheyraei, M., 1395. Compersian of Adaptive Neuro-Fuzzy Inference System Techniques, Artificial Neural Network and Gene Experssion Planning in estimating Groundwater Hardness (Case Study: Mazandaran Plain). New finding in applied geology. 10(19), 51-62, [In Persian].
9- Cho, K.H., Sthiannopkao, S., Pachepsky, Y.A., Kim, K.W., Kim, J.H., 2011. Prediction of contamination potential of groundwater arsenic in Cambodia, Laos and Thailand using artificial neural network. Journal of Water Research, Vol. 45, PP. 5535-5544.
10- Alagha, J.S., Said, M.A.M., Mogheir, Y., 2014. Modeling of nitrate concentration in groundwater using artificial intelligence approach- acase study of Gaza coastal aquifer. Vol.186, PP.35-45.
11- Kheradpisheh, Z., Talebi, A., Rafati L., Ghaneian, M.T., Ehrampoush, M.H., 2015. Groundwater quality assessment using artificial neural network: A case study of Bahabad plain. Yazd, Iran. Journal of Desert, Vol. 20, PP. 65-71.
12- Khaki, M., Yusoff, I., Islami N., 2015. Application of the Artificial Neural Network and Neuro-fuzzy System for Assessment of Groundwater Quality. Journal of Clean Soil Air Water, Vol. 43, PP. 551-560.
13- Gong, Y., Zhang, Y., Lan, S., Wang, H., 2016. A Comparative Study of Artificial Neural Networks, Support Vector Machines and Adaptive Neuro Fuzzy Inference System for Forecasting Groundwater Levels near Lake Okeechobee, Florida. Water Resources Management, Vol. 30, PP. 375-391.
14- Ehteshami, M., Dolatabadi Farahani, N., Tavassoli S., 2016. Simulation of nitrate contamination in groundwater using artificial neural networks. Modeling Earth Systems and Environment, Vol. 28, PP. 2-10.
15- Arabgol, R., Sartaj, M., Asghari, A., 2016. Prediction Nitrate Concentration and Its Spatial Distribution in Groundwater Resources Using Support Vector Machines (SVMS) Model. Journal of Environmental Modeling & Assessment, Vol. 21, PP. 71-82.
16- 16-Dawson, C.W., Abrahart, R.J., Shamseldin, A.Y. and Wibly, R.L., 2006. Flood estimation at ungauged sites using artificial neural networks. Journal of Hydrology, Vol. 319, PP. 391-409.
17- Coulibaly, P., Anctil, F., Bobée, B., 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology, Vol. 230, PP. 244-257.
18- ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. 2000. Artificial neural networks in hydrology. I preliminary concepts. Journal of Hydrologic Engineering, Vol.5, PP.115-123.
19- Dibike, Y., Velickov, S., Solomatine, D., Abbott, M., 2001. Model induction with of support vector machines: Introduction and applications. Journal of Computing in Civil Engineering, Vol. 15, PP. 208- 216.
20- Yoon, H., Jun, S.C., Hyun Y., Bae, G.O., Lee, K.K., 2011. A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. Journal of Hydrology, Vol. 396, PP. 128-138.
21- Isazadeh, M., Biazar, S. M., Ashrafzadeh, A., 2017. Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters. Environmental Earth Sciences, 76(17), 610.
22- Kavzoglu, T., Colkesen, I., 2009. A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, Vol. 11, PP. 352-359.
23- Ashrafzadeh, A., Malik, A., Jothiprakash, V., Ghorbani, M. A., Biazar, S. M., 2018. Estimation of daily pan evaporation using neural networks and meta-heuristic approaches. ISH Journal of Hydraulic Engineering, 1-9.
24- Durrant, P.J., 2001. Win_Gamma TM A non-linear data analysis and modeling tool with applications to flood prediction. PhD Thesis, Department of Computer Science, Cardiff University Wales, UK.
25- Evans, D., Jone, A., 2002 A proof of the gamma test. Proceedings of Royal Society, Series A, Vol. 458, PP. 2759-2799.
26- Misra, D., Oommen, T., Agarwal, A., and Mishra, S.K., 2009. Application and analysis of Support Vector machine based simulation for runoff and sediment yield. Journal of Biosystems Engineering, Vol.103, PP. 527-535.