شبیه‌سازی اثرات تغییر اقلیم بر رواناب با استفاده از مدل‌های شبکه عصبی مصنوعی و سیستم استنتاج عصبی فازی تطبیقی (مطالعه موردی: حوضه آبریز طشک- بختگان)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشیار، گروه علوم و مهندسی منابع آب، دانشگاه بین‌المللی امام خمینی، قزوین، ایران.

2 دانشجوی دکتری، گروه مهندسی منابع آب، دانشگاه بین‌المللی امام خمینی، قزوین، ایران.

چکیده

در برنامه‌ریزی پروژه‌های منابع آب، برآورد میزان دسترسی به آب نقش مهمی ایفا می‌کند. اولین مرحله در برآورد در دسترس بودن آب، محاسبه رواناب در حوضه‌های آبریز است. از طرفی، تغییر اقلیم به‌صورت مستقیم بر روی مؤلفه‌های هیدرولوژیکی و منابع آبی تأثیرگذار است؛ لذا بررسی اثرات تغییر اقلیم بر مؤلفه‌های آبی همچون رواناب امری ضروری است. از این رو در این مطالعه وضعیت جریان ورودی به دریاچه‌های طشک- بختگان به‌عنوان یکی از مهمترین دریاچه‌های کشور مورد بررسی قرار گرفت. از آنجا که فرآیند بارش- رواناب به دلیل ماهیت غیرخطی و چند بعدی، مفهومی پیچیده است، تاکنون مدل‌های مفهومی و فیزیک- پایه مختلفی به منظور پیش‌بینی رواناب توسعه یافته است. وابستگی زیاد این مدل‌ها به پارامترها و نقشه‌های متعدد، عملاً کارایی آنها را در حوضه­‌های با آمار محدود با چالشی اساسی روبرو می­‌نماید. در مقابل، مدل‌های مبتنی بر شبکه‌ عصبی مصنوعی و سیستم استنتاج فازی به عنوان ابزارهای کاربردی درنظر گرفته می‌شوند که می‌توانند در چنین شرایطی به هیدرولوژیست‌ها در فعالیت‌های عملیاتی کمک کنند. در این مطالعه مدل‌های شبکه عصبی انتشار به جلو FFBPNN و سیستم استنتاج عصبی فازی تطبیقی ANFIS و تلفیق آن با الگوریتم‌های فراابتکاری بهینه‌سازی ازدحام ذرات (PSO) و ژنتیک (GA) به منظور بررسی وضعیت رواناب در شرایط تاریخی و نیز تغییر اقلیم تحت سناریوهای RCP و SSP مورد بررسی قرار گرفته است. نتایج به‌دست‌آمده نشان می‌دهد که مدل‌های FFBPNN و ANFIS تلفیق شده با الگوریتم PSO (ANFIS_PSO) با استفاده از متغیرهای بارش، دمای حداقل و دمای حداکثر به عنوان متغیرهای ورودی، به ترتیب با مقادیر ضریب همبستگی، ریشه میانگین مربعات خطا (متر مکعب بر ثانیه)، ضریب نش- ساتکلیف و کلینگ گوپتا (0/99، 2/07، 0/99 و 0/98 در دوره‌ آموزش و 0/94، 3/61، 0/91 و 0/88 در دوره‌ آزمون) و (0/98، 2/94، 0/97 و 0/98 در دوره‌ آموزش و 0/93، 3/87، 0/85 و 0/88 در دوره‌ آزمون) عملکرد بهتری نسبت به سایر مدل‎ها با ورودی‌های متفاوت داشته‌اند. نتایج این تحقیق می‌تواند برای بررسی اثرات این سناریوها بر حوضه‌های مهم کشور و در نتیجه برنامه‌ریزی و مدیریت منابع آب در شرایط تغییر اقلیم مفید باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Simulation of the Effects of Climate Change on Runoff Using Artificial Neural Network Models and Adaptive Fuzzy Neural Inference System (Case Study: Tashk-Bakhtegan Basin)

نویسندگان [English]

  • Hamed Mazandarani zadeh 1
  • Mohammad Fallah Kalaki 2
  • Asghar Azizian 1
1 Associate Professor, Water Resources Engineering Department, Imam Khomeini International University, Qazvin, Iran.
2 Ph.D. Student, Water Resources Engineering Department, Imam Khomeini International University, Qazvin, Iran .
چکیده [English]

Estimating the available water plays a vital role in planning water resources projects. The first step in assessing water availability is to calculate runoff in catchments. Moreover, it is necessary to study the effects of climate change on water components such as runoff since climate change directly affects the hydrological components and water resources. In this study, the status of the inflow to Tashk-Bakhtegan lakes as one of the most important lakes in the country was investigated. Because generation of runoff is a complex concept due to its nonlinear and multidimensional nature, various theoretical and physical models have been developed to predict runoff. The high dependence of these physical models on numerous parameters and maps, practically challenfged their efficiency in basins with limited observations. On the other hand, models based on artificial neural networks and fuzzy inference systems are considered applied tools that can help hydrologists in such circumstances. In this study, FFBPNN and ANFIS models and their combination with PSO and GA metaheuristic algorithms have been investigated in evaluating the runoff in historical conditions and under RCP and SSP climate change scenarios.  The obtained results showed that the FFBPNN and ANFIS models combined with the PSO algorithm (ANFIS_PSO) using precipitation, minimum temperature, and maximum temperature as inputs had better performance compared to other models with different inputs. The values of the correlation coefficient, root mean square error (m3/s), Nash-Sutcliffe coefficient and Kling Gupta were respectively 0.99, 2.07, 0.99 and 0.98 in the training period and 0.94, 3.61, 0.91 and 0.88 in the test period and 0.98, 94. 2, 0.97 and 0.98 in the training period and 0.93, 3.87, 0.85 and 0.88 in the test period. The results of this study can be used in investigating the effects of the above mentioned scenarios on important basins of the country and consequently in planning and managing water resources in the context of climate change.

کلیدواژه‌ها [English]

  • Climate Change
  • FFBPNN
  • ANFIS
  • Metaheuristic Algorithms
Evaluation of the effects of climate change on water resource sustainability in basins using water footprint scarcity indicators. Iran-Water Resources Research 15(4):259-272 (In Persian)
Aghakhaniafshar A, Hasanzadeh Y, Pourreza-Bilondi A A B M (2016) Seasonal changes of precipitation and temperature of mountainous watersheds in future periods with approach of fifth report of Intergovernmental Panel on Climate Change (Case study: Kashafrood Watershed Basin). Journal of Water and Soil 30(5):1718-1732
Almazroui M, Saeed F, Saeed S, Islam M N, Ismail M, Klutse N A B (2020) Siddiqui, M.H. projected change in temperature and precipitation over Africa from CMIP6. Earth Systems and Environment 4(3):455–475
Annayat W, Gupta A, Prakash K R, Sil B S (2021) Application of artificial neural networks and multiple linear regression for rainfall–runoff modeling. In Communication Software and Networks, Springer, Singapore.‏ 719-727
Dastorani M T, Moghadamnia A, Piri J, Rico-Ramirez M (2010) Application of ANN and ANFIS models for reconstructing missing flow data. Environmental Monitoring and Assessment 166(1):421-434‏
Delavar M, Morid S, and Morid R (2017) Basin-wide water accounting based on modified SWAT model (SWAT-PARS): an application on the Tashk Bakhtegan Basin, Iran. 2017 International SWAT Conference in Warsaw, Poland
Delavar M, Morid S, Morid R, Farokhnia A, Babaeian F, Srinivasan R, Karimi P (2020) Basin-wide water accounting based on modified SWAT model and WA+ framework for better policy making. Journal of Hydrology 585:124762‏
Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. In MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science (pp. 39-43)
Elbedwehy M N, Zawbaa H M, Ghali N, Hassanien A E (2012) Detection of heart disease using binary particle swarm optimization. In 2012 Federated Conference on Computer Science and Information Systems (FedCSIS) (pp. 177-182)
Fallah Kalaki M, Shokri Kuchak V, Ramezani Etedali H (2021) Simulating the effects of climate change on runoff using the CMIP5 and CMIP6 climate models by SWAT hydrological model (Case Study: Tashk-Bakhtegan Basin). Iran-Water Resources Research 17(3):345-359‏ (In Persian)
Ghomsheh V S, Shoorehdeli M A, Teshnehlab M (2007) Training ANFIS structure with modified PSO algorithm. In 2007 Mediterranean Conference on Control & Automation (pp. 1-6), IEEE‏
Ghose D K, Samantaray S (2018) Modelling sediment concentration using back propagation neural network and regression coupled with genetic algorithm. Procedia Computer Science 9(125):85-92‏
Goldberg D E, Holland J H (1988) Genetic algorithms and machine learning. Machine Learning, Springer
Gupta H V, Kling H, Yilmaz K K, Martinez G F (2009) Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. Journal of Hydrology 377(1-2):80-91‏
Hempel S, Frieler K, Warszawski L, Schewe J, Piontek F (2013) A trend-preserving bias correction–the ISI-MIP approach. Earth System Dynamics 4(2):219-236‏
Hyndman R J, Koehler A B (2006) Another look at measures of forecast accuracy. International Journal of Forecasting 22(4):679-688‏
Jang J S (1993) ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics 23(3):665-685‏
Jang J S R, Gulley N (1995) The fuzzy logic toolbox for use with MATLAB. Natick, MA: The Mathworks
Jimmy S R, Sahoo A, Samantaray S, Ghose D K (2021) Prophecy of runoff in a river basin using various neural networks. In Communication software and networks. Springer, Singapore‏ 709-718
Kavoosi M, Khozeymehnehad H (2021) Review and compare performance of 4 modeling methods LS-SVM, NN, GEP and ANFIS-PSO in simulation of rainfall-runoff (Study area: Halil River-Jiroft Dam). Irrigation and Water Engineering 11(3):96-110‏ (In Persian)
Kazemzadeh M, Malekian A, Moghaddam N A, Khalighi S S (2019) Evaluation of climate change impacts on hydrological characteristics of watershed (Case study: Aji-Chai Watershed).‏ Iranian Journal of Watershed Management Science and Engineering 13(45 ):1-11 (In Persian)
Kim J H, Sung J H, Chung E S, Kim S U, Son M, Shiru M S (2021) Comparison of projection in meteorological and hydrological droughts in the Cheongmicheon watershed for RCP4. 5 and SSP2-4.5. Sustainability 13(4):2066‏
Lin Y, Wen H, Liu S (2019) Surface runoff response to climate change based on artificial neural network (ANN) models: A case study with Zagunao catchment in Upper Minjiang River, Southwest China. Journal of Water and Climate Change 10(1):158-166‏
Mansouri A, Aminnejad B, Ahmadi H (2018) Investigating the effect of climate change on inflow runoff into the Karun-4 Dam based on IPCC's fourth and fifth report. JWSS-Isfahan University of Technology 22(2):345-359‏
Mehri Y, Mehri M, Soltani J (2020) Evaluation of combined models with optimization approach of PSO and GA in ANFIS for predicting of dispersion coefficient in rivers. Water and Irrigation Management 10(1):45-59 (In Persian)
Mirjalili S (2019) Genetic algorithm. In Evolutionary Algorithms and Neural Networks (pp. 43-55), Springer, Cham‏
Moayedi H, Aghel B, Vaferi B, Foong L K, Bui D T (2020) The feasibility of Levenberg–Marquardt algorithm combined with imperialist competitive computational method predicting drag reduction in crude oil pipelines. Journal of Petroleum Science and Engineering 185:106634
MOE (Ministry of Energy) (2017) Climate change adaptation strategies and national plans in water sector, Simulating water resources and agricultural systems in Tashk-Bakhtegan basin. (In Persian)
Moghaddamnia A, Gousheh M G, Piri J, Amin S, Han D (2009) Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. Advances in Water Resources 32(1):88-97‏
Nabizadeh M, Mosaedi A, Dehghani A A (2012) Intelligent estimation of stream flow by adaptive neuro-fuzzy inference system. Water and Irrigation Management 2(1):69-80‏ (In Persian)
Nash J E, Sutcliffe J V (1970) River flow forecasting through conceptual models, part I-A, discussion of principles. Journal of Hydrology 10(3):282-290‏
Nath A, Mthethwa F, Saha G (2020) Runoff estimation using modified adaptive neuro-fuzzy inference system. Environmental Engineering Research 25(4):545-553‏
Nayak P C, Sudheer K P, Rangan D M, Ramasastri K S (2004) A neuro-fuzzy computing technique for modeling hydrological time series. Journal of Hydrology 291(1-2):52-66‏
‏Nouri H, Ildoromi A, Sepehri M, Artimani M (2019) Comparing three main methods of artificial intelligence in flood estimation in Yalphan Catchment. Geography and Environmental Planning 29(4):35-50‏ (In Persian)
Pearson K (1897) Mathematical contributions to the theory of evolution. On a form of spurious correlation which may arise when indices are used in the measurement of organs. Proceedings of the Royal Society of London 60(359-367):489-498‏
Rezaeianzadeh M, Tabari H, Arabi Yazdi A, Isik S, Kalin L (2014) Flood flow forecasting using ANN, ANFIS and regression models. Neural Computing and Applications 25(1):25-37
Roy B, Singh M P (2020) An empirical-based rainfall-runoff modelling using optimization technique. International Journal of River Basin Management 18(1):49-67‏
Samanataray S, Sahoo A (2021) A comparative study on prediction of monthly streamflow using hybrid ANFIS-PSO approaches. KSCE Journal of Civil Engineering 25(10):4032-4043‏
Sarbayev M, Yang M, Wang H (2019) Risk assessment of process systems by mapping fault tree into artificial neural network. Journal of Loss Prevention in the Process Industries 60:203-212
Shahin M A, Maier H R, Jaksa M B (2004) Data division for developing neural networks applied to geotechnical engineering. Journal of Computing in Civil Engineering 18(2):105-114‏
‏Shaik N B, Pedapati S R, Taqvi S A A, Othman A R, Dzubir F A A (2020) A feed-forward back propagation neural network approach to predict the life condition of crude oil pipeline. Processes 8(6):661‏
Shokri Kuchak S, Radmanesh F (2015) Drought forecast in Tashk Bakhtegan Basin. National Congress of Irrigation and Drainage of Iran, Ferdowsi University of Mashhad (In Persian)
Smith J, Eli R N (1995) Neural-network models of rainfall-runoff process. Journal of Water Resources Planning and Management 121(6):499-508
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics SMC-15(1):116-132‏
Taqvi S A, Tufa L D, Zabiri H, Maulud A S, Uddin F (2020) Fault detection in distillation column using NARX neural network. Neural Computing and Applications 32(8):3503-3519‏
Tokar A S, & Markus M (2000) Precipitation-runoff modeling using artificial neural networks and conceptual models. Journal of Hydrologic Engineering 5(2):156-161‏
Wajahat A, Sundar S B (2018) Estimation and analysis of possible flood for the Silchar city-A Case Study.‏ Disaster Advances 11(1):25-32
Wang J, Hu L, Li D, Ren M (2020) Potential impacts of projected climate change under CMIP5 RCP scenarios on streamflow in the Wabash River Basin. Advances in Meteorology 2020(4):1-18
Wu F, Shi Q, Hasan S S, Shi C, Gibson J (2019) Urbanization and industrial transformation for improved water management. River Basin Management, Book series Ecohydrology 1-29
Wu S J, Hsu C T, Chang C H (2021) Stochastic modeling of artificial neural networks for real-time hydrological forecasts based on uncertainties in transfer functions and ANN weights. Hydrology Research 52(6):1490-1525‏
Yang C C, Chen C S (2009) Application of integrated back‐propagation network and self-organizing map for flood forecasting. Hydrological Processes: An International Journal 23(9):1313-1323‏
Yaseen Z M, Ebtehaj I, Kim S, Sanikhani H, Asadi H, Ghareb M I, Shahid S (2019) Novel hybrid data-intelligence model for forecasting monthly rainfall with uncertainty analysis. Water 11(3):502‏
Zadeh L A (1965) Fuzzy set theory. Information and Control 8(3):338-353‏