Reservoir Inflow Prediction: A Comparison between Semi Distributed Numerical and Artificial Neural Network Modelling

Springer Science and Business Media LLC - Tập 37 Số 15 - Trang 6127-6143 - 2023
Shelke, Mahesh1, Londhe, S. N.2, Dixit, P. R.2, Kolhe, Pravin3
1Vishwakarma Institute of Information Technology, Pune, India
2Department of Civil Engineering, Vishwakarma Institute of Information Technology, Pune, India
3Water Resource Department, Government of Maharashtra, Pune, India

Tóm tắt

Reservoir inflow is a major component of the reservoir operations management system. It becomes highly essential to predict the accurate reservoir inflow. The lumped models and semi-distributed or fully distributed model implemented to solve a range of specific problems in the prediction of reservoir inflow. The findings in this paper compare a conceptual semi distributed Hydrologic Engineering Centre Hydrologic Modelling System (HEC-HMS) model and an ANN (Artificial Neural Network) based model for the prediction of inflow in the Koyna reservoir catchment, Maharashtra. The performance of the models is assessed using different statistical indicators such as Nash–Sutcliffe Efficiency (NSE), Root Mean Square Error (RMSE), Correlation Coefficient (r) and Mean Absolute Error (MAE). The results confirmed the ability of the semi distributed (rHEC-HMS = 0.92, RMSEHEC-HMS = 129.37 m3/s, MAEHEC-HMS = 21.66 m3/s, NSEHEC-HMS = 0.82 and RSRHEC-HMS = 0.42) and ANN model (rANN = 0.85, RMSEANN = 176.29 m3/s, MAEANN = 14.62 m3/s, NSEANN = 0.69 and RSRANN = 0.55) to capture the effect of the complex hydrological phenomenon, variations of land use and soils of watershed. The study illustrates that the semi distributed HEC-HMS model shows moderately better results compared to ANN model. It may be noted that the ANN predicts the reservoir inflow using only one input i.e., rainfall, whereas the HEC-HMS requires exogenous input parameters and plenty of time for model building compared to ANN. This work will have a significant contribution for planning of reservoir operations within the catchment of Koyna reservoir.

Tài liệu tham khảo

citation_journal_title=Water; citation_title=The performance of physically based and conceptual hydrologic models: a case study for Makkah Watershed, Saudi Arabia; citation_author=AM Al-Areeq, MA Al-Zahrani, HO Sharif; citation_volume=13; citation_publication_date=2021; citation_pages=1098; citation_doi=10.3390/w13081098; citation_id=CR1 ASCE Task Committee (2000) Application of artificial neural networks in Hydrology 1: Preliminary concepts. J Hydrol Eng ASCE 5(2):115–123 citation_journal_title=Water Resour Manage; citation_title=Artificial neural network and support vector machine models for inflow prediction of dam reservoir (case study: Zayandehroud dam reservoir); citation_author=M Babaei, R Moeini, E Ehsanzadeh; citation_volume=33; citation_publication_date=2019; citation_pages=1-16; citation_doi=10.1007/s11269-019-02252-5; citation_id=CR3 citation_journal_title=Environ Dev Sustain; citation_title=Reservoir operation under influence of the joint uncertainty of inflow and evaporation; citation_author=HO Bozorg, P Yari, M Delpasand, X Chu; citation_volume=24; citation_issue=2; citation_publication_date=2022; citation_pages=2914-2940; citation_doi=10.1007/s10668-021-01560-4; citation_id=CR4 citation_journal_title=J Water; citation_title=Daily reservoir runoff forecasting method using artificial neural network based on quantum-behaved particle swarm optimization; citation_author=C Cheng, W Niu, Z Feng, J Shen, K Chau; citation_volume=7; citation_publication_date=2015; citation_pages=4232-4246; citation_doi=10.3390/w7084232; citation_id=CR5 Chiamsathit S, Adeloye AJ, Bankaru-Swamy S (2016) Inflow forecasting using artificial neural networks for reservoir operation. International Association of Hydrological Sciences. https://proc-iahs.net/373/209/2016/ Congedo L (2021) Semi-automatic classification plug-in: a python tool for the download and processing of remote sensing images in QGIS. J Open-Source Softw 6(64):3172. https://doi.org/10.21105/joss.03172 citation_journal_title=Prog Phys Geogr; citation_title=Hydrological modelling using artificial neural network; citation_author=CW Dawson, RL Wilby; citation_volume=25; citation_issue=1; citation_publication_date=2001; citation_pages=80-108; citation_doi=10.1177/030913330102500104; citation_id=CR8 citation_journal_title=J Environ Model Softw; citation_title=Application of the HEC-HMS model for runoff simulation in a tropical catchment; citation_author=D Halwatura, M Najim; citation_volume=46; citation_publication_date=2013; citation_pages=155-162; citation_doi=10.1016/j.envsoft.2013.03.006; citation_id=CR9 HEC (2021) U.S. Army Corps of Engineers, Hydrologic Engineering Center. HEC-HMS hydrologic modelling system, User’s Manual, Version 4.8.0 Davis, CA. https://www.hec.usace.army.mil/software/HEC-HMS/documentation.aspx Hu S, Shrestha P (2020) Examine the impact of land use and land cover changes on peak discharges of a watershed in the Midwestern United States using the HEC-HMS model. Papers in Applied Geography. ISSN: 2375-4931. https://doi.org/10.1080/23754931.2020.1732447 Ibrahim SM, Yuk FH, Ali NA, Chai HK, Ahmed E (2022) A review of the hybrid artificial intelligence and optimization modelling of hydrological streamflow forecasting. Alexandria Eng J 61(1):279–303. ISSN: 1110-0168. https://doi.org/10.1016/j.aej.2021.04.100 citation_journal_title=J Hydraul Eng; citation_title=Rainfall- Runoff modelling using Neural Networks: State of the art and future research needs; citation_author=A Jain, HR Maier, GC Dandy, KP Sudheer; citation_volume=15; citation_issue=1; citation_publication_date=2009; citation_pages=52-74; citation_id=CR13 citation_journal_title=Int J Ships Offshore Struct; citation_title=Neural networks in ocean engineering; citation_author=P Jain, MC Deo; citation_volume=1; citation_publication_date=2006; citation_pages=25-35; citation_doi=10.1533/saos.2004.0005; citation_id=CR14 citation_journal_title=J Hydrol; citation_title=Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data; citation_author=V Jothiprakash, RB Magar; citation_publication_date=2012; citation_doi=10.1016/j.jhydrol.2012.04.045; citation_id=CR15 citation_journal_title=J Civil Eng; citation_title=Time of concentration of small agricultural watersheds; citation_author=ZP Kirpich; citation_volume=10; citation_publication_date=1940; citation_pages=362-368; citation_id=CR16 citation_journal_title=J Water Resour Eng; citation_title=Evaluating the use of “goodness-of-fit” Measures in hydrologic and hydroclimatic model validation; citation_author=DR Legates, GJ McCabe; citation_volume=35; citation_publication_date=1999; citation_pages=233-241; citation_doi=10.1029/1998WR900018; citation_id=CR17 citation_journal_title=J Hydrol Sci; citation_title=Comparison of data-driven modelling techniques for river flow forecasting; citation_author=S Londhe, S Charhate; citation_volume=55; citation_issue=7; citation_publication_date=2010; citation_pages=1163-1174; citation_doi=10.1080/02626667.2010.512867; citation_id=CR18 Londhe S, Panchang V (2018) ANN techniques: a survey of coastal applications. J Adv Coast Hydraul 199–234 citation_journal_title=J Earth Syst Sci; citation_title=Intermittent reservoir daily-inflow prediction using lumped and distributed data multi- linear regression models; citation_author=RB Magar, V Jothiprakash; citation_volume=120; citation_issue=6; citation_publication_date=2011; citation_pages=1067-1084; citation_doi=10.1007/s12040-011-0127-9; citation_id=CR20 Mitra S, Nigam R (2021) An approach to utilize artificial neural network for runoff prediction: River perspective. In: Proceeding of 2021 International Conference on Emerging Trends in Materials Science Technology and Engineering. pp 2214–7853 Namara GW, Damise TA, Tufa FG (2019) Rainfall runoff modelling using HECH-HMS: The case of Awash Bello subcatchment, Upper Awash Basin, Ethiopia. Int J Environ 9(1). ISSN: 2091-2854 citation_journal_title=J Earth Syst Sci; citation_title=Simulation of rainfall–runoff process for an ungauged catchment using an event-based hydrologic model: a case study of koraiyar basin in Tiruchirappalli city, India; citation_author=S Natarajan, N Radhakrishnan; citation_volume=130; citation_publication_date=2021; citation_pages=1; citation_doi=10.1007/s12040-020-01532-8; citation_id=CR23 Niu W-J, Feng Z-K, Feng B-F, Min Y-W, Cheng C-T, Zhou J-Z (2018) Comparison of multiple linear regression, artificial neural network, extreme learning machine, and support vector machine in deriving operation rule of hydropower reservoir. J Water 11:88. https://doi.org/10.3390/w11010088 citation_journal_title=J Afr Earth Sci; citation_title=Runoff assessment and modeling in arid regions by integration of watershed and hydrologic models with GIS techniques; citation_author=BA Niyazi, Masoud M Hm, M Admed, JM Basahi, MA Rashed; citation_volume=172; citation_publication_date=2020; citation_pages=103966; citation_doi=10.1016/j.jafrearsci.2020.103966; citation_id=CR25 citation_journal_title=Hydrology; citation_title=Suzuki S (2023) A comparative evaluation of lumped and semi-distributed conceptual hydrological models: Does model complexity enhance hydrograph prediction?; citation_author=E Okiria, H Okazawa, K Noda, Y Kobayashi; citation_volume=9; citation_publication_date=2022; citation_pages=89; citation_doi=10.3390/hydrology9050089; citation_id=CR26 citation_journal_title=J Water Sci Eng; citation_title=Application of HEC-HMS for flood forecasting in Misai and Wan’an catchments in China; citation_author=JO Oleyiblo, ZJ Li; citation_volume=3; citation_issue=1; citation_publication_date=2010; citation_pages=14-22; citation_id=CR27 citation_journal_title=Water Resour Manage; citation_title=Improving hybrid models for precipitation forecasting by combining nonlinear machine learning methods; citation_author=L Parviz, K Rasouli, HA Torabi; citation_volume=37; citation_publication_date=2023; citation_pages=3833-3855; citation_doi=10.1007/s11269-023-03528-7; citation_id=CR28 citation_journal_title=J of Water; citation_title=Impact assessment of rainfall runoff simulations on the flow duration curve of the upper indus river-a comparison of data-driven and hydrologic models; citation_author=A Rauf, AR Ghumman; citation_volume=10; citation_publication_date=2018; citation_pages=876; citation_doi=10.3390/w10070876; citation_id=CR29 Saikia P, Dutta R, Singh SK, Chaudhuri PK (2020) Artificial Neural Networks in the domain of reservoir characterization: a review from shallow to deep models. J Comput Geosci 135:104357. 0098–3004/© 2019 Elsevier Ltd. https://doi.org/10.15666/aeer/1504_497510 2017 Shah M, Lone M (2022) Hydrological modelling to simulate stream flow in the Sindh Valley watershed, northwest Himalayas. Model Earth Syst Environ 8. https://doi.org/10.1007/s40808-021-01241-1 citation_journal_title=Water Resour; citation_title=A hybrid model for runoff prediction using variational mode decomposition and artificial neural network; citation_author=M Sibtain, X Li, B Hassan, MI Azam; citation_volume=48; citation_issue=2021; citation_publication_date=2020; citation_pages=701-712; citation_id=CR32 Sitterson J, Knightes C, Parmar R, Wolfe K, MucheM, Avant B (2017) An overview of rainfall runoff model types. United States Environmental Protection Agency Report Washington DC EPA/600/R-14/152 Tassew B, Belete MA, Miegel K (2019) Application of HEC-HMS model for flow simulation in the Lake Tana Basin: The case of Gilgel Abay catchment, Upper Blue Nile Basin, Ethiopia. J Hydrol 6:(21) Vidyarthi VK, Jain A (2020) Modelling rainfall-runoff process using artificial neural network with emphasis on parameter sensitivity. J Model Earth Syst Env 2(1):833–837 Webster G, Donald TR, Innocent N, Trimothy D (2017) Ungauged runoff simulation in Upper Manyame Catchment, Zimbabwe Application of the HEC-HMS model. J Phys Chem Earth 100:371–382 citation_journal_title=J Hydrol; citation_title=Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model; citation_author=S Yang, D Yang, J Chen, B Zhao; citation_volume=579; citation_issue=2019; citation_publication_date=2019; citation_pages=124229; citation_doi=10.1016/j.jhydrol.2019.124229; citation_id=CR37 Yaseen ZM, Sulaiman SO, Sadeq OS, Ravinesh CD, Chau KW (2019) An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569. https://doi.org/10.1016/j.jhydrol.2018.11.069 citation_journal_title=Water Resour Manage; citation_title=Application of machine learning-based energy use forecasting for inter-basin water transfer project; citation_author=S Yi, GM Kondolf, S Sandoval-Solis, L Dale; citation_volume=36; citation_publication_date=2022; citation_pages=5675-5694; citation_doi=10.1007/s11269-022-03326-7; citation_id=CR39 citation_journal_title=Int J Disaster Risk Reduct; citation_title=Flash floods, land-use change, and risk dynamics in mountainous tourist areas: a case study of the Yesanpo Scenic Area, Beijing, China; citation_author=C Yu, W Ying, Z Yue, Q Luan, C Xiaojuan; citation_volume=50; citation_publication_date=2020; citation_pages=101873; citation_doi=10.1016/j.ijdrr.2020.101873; citation_id=CR40 citation_journal_title=Water Resour Manage; citation_title=Optimizing the runoff estimation with HEC-HMS model using spatial evapotranspiration by the SEBS model; citation_author=M Zare, M Pakparvar, S Jamshidi; citation_volume=35; citation_publication_date=2021; citation_pages=2633-2648; citation_doi=10.1007/s11269-021-02855-x; citation_id=CR41 citation_journal_title=J Hydrol; citation_title=Modelling and simulating reservoir operation using the artificial neural network, support vector regression and deep learning algorithm; citation_author=D Zhang, J Lin, Q Peng, D Wang, T Yang, S Sorooshian, X Liu, J Zhuang; citation_volume=565; citation_publication_date=2018; citation_pages=720-736; citation_doi=10.1016/j.jhydrol.2018.08.050; citation_id=CR42 citation_journal_title=Manage: Eur Water Resour Assoc (EWRA); citation_title=Quantifying the uncertainties in data-driven models for reservoir inflow prediction; citation_author=X Zhang, H Wang, A Peng, W Wang, B Li, X Huang; citation_volume=34; citation_issue=4; citation_publication_date=2020; citation_pages=1479-1493; citation_id=CR43