ارزیابی عدم قطعیت مدلهای ANN و ANFIS در تخمین جریان ورودی به سد رئیسعلی دلواری
محورهای موضوعی :
مدیریت منابع آب
علی اسکندری
1
,
روح اله نوری
2
,
محمدرضا وصالی ناصح
3
,
فریماه سعیدی
4
1 - مربی مهندسی عمران، گروه مهندسی عمران، واحد بوشهر، دانشگاه آزاد اسلامی، بوشهر، ایران(مسئول مکاتبات)
2 - استادیار مهندسی محیطزیست، دانشکده تحصیلات تکمیلی محیطزیست، پردیس فنی، دانشگاه تهران، تهران، ایران
3 - استادیار مهندسی محیطزیست، گروه مهندسی عمران، دانشگاه اراک، اراک، ایران
4 - کارشناس مهندسی محیطزیست، دانشکده تحصیلات تکمیلی محیطزیست، پردیس فنی، دانشگاه تهران، تهران، ایران
تاریخ دریافت : 1395/01/20
تاریخ پذیرش : 1395/08/10
تاریخ انتشار : 1398/07/01
کلید واژه:
رودخانه شاپور,
تخمین جریان,
تحلیل عدم قطعیت,
سد رئیسعلی دلواری,
چکیده مقاله :
زمینه و هدف: اطلاع دقیق از کمیت آب جاری در رودخانهها تاثیر فراوان بر مدیریت کمی و کیفی منابع آب در جوامع وابسته با آن دارد. در این راستا هدف تحقیق حاضر ارزیابی عدم قطعیت در فرآیند تخمین جریان رودخانه شاپور، ورودی به سد رئیسعلی دلواری، واقع در استان بوشهر میباشد. روش بررسی: برای تخمین جریان ماهانه ورودی به سد رئیسعلی دلواری از مدلهای هوش مصنوعی شبکه عصبی مصنوعی (ANN) و سیستم استنتاج نروفازی تطبیقی (ANFIS) استفاده گردید. همچنین به منظور بهبود استفاده از نتایج این مدلها در تصمیمات مدیریتی در بخش آب، تعیین عدم قطعیت هر یک از آنها در فرآیند مدلسازی جریان انجام شد. در این راستا از نتایج شبیهسازی شده در اجرای هر مدل تحت الگوهای متفاوتی از دادههای واسنجی، استفاده و برای ارزیابی عدم قطعیت هر مدل نیز از دو شاخص عرض محدوده اطمینان (d-factor) و 95 درصد عدم قطعیت پیشبینیها واقع شده در این محدوده (95PPU) استفاده گردید. یافتهها: مطابق نتایج به دست آمده از مدلهای ANN و ANFIS بهینه اجرا شده، مشخص گردید که اگر چه مقادیر آمارههای ضریب تعیین (R2) و قدرمطلق میانگین خطاها (MAE) برای هر دو مدل از مقادیر مناسبی برخوردار بودند، اما عملکرد آنها در برخی نقاط با دبی بالا با خطای قابل توجهی همراه بود. همچنین با بررسی نتایج عدم قطعیت مدلها مشخص شد مدل ANFIS با مقدارd-factor کمتر و مقدار شاخص 95PPU بزرگتر، از عدم قطعیت کمتری نسبت به مدل ANN برخوردار بود. بحث و نتیجهگیری: با توجه به عملکرد تقریباً یکسان هر دو مدل ANN و ANFIS در مراحل واسنجی و صحتسنجی، میتوان مدل ANFIS را به عنوان مدل بهینه تخمین جریان ماهانه ورودی به سد رئیسعلی دلواری به دلیل دارا بودن عدم قطعیت کمتر پیشنهاد نمود.
چکیده انگلیسی:
Background and Objective: Accurate information about the river flow significantly influences the water resources management for the communities that use the water. In this regard, this study aims to present a reliable prediction of the monthly discharge of Shahpour River, inflow to Raees-Ali Delvari Dam, located in the Boushehr Province, Iran. Methods: To forecast the monthly inflow to Raees-Ali Delvari Dam, the artificial intelligence models, i.e. artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS), were applied. Also, uncertainty determination of the both models was carried out in order to improve the application of their results in the management decisions in the water sector. In this regard, the simulated results of the models, tuned with the different pattern of calibration data, were used. Two indices, i.e. the width of confidence band (d-factor) and the values bracketed by 95 percent prediction uncertainties (95PPU) were applied in order to evaluate the models’ uncertainty. Findings: Results of tuned ANN and ANFIS models indicated that although the both models had the appropriate values of determination coefficient (R2) and mean absolute error (MAE), their performance was along with considerable errors in the high extreme values. Besides, a look at through the uncertainty results of the models indicated the ANFIS model, that included the less d-factor and higher 95PPU values, had less uncertainty than the ANN. Discussion and Conclusion: Considering the same performance of the both ANN and ANFIS models in the calibration and test steps, it can be concluded that the ANFIS model was the best selection for monthly inflow prediction into Raees-Ali Delvari Dam due to its less uncertainty that ANN model.
منابع و مأخذ:
Sanikhani, H., Kisi, O., 2012. River flow estimation and forecasting by using two different adaptive neuro-fuzzy approaches. Water Resources Management, Vol. 26, pp.1715-1729
Patel, S.S., Ramachandran, P., 2015. A comparison of machine learning techniques for modeling river flow time series: the case of upper Cauvery river basin. Water Resources Management, Vol. 29, pp.589-602
Noori, R., Farokhnia, A., Morid, S., Madvar, H.R., 2009. Effect of inpiut variables preprocessing in artificial neural network on monthly flow prediction by PCA and wavelet transformation. Journal of Water and Wastewater, Vol. 1, pp.13-22 (In: Persian).
Marce, R., Comerma, M., García, J.C., Armengol, J., 2004. A neuro-fuzzy modeling tool to estimate fluvial nutrient loads in watersheds under time-varying human impact. Limnology and Oceanography Methods, Vol. 2, pp.342-355
Aqil, M., Kita, I., Yano, A., Nishiyama, S., 2007. Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool. Journal of Environmental Management, Vol. 85, pp.215-223
Noori, R., Safavi, S., Shahrokni, S.A.N., 2013. A reduced-order adaptive neuro-fuzzy inference system model as a software sensor for rapid estimation of five-day biochemical oxygen demand. Journal of Hydrology, Vol. 495, pp.175-185. https://doi.org/10.1016/j.jhydrol.2013.04.052
Noori, R., Yeh, H.D., Abbasi, M., Kachoosangi, F.T., Moazami, S. (2015). Uncertainty analysis of support vector machine for online prediction of five-day biochemical oxygen demand. Journal of Hydrology 527: 833-843. https://doi.org/10.1016/j.jhydrol.2015.05.046
Noori, R., Deng, Z., Kiaghadi, A., Kachoosangi, F.T., 2016. How reliable are ANN, ANFIS, and SVM techniques for predicting longitudinal dispersion coefficient in natural rivers? Journal of Hydraulic Engineering, Vol. 142. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001062
Jang, J.S.R., 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics Vol. 23, pp.665-685
Haykin, S., 1994. Neural Networks: A Comprehensive Foundation. Prentice Hall, New Jeresy.
Jalili, M., Noori, R., 2008. Prediction of municipal solid waste generation by use of artificial neural network: a case study of Mashhad. International Journal of Environmental Research, Vol. 2, pp.13-22
Noori, R., Karbassi, A., Farokhnia, A., Dehghani, M., 2009. Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environmental Engineering Science, Vol. 26, pp.1503-1510. https://doi.org/10.1089/ees.2008.0360
Noori, R., Karbassi, A.R., Mehdizadeh, H., Vesali‐Naseh, M., Sabahi, M.S., 2011. A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network. Environmental Progress & Sustainable Energy, Vol. 30, pp.439-449. https://doi.org/10.1002/ep.10478
Jang, J.S.R., Sun, C.T., 1995. Neuro-fuzzy modeling and control. Proceed. IEEE, Vol. 83, pp.378-406.
Dehghani, M., Saghafian, B., Nasiri Saleh, F., Farokhnia, A., Noori, R., 2014. Uncertainty analysis of streamflow drought forecast using artificial neural networks and Monte‐Carlo simulation. International Journal of Climatology, Vol. 34, pp.1169-1180. https://doi.org/10.1002/joc.3754
Moazami, S., Noori, R., Amiri, B.J., Yeganeh, B., 2016. Reliable prediction of carbon monoxide using developed support vector machine. Atmospheric Pollution Research, Vol. 7, pp.412-418. https://doi.org/10.1016/j.apr.2015.10.022
Noori, R., Hoshyaripour, G., Ashrafi, K., Araabi, B.N., 2010. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Atmospheric Environment, Vol. 44, pp.476-482. https://doi.org/10.1016/j.atmosenv.2009.11.005
_||_
Sanikhani, H., Kisi, O., 2012. River flow estimation and forecasting by using two different adaptive neuro-fuzzy approaches. Water Resources Management, Vol. 26, pp.1715-1729
Patel, S.S., Ramachandran, P., 2015. A comparison of machine learning techniques for modeling river flow time series: the case of upper Cauvery river basin. Water Resources Management, Vol. 29, pp.589-602
Noori, R., Farokhnia, A., Morid, S., Madvar, H.R., 2009. Effect of inpiut variables preprocessing in artificial neural network on monthly flow prediction by PCA and wavelet transformation. Journal of Water and Wastewater, Vol. 1, pp.13-22 (In: Persian).
Marce, R., Comerma, M., García, J.C., Armengol, J., 2004. A neuro-fuzzy modeling tool to estimate fluvial nutrient loads in watersheds under time-varying human impact. Limnology and Oceanography Methods, Vol. 2, pp.342-355
Aqil, M., Kita, I., Yano, A., Nishiyama, S., 2007. Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool. Journal of Environmental Management, Vol. 85, pp.215-223
Noori, R., Safavi, S., Shahrokni, S.A.N., 2013. A reduced-order adaptive neuro-fuzzy inference system model as a software sensor for rapid estimation of five-day biochemical oxygen demand. Journal of Hydrology, Vol. 495, pp.175-185. https://doi.org/10.1016/j.jhydrol.2013.04.052
Noori, R., Yeh, H.D., Abbasi, M., Kachoosangi, F.T., Moazami, S. (2015). Uncertainty analysis of support vector machine for online prediction of five-day biochemical oxygen demand. Journal of Hydrology 527: 833-843. https://doi.org/10.1016/j.jhydrol.2015.05.046
Noori, R., Deng, Z., Kiaghadi, A., Kachoosangi, F.T., 2016. How reliable are ANN, ANFIS, and SVM techniques for predicting longitudinal dispersion coefficient in natural rivers? Journal of Hydraulic Engineering, Vol. 142. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001062
Jang, J.S.R., 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics Vol. 23, pp.665-685
Haykin, S., 1994. Neural Networks: A Comprehensive Foundation. Prentice Hall, New Jeresy.
Jalili, M., Noori, R., 2008. Prediction of municipal solid waste generation by use of artificial neural network: a case study of Mashhad. International Journal of Environmental Research, Vol. 2, pp.13-22
Noori, R., Karbassi, A., Farokhnia, A., Dehghani, M., 2009. Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environmental Engineering Science, Vol. 26, pp.1503-1510. https://doi.org/10.1089/ees.2008.0360
Noori, R., Karbassi, A.R., Mehdizadeh, H., Vesali‐Naseh, M., Sabahi, M.S., 2011. A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network. Environmental Progress & Sustainable Energy, Vol. 30, pp.439-449. https://doi.org/10.1002/ep.10478
Jang, J.S.R., Sun, C.T., 1995. Neuro-fuzzy modeling and control. Proceed. IEEE, Vol. 83, pp.378-406.
Dehghani, M., Saghafian, B., Nasiri Saleh, F., Farokhnia, A., Noori, R., 2014. Uncertainty analysis of streamflow drought forecast using artificial neural networks and Monte‐Carlo simulation. International Journal of Climatology, Vol. 34, pp.1169-1180. https://doi.org/10.1002/joc.3754
Moazami, S., Noori, R., Amiri, B.J., Yeganeh, B., 2016. Reliable prediction of carbon monoxide using developed support vector machine. Atmospheric Pollution Research, Vol. 7, pp.412-418. https://doi.org/10.1016/j.apr.2015.10.022
Noori, R., Hoshyaripour, G., Ashrafi, K., Araabi, B.N., 2010. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Atmospheric Environment, Vol. 44, pp.476-482. https://doi.org/10.1016/j.atmosenv.2009.11.005