Abstract
Reservoirs play a crucial role in flood control by storing and regulating the water. Inflow forecasting in real-time is essential for the effective management of reservoir water. The emergence of high spatial resolution weather forecasts and explainable Machine Learning (eXML) algorithms remove the barriers to accurate forecasting and provide a better understanding of Machine Learning (ML) models. In this context, reservoir inflows are forecasted using eXML models and Global Forecasting System (GFS) data: precipitation, minimum and maximum temperature. Popular ML methods like Long Short Term Memory (LSTM), Multilayer Perceptron, Support Vectors Machine and Random Forest are used in this study. Further, these models' explainability is assessed using the Shapley additive explanations method. The ML models are trained and tested using the observed data from 2000 to 2018 in the Tenughat catchment, Damodar river basin, India. Among all the ML models, the LSTM model better predicted the inflows with an NSE value of 0.938. The eXML revealed that inflow and precipitation variables of 1-day lag significantly impact the models’ prediction in all models. The GFS data of 2017–2018 was bias-corrected using the Scaled Distribution Mapping method, and the method improved the GFS data significantly. The inflow forecasting using the LSTM model with the bias-corrected GFS data revealed that the LSTM model performed well up to 3-day lead time (NSE = 0.908, 0.888, 0.876 for 1–3 day lead). Thus, the LSTM model with the GFS forecasts has substantial potential for real-time forecasting of reservoir inflows.
Similar content being viewed by others
References
Adnan RM, Zounemat-Kermani M, Kuriqi A, Kisi O (2021) Machine learning method in prediction streamflow considering periodicity component. In: Intelligent data analytics for decision-support systems in hazard mitigation. Springer, Singapore, pp 383–403. https://doi.org/10.1007/978-981-15-5772-9_18
Althoff D, Bazame HC, Nascimento JG (2021) Untangling hybrid hydrological models with explainable artificial intelligence. H2Open J 4(1):13–28. https://doi.org/10.2166/h2oj.2021.066
Babaei M, Moeini R, Ehsanzadeh E (2019) Artificial neural network and support vector machine models for inflow prediction of dam reservoir (case study: Zayandehroud dam reservoir). Water Resour Manag 33(6):2203–2218. https://doi.org/10.1007/s11269-019-02252-5
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Casanueva A, Herrera S, Iturbide M et al (2020) Testing bias adjustment methods for regional climate change applications under observational uncertainty and resolution mismatch. Atmos Sci Lett 21(7):978. https://doi.org/10.1002/asl.978
Chen J, Brissette FP, Chaumont D, Braun M (2013) Performance and uncertainty evaluation of empirical downscaling methods in quantifying the climate change impacts on hydrology over two North American river basins. J Hydrol 479:200–214. https://doi.org/10.1016/j.jhydrol.2012.11.062
Cheng M, Fang F, Kinouchi T, Navon IM, Pain CC (2020) Long lead-time daily and monthly streamflow forecasting using machine learning methods. J Hydrol 590:125376. https://doi.org/10.1016/j.jhydrol.2020.125376
Dikshit A, Pradhan B (2021) Explainable AI in drought forecasting. Mach Learn Appl 6:100192. https://doi.org/10.1016/j.mlwa.2021.100192
Efron B (2000) The bootstrap and modern statistics. J Am Stat Assoc 95(452):1293–1296. https://doi.org/10.1080/01621459.2000.10474333
Elbeltagi A, Di-Nunno F, Kushwaha NL, de Marinis G, Granata F (2022) River flow rate prediction in the Des Moines watershed (Iowa, USA): a machine learning approach. Stoch Environ Res Risk Assess 36:3835–3855. https://doi.org/10.1007/s00477-022-02228-9
Gumindoga W, Rientjes TH, Haile AT, Makurira H, Reggiani P (2019) Performance of bias-correction schemes for CMORPH rainfall estimates in the Zambezi River basin. Hydrol Earth Syst Sci 23(7):2915–2938. https://doi.org/10.5194/hess-23-2915-2019
Hameed MM, AlOmar MK, Al-Saadi AA, AlSaadi MA (2022) Inflow forecasting using regularized extreme learning machine: Haditha reservoir chosen as case study. Stoch Environ Res Risk Assess 36(6):1–21. https://doi.org/10.1007/s00477-022-02254-7
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hong J, Lee S, Bae JH et al (2020) Development and evaluation of the combined machine learning models for the prediction of dam inflow. Water 12(10):2927. https://doi.org/10.3390/w12102927
Johny CJ, Prasad VS (2020) Application of hind cast in identifying extreme events over India. J Earth Syst Sci 129(1):1–11. https://doi.org/10.1007/s12040-020-01435-8
Jones PW (1999) First-and second-order conservative remapping schemes for grids in spherical coordinates. Mon Weather Rev 127(9):2204–2210. https://doi.org/10.1175/1520-0493(1999)
Karamouz M, Ahmadi A, Moridi A (2009) Probabilistic reservoir operation using Bayesian stochastic model and support vector machine. Adv Water Resour 32(11):1588–1600. https://doi.org/10.1016/j.advwatres.2009.08.003
Kumar A, Ramsankaran RJ, Brocca L, Muñoz-Arriola F (2021) A simple machine learning approach to model real-time streamflow using satellite inputs: demonstration in a data scarce catchment. J Hydrol 595:126046. https://doi.org/10.1016/j.jhydrol.2021.126046
Kumar A, Sridevi C, Durai VR, Singh KK, Mukhopadhyay P, Chattopadhyay N (2019) MOS guidance using a neural network for the rainfall forecast over India. J Earth Syst Sci 128:1–12. https://doi.org/10.1007/s12040-019-1149-y
Kumar S, Tiwari MK, Chatterjee C, Mishra A (2015) Reservoir inflow forecasting using ensemble models based on neural networks, wavelet analysis and bootstrap method. Water Resour Manag 29(13):4863–4883. https://doi.org/10.1007/s11269-015-1095-7
Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Adv Neural Info Process Syst 30:4768–4777
Latif SD, Ahmed AN, Sathiamurthy E, Huang YF, El-Shafie A (2021) Evaluation of deep learning algorithm for inflow forecasting: a case study of Durian Tunggal Reservoir, Peninsular Malaysia. Nat Hazards 109(1):351–369. https://doi.org/10.1007/s11069-021-04839-x
Lenderink G, Buishand A, Van Deursen W (2007) Estimates of future discharges of the river Rhine using two scenario methodologies: direct versus delta approach. Hydrol Earth Syst Sci 11(3):1145–1159. https://doi.org/10.5194/hess-11-1145-2007
Leander R, Buishand TA (2007) Resampling of regional climate model output for the simulation of extreme river flows. J Hydrol 332(3–4):487–496. https://doi.org/10.1016/j.jhydrol.2006.08.006
Luo X, Yuan X, Zhu S, Xu Z, Meng L, Peng J (2019) A hybrid support vector regression framework for streamflow forecast. J Hydrol 568:184–193. https://doi.org/10.1016/j.jhydrol.2018.10.064
Malik A, Tikhamarine Y, Souag-Gamane D, Kisi O, Pham QB (2020) Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction. Stoch Environ Res Risk Assess 34(11):1755–1773. https://doi.org/10.1007/s00477-020-01874-1
Meddage DP, Ekanayake IU, Weerasuriya AU et al (2022) Explainable Machine Learning (XML) to predict external wind pressure of a low-rise building in urban-like settings. J Wind Eng Ind Aerodyn 226:105027. https://doi.org/10.1016/j.jweia.2022.105027
Molnar C (2020) Interpretable machine learning. Lulu Press, Morrisville
Mukhopadhyay P, Prasad VS, Krishna R et al (2019) Performance of a very high-resolution global forecast system model (GFS T1534) at 12.5 km over the Indian region during the 2016–2017 monsoon seasons. J Earth Syst Sci 128(6):1–18. https://doi.org/10.1007/s12040-019-1186-6
Nanda T, Sahoo B, Beria H, Chatterjee C (2016) A wavelet-based non-linear autoregressive with exogenous inputs (WNARX) dynamic neural network model for real-time flood forecasting using satellite-based rainfall products. J Hydrol 539:57–73. https://doi.org/10.1016/j.jhydrol.2016.05.014
Nicolle P, Pushpalatha R, Perrin C et al (2014) Benchmarking hydrological models for low-flow simulation and forecasting on French catchments. Hydrol Earth Syst Sci 18(8):2829–2857. https://doi.org/10.5194/hess-18-2829-2014
Parisouj P, Mohebzadeh H, Lee T (2020) Employing machine learning algorithms for streamflow prediction: a case study of four river basins with different climatic zones in the United States. Water Resour Manag 34(13):4113–4131. https://doi.org/10.1007/s11269-020-02659-5
Piani C, Haerter JO, Coppola E (2010) Statistical bias correction for daily precipitation in regional climate models over Europe. Theor Appl Climatol 99(1):187–192. https://doi.org/10.1007/s00704-009-0134-9
Rao SA, Goswami BN, Sahai AK et al (2019) Monsoon mission: a targeted activity to improve monsoon prediction across scales. Bull Am Meteorol Soc 100(12):2509–2532. https://doi.org/10.1175/BAMS-D-17-0330.1
Ribeiro MT, Singh S, Guestrin C (2018) Anchors: high-precision model-agnostic explanations. I:n Proceedings of the AAAI conference on artificial intelligence, p 32. https://doi.org/10.1609/aaai.v32i1.11491
Ringard J, Seyler F, Linguet L (2017) A quantile mapping bias correction method based on hydroclimatic classification of the Guiana shield. Sensors 17(6):1413. https://doi.org/10.3390/s17061413
Shah HL, Mishra V (2016) Hydrologic changes in Indian subcontinental river basins (1901–2012). J Hydrometeorol 17(10):2667–2687. https://doi.org/10.1175/JHM-D-15-0231.1
Shapley LS (1953) A value for n-person games. Contrib Theory Games 2:307–317
Sridevi C, Singh KK, Suneetha P, Durai VR, Kumar A (2020) Rainfall forecasting skill of GFS model at T1534 and T574 resolution over India during the monsoon season. Meteorol Atmosp Phys 132(1):35–52. https://doi.org/10.1007/s00703-019-00672-x
Sudheer C, Maheswaran R, Panigrahi BK, Mathur S (2014) A hybrid SVM-PSO model for forecasting monthly streamflow. Neural Comput Appl 24(6):1381–1389. https://doi.org/10.1007/s00521-013-1341-y
Switanek MB, Troch PA, Castro CL et al (2017) Scaled distribution mapping: a bias correction method that preserves raw climate model projected changes. Hydrol Earth Syst Sci 21(6):2649–2666. https://doi.org/10.5194/hess-21-2649-2017
Tian Y, Peters-Lidard CD, Eylander JB (2010) Real-time bias reduction for satellite-based precipitation estimates. J Hydrometeorol 11(6):1275–1285. https://doi.org/10.1175/2010JHM1246.1
Tiwari AD, Mukhopadhyay P, Mishra V (2021) Influence of bias correction of meteorological and streamflow forecast on hydrological prediction in India. J Hydrometeorol 23(7):1171–1192. https://doi.org/10.1175/JHM-D-20-0235.1
Vapnik V (1995) The nature of statistical learning theory. Springer, New York
Wood AW, Leung LR, Sridhar V, Lettenmaier DP (2004) Downscaling climate model surface precipitation and temperature: a comparison of methods. Clim Change 62:189–216. https://doi.org/10.1023/B:CLIM.0000013685.99609.9e
Zhang JR, Zhang J, Lok TM, Lyu MR (2007) A hybrid particle swarm optimisation–backpropagation algorithm for feedforward neural network training. Appl Math Comput 185(2):1026–1037. https://doi.org/10.1016/j.amc.2006.07.025
Zhu S, Luo X, Yuan X, Xu Z (2020) An improved long short-term memory network for streamflow forecasting in the upper Yangtze River. Stoch Environ Res Risk Assess 34(9):1313–1329. https://doi.org/10.1007/s00477-020-01766-4
Funding
The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by KS, AM, and RS. The first draft of the manuscript was written by KS and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sushanth, K., Mishra, A., Mukhopadhyay, P. et al. Near-real-time forecasting of reservoir inflows using explainable machine learning and short-term weather forecasts. Stoch Environ Res Risk Assess 37, 3945–3965 (2023). https://doi.org/10.1007/s00477-023-02489-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-023-02489-y