A Deep-Learning based Monthly Precipitation Forecasting with Implications for Urban Design and Water Management
DOI:
https://doi.org/10.15377/2409-9821.2025.12.15Keywords:
Deep learning, Precipitation forecasting, Urban water management, Climate-responsive design, Entropy-based wavelet decomposition.Abstract
Accurate precipitation forecasting is essential for disaster preparedness and climate-responsive urban planning such as drainage designing under increasing climatic variability. This study investigates an entropy-guided deep learning framework to improve monthly precipitation forecasting by integrating the Maximal Overlap Discrete Wavelet Entropy Transform (MODWET) with a Gated Recurrent Unit (GRU) model. Unlike the conventional Maximal Overlap Discrete Wavelet Transform (MODWT), MODWET employs entropy to objectively determine the optimal wavelet filter and decomposition level, addressing a key limitation in wavelet-based preprocessing related to over- or under-decomposition of hydroclimatic signals. While the effectiveness of MODWET has previously been demonstrated for streamflow forecasting, its application to precipitation prediction has not yet been explored. The proposed framework is evaluated using monthly precipitation data from three hydrometeorological case studies close to urbane are, selected from the CAMELS dataset across the United States. Model performance is assessed using multiple statistical metrics, including NSE, RMSE, percent bias (PBIAS), and correlation coefficient (r2). In addition, the Partial Correlation Index (PCI) is employed to identify informative predictors and reduce input redundancy. Results show that the hybrid PCI–MODWET–GRU model consistently outperforms the standalone GRU model, achieving improved correlation (up to r2 = 0.78 at selected stations) and overall predictive accuracy. These findings highlight the potential of combining entropy-based wavelet preprocessing with deep learning models to enhance precipitation forecasting reliability, with direct relevance for urban and peri-urban water management and climate-responsive design applications.
Downloads
References
[1] Agonafir C, Lakhankar T, Khanbilvardi R, Krakauer N, Radell D, Devineni N. A review of recent advances in urban flood research. Water Secur. 2023; 19: 100141. https://doi.org/10.1016/j.wasec.2023.100141
[2] Fletcher TD, Shuster W, Hunt WF, Ashley R, Butler D, Arthur S, et al. SUDS, LID, BMPs, WSUD and more – The evolution and application of terminology surrounding urban drainage. Urban Water J. 2015; 12(7): 525-42. https://doi.org/10.1080/1573062X.2014.916314
[3] Ma XY, Wang XC. Ecotoxicity comparison of organic contaminants and heavy metals using Vibrio-qinghaiensis sp.-Q67. Water Sci Technol. 2013; 67(10): 2221-7. https://doi.org/10.2166/wst.2013.113
[4] Jha AK, Bloch R, Lamond J. Cities and flooding: a guide to integrated urban flood risk management for the 21st century. Washington, DC: World Bank; 2012. https://doi.org/10.1596/978-0-8213-8866-2
[5] Milly PCD, Betancourt J, Falkenmark M, Hirsch RM, Kundzewicz ZW, Lettenmaier DP, et al. Stationarity is dead: whither water management? Science. 2008; 319(5863): 573-4. https://doi.org/10.1126/science.1151915
[6] Meerow S, Newell JP, Stults M. Defining urban resilience: A review. Landsc Urban Plan. 2016; 147: 38-49. https://doi.org/10.1016/j.landurbplan.2015.11.011
[7] Emmanuel R, Loconsole A. Green infrastructure as an adaptation approach to tackling urban overheating in the Glasgow Clyde Valley Region, UK. Landsc Urban Plan. 2015; 138: 71-86. https://doi.org/10.1016/j.landurbplan.2015.02.012
[8] Kinnane O, Sinnott D, Turner WJN. Evaluation of passive ventilation provision in domestic housing retrofit. Build Environ. 2016; 106: 205-18. https://doi.org/10.1016/j.buildenv.2016.06.032
[9] Wong THF, Brown RR. The water sensitive city: principles for practice. Water Sci Technol. 2009; 60(3): 673-82. https://doi.org/10.2166/wst.2009.436
[10] Campbell T. Learning cities: Knowledge, capacity and competitiveness. Habitat Int. 2009; 33(2): 195-201. https://doi.org/10.1016/j.habitatint.2008.10.012
[11] Ortiz J, Fonseca i Casas A, Salom J, Garrido Soriano N, Fonseca i Casas P. Cost-effective analysis for selecting energy efficiency measures for refurbishment of residential buildings in Catalonia. Energy Build. 2016; 128: 442-57. https://doi.org/10.1016/j.enbuild.2016.06.059
[12] Czemiel Berndtsson J. Green roof performance towards management of runoff water quantity and quality: A review. Ecol Eng. 2010; 36(4): 351-60. https://doi.org/10.1016/j.ecoleng.2009.12.014
[13] Zhou Q. A review of sustainable urban drainage systems considering the climate change and urbanization impacts. Water. 2014; 6(4): 976-92. https://doi.org/10.3390/w6040976
[14] Meerow S, Newell JP. Spatial planning for multifunctional green infrastructure: Growing resilience in Detroit. Landsc Urban Plan. 2017; 159: 62-75. https://doi.org/10.1016/j.landurbplan.2016.10.005
[15] Santana MV, Zhang Q, Nachabe MH, Xie X, Mihelcic JR. Could smart growth lower the operational energy of water supply? A scenario analysis in Tampa, Florida, USA. Landsc Urban Plan. 2017; 164: 99-108. https://doi.org/10.1016/j.landurbplan.2017.04.010
[16] Geneletti D, Zardo L. Ecosystem-based adaptation in cities: An analysis of European urban climate adaptation plans. Land Use Policy. 2016; 50: 38-47. https://doi.org/10.1016/j.landusepol.2015.09.003
[17] Ahiablame LM, Engel BA, Chaubey I. Effectiveness of Low Impact Development Practices: Literature Review and Suggestions for Future Research. Water Air Soil Pollut. 2012; 223(7): 4253-73. https://doi.org/10.1007/s11270-012-1189-2
[18] Demuzere M, Orru K, Heidrich O, Olazabal E, Geneletti D, Orru H, et al. Mitigating and adapting to climate change: Multi-functional and multi-scale assessment of green urban infrastructure. J Environ Manage. 2014; 146: 107-15. https://doi.org/10.1016/j.jenvman.2014.07.025
[19] Hathaway JM, Bean EZ, Bernagros JT, Christian DP, Davani H, Ebrahimian A, et al. A synthesis of climate change impacts on stormwater management systems: designing for resiliency and future challenges. J Sustain Water Built Environ. 2024; 10(2): 04023014. https://doi.org/10.1061/JSWBAY.SWENG-533
[20] Zellner ML, Massey D. Modeling benefits and tradeoffs of green infrastructure: Evaluating and extending parsimonious models for neighborhood stormwater planning. Heliyon. 2024; 10(5): e27007. https://doi.org/10.1016/j.heliyon.2024.e27007
[21] Nodine TG, Conley G, Riihimaki CA, Holland C, Beck NG. Modeling the impact of future rainfall changes on the effectiveness of urban stormwater control measures. Sci Rep. 2024; 14(1): 4082. https://doi.org/10.1038/s41598-024-53611-1
[22] Meema T, Tachikawa Y, Ichikawa Y, Yorozu K. Real-time optimization of a large-scale reservoir operation in Thailand using adaptive inflow prediction with medium-range ensemble precipitation forecasts. J Hydrol Reg Stud. 2021; 38: 100939. https://doi.org/10.1016/j.ejrh.2021.100939
[23] Specifications and Accuracy of Rainfall Forecast Required for Pre-Release at Multi-Purpose Reservoirs in Japan. (cited 2026 Jan 9). https://doi.org/10.3390/w15071277
[24] Ferdowsi A, Piadeh F, Behzadian K, Mousavi SF, Ehteram M. Urban water infrastructure: A critical review on climate change impacts and adaptation strategies. Urban Clim. 2024; 58: 102132. https://doi.org/10.1016/j.uclim.2024.102132
[25] Dharmarathne G, Waduge AO, Bogahawaththa M, Rathnayake U, Meddage DPP. Adapting cities to the surge: A comprehensive review of climate-induced urban flooding. Results Eng. 2024; 22: 102123. https://doi.org/10.1016/j.rineng.2024.102123
[26] Akinsanola AA, Singhai P, Taguela TN, Folorunsho AH, Adeyeri OE, Morakinyo TE, et al. A review of urban resilience to weather and climate extremes. City Built Environ. 2025; 3(1): 24. https://doi.org/10.1007/s44213-025-00063-6
[27] Cuo L, Pagano TC, Wang QJ. A Review of Quantitative Precipitation Forecasts and Their Use in Short- to Medium-Range Streamflow Forecasting. J Hydrometeorol. 2011; 12(5): 713-28. https://doi.org/10.1175/2011JHM1347.1
[28] Briggs MA, Gazoorian CL, Doctor DH, Burns DA. A multiscale approach for monitoring groundwater discharge to headwater streams by the U.S. Geological Survey Next Generation Water Observing System Program—An example from the Neversink Reservoir watershed, New York. Fact Sheet. U.S. Geological Survey; 2022 (cited 2024 Dec 5). Report No.: 2022-3077. https://doi.org/10.3133/fs20223077
[29] Cheung KKW. Bridging the Scaling Gap: A Review of Nonlinear Paradigms for the Estimation and Understanding of Extreme Rainfall from Heavy Storms. Fractal Fract. 2025; 9(12): 827. https://doi.org/10.3390/fractalfract9120827
[30] Koltermann da Silva J, Burrichter B, Niemann A, Quirmbach M. A systematic modular approach for the coupling of deep-learning-based models to forecast urban flooding maps in early warning systems. Hydrology. 2024; 11(12): 215. https://doi.org/10.3390/hydrology11120215
[31] Sham FAF, El-Shafie A, Jaafar WZBW, Adarsh S, Sherif M, Ahmed AN. Improving rainfall forecasting using deep learning data fusing model approach for observed and climate change data. Sci Rep. 2025; 15(1): 27872. https://doi.org/10.1038/s41598-025-13567-2
[32] Zhao X, Wang H, Bai M, Xu Y, Dong S, Rao H, et al. A comprehensive review of methods for hydrological forecasting based on deep learning. Water. 2024; 16(10): 1407. https://doi.org/10.3390/w16101407
[33] Chuasuk P, Bhatrasataponkul T, Akkarapongtrakul A. Comparative analysis and enhancing rainfall prediction models for monthly rainfall prediction in the Eastern Thailand. MethodsX. 2025; 14: 103094. https://doi.org/10.1016/j.mex.2024.103094
[34] Sit M, Demiray BZ, Xiang Z, Ewing GJ, Sermet Y, Demir I. A comprehensive review of deep learning applications in hydrology and water resources. Water Sci Technol. 2020; 82(12): 2635-70. https://doi.org/10.2166/wst.2020.369
[35] Behbahani MRM, Rey DM, Briggs MA, Bagtzoglou AC. A spatiotemporal deep learning approach for predicting daily air-water temperature signal coupling and identification of key watershed physical parameters in a montane watershed. J Hydrol. 2025; 663: 134139. https://doi.org/10.1016/j.jhydrol.2025.134139
[36] Gao S, Huang Y, Zhang S, Han J, Wang G, Zhang M, et al. Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. J Hydrol. 2020; 589: 125188. https://doi.org/10.1016/j.jhydrol.2020.125188
[37] Łępicki M, Latkowski T, Antoniuk I, Bukowski M, Świderski B, Baranik G, et al. Comparative Evaluation of Sequential Neural Network (GRU, LSTM, Transformer) Within Siamese Networks for Enhanced Job–Candidate Matching in Applied Recruitment Systems. Appl Sci. 2025; 15(11): 5988. https://doi.org/10.3390/app15115988
[38] Shi T, Shide K. A comparative analysis of LSTM, GRU, and Transformer models for construction cost prediction with multidimensional feature integration. J Asian Archit Build Eng. 2026; 25(1): 634-49. https://doi.org/10.1080/13467581.2025.2455034
[39] Guo T, Zhang T, Lim E, López-Benítez M, Ma F, Yu L. A Review of Wavelet Analysis and Its Applications: Challenges and Opportunities. IEEE Access. 2022; 10: 58869-903. https://doi.org/10.1109/ACCESS.2022.3179517
[40] Xie J, Chen W, Dai H. Distributed cooperative learning algorithms using wavelet neural network. Neural Comput Appl. 2019; 31(4): 1007-21. https://doi.org/10.1007/s00521-017-3134-1
[41] Abda Z, Zerouali B, Chettih M, Guimarães Santos CA, de Farias CAS, Elbeltagi A. Assessing machine learning models for streamflow estimation: a case study in Oued Sebaou watershed (Northern Algeria). Hydrol Sci J. 2022; 67(9): 1328-41. https://doi.org/10.1080/02626667.2022.2083511
[42] Quilty J, Adamowski J. Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework. J Hydrol. 2018; 563: 336-53. https://doi.org/10.1016/j.jhydrol.2018.05.003
[43] Xia YX, Xu RK, Ni YQ, Jin ZQ. Strain signal denoising in bridge SHM: A comparative analysis of MODWT and other techniques. J Infrastruct Intell Resil. 2025; 4(3): 100155. https://doi.org/10.1016/j.iintel.2025.100155
[44] Varghese PR, Subathra MSP, Peter G, Stonier AA, Kuppusamy R, Teekaraman Y. A novel MODWT–local pattern transformation feature fusion approach for high-impedance fault detection in medium voltage power distribution networks. Neural Comput Appl. 2025; 37(22): 17457-71. https://doi.org/10.1007/s00521-024-10863-2
[45] Tahi M, Miloudi A. Rotating machinery faults classification by MODWT and the SVM distribution generated by the genetic wrapper. Aust J Electr Electron Eng. 2025; 1-14. https://doi.org/10.1080/1448837X.2025.2528473
[46] Behbahani MRM, Mazarei M, Bagtzoglou AC. Improving deep learning-based streamflow forecasting under trend varying conditions through evaluation of new wavelet preprocessing technique. Stoch Environ Res Risk Assess. 2024; 38(10): 3963-84. https://doi.org/10.1007/s00477-024-02788-y
[47] Mazarei Behbahani MR, Mazarei A. A new criteria for determining the best decomposition level and filter for wavelet-based data-driven forecasting frameworks- validating using three case studies on the CAMELS dataset. Stoch Environ Res Risk Assess. 2023; 37(12): 4827-42. https://doi.org/10.1007/s00477-023-02531-z
[48] Coifman RR, Wickerhauser MV. Entropy-based algorithms for best basis selection. IEEE Trans Inf Theory. 1992; 38(2): 713-8. https://doi.org/10.1109/18.119732
[49] Rosso OA, Larrondo HA, Martin MT, Plastino A, Fuentes MA. Distinguishing noise from chaos. Phys Rev Lett. 2007; 99(15): 154102. https://doi.org/10.1103/PhysRevLett.99.154102
[50] Wang GJ, Xie C, Stanley HE. Correlation structure and evolution of world stock markets: evidence from pearson and partial correlation-based networks. Comput Econ. 2018; 51(3): 607-35. https://doi.org/10.1007/s10614-016-9627-7
[51] Addor N, Newman AJ, Mizukami N, Clark MP. The CAMELS data set: catchment attributes and meteorology for large-sample studies. Hydrol Earth Syst Sci. 2017; 21(10): 5293-313. https://doi.org/10.5194/hess-21-5293-2017
[52] Kiparsky M, Joyce B, Purkey D, Young C. Potential Impacts of Climate Warming on Water Supply Reliability in the Tuolumne and Merced River Basins, California. PLOS One. 2014; 9(1): e84946. https://doi.org/10.1371/journal.pone.0084946
[53] Fassnacht SR, Records RM. Large snowmelt versus rainfall events in the mountains. J Geophys Res Atmospheres. 2015; 120(6): 2375-81. https://doi.org/10.1002/2014JD022753
[54] Lombard PJ. Flood of April and May 2008 in Northern Maine. Scientific Investigations Report. U.S. Geological Survey; 2010 (cited 2026 Jan 11). Report No.: 2010-5003. Available from: https://pubs.usgs.gov/publication/sir20105003
[55] Monthly Climate/Ocean Indices (Time-Series): NOAA Physical Sciences Laboratory. (cited 2026 Jan 10). Available from: https://psl.noaa.gov/data/timeseries/month/
[56] Nilsson P, Uvo CB, Berndtsson R. Monthly runoff simulation: Comparing and combining conceptual and neural network models. J Hydrol. 2006; 321(1): 344-63. https://doi.org/10.1016/j.jhydrol.2005.08.007
[57] Espeholt L, Agrawal S, Sønderby C, Kumar M, Heek J, Bromberg C, et al. Deep learning for twelve hour precipitation forecasts. Nat Commun. 2022; 13(1): 5145. https://doi.org/10.1038/s41467-022-32483-x
[58] Salem FM. Gated RNN: The Gated Recurrent Unit (GRU) RNN. In: Salem FM, Ed. Recurrent Neural Networks: From Simple to Gated Architectures. Cham: Springer International Publishing; 2022 [cited 2026 Jan 10]. p. 85-100. https://doi.org/10.1007/978-3-030-89929-5_5
[59] Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J. LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst. 2017; 28(10): 2222-32. https://doi.org/10.1109/TNNLS.2016.2582924
[60] Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw. 1994; 5(2): 157-66. https://doi.org/10.1109/72.279181
[61] Eskov VM, Eskov VV, Vochmina YuV, Gorbunov DV, Ilyashenko LK. Shannon entropy in the research on stationary regimes and the evolution of complexity. Mosc Univ Phys Bull. 2017; 72(3): 309-17. https://doi.org/10.3103/S0027134917030067
[62] Kim TK. T test as a parametric statistic. Korean J Anesthesiol. 2015; 68(6): 540-6. https://doi.org/10.4097/kjae.2015.68.6.540
[63] Fang W, Ren K, Liu T, Shang J, Jia S, Jiang X, et al. An evaluation of random forest based input variable selection methods for one month ahead streamflow forecasting. Sci Rep. 2024; 14(1): 29766. https://doi.org/10.1038/s41598-024-81502-y
[64] Ren K, Fang W, Qu J, Zhang X, Shi X. Comparison of eight filter-based feature selection methods for monthly streamflow forecasting – Three case studies on CAMELS data sets. J Hydrol. 2020; 586: 124897. https://doi.org/10.1016/j.jhydrol.2020.124897
[65] Fish River at Fort Kent. Last updated: Feb 9, 2026. Available from: https://water.noaa.gov/gauges/01013500?utm
[66] Menoni S. Urban Planning for Disaster Risk Reduction and Climate Change Adaptation: A Review at the Crossroads of Research and Practice. Sustainability. 2025; 17(20): 9092. https://doi.org/10.3390/su17209092
[67] Harrs JA, Reinhart V, Vögt V, Scheib JPP, Tewes T, Pohl T, et al. Integration of climate information into urban climate change adaptation: A case study of municipal processes in Constance. Clim Serv. 2024; 35: 100495. https://doi.org/10.1016/j.cliser.2024.100495
[68] Sharifi A, Yamagata Y. Principles and criteria for assessing urban energy resilience: A literature review. Renew Sustain Energy Rev. 2016; 60: 1654-77. https://doi.org/10.1016/j.rser.2016.03.028
[69] Fernandes P, Tomás R, Acuto F, Pascale A, Bahmankhah B, Guarnaccia C, et al. Impacts of roundabouts in suburban areas on congestion-specific vehicle speed profiles, pollutant and noise emissions: An empirical analysis. Sustain Cities Soc. 2020; 62: 102386. https://doi.org/10.1016/j.scs.2020.102386
[70] Gray M, Wilmers CC, Reed SE, Merenlender AM. Landscape feature-based permeability models relate to puma occurrence. Landsc Urban Plan. 2016; 147: 50-8. https://doi.org/10.1016/j.landurbplan.2015.11.009
[71] Akan AO, Houghtalen RJ. Urban hydrology, hydraulics, and stormwater quality engineering applications and computer modeling. WILEY; 2003.
[72] Chow VT. Applied Hydrology. Int Assoc Sci Hydrol Bull. 1965; 10(1): 82-3. https://doi.org/10.1080/02626666509493376
Downloads
Published
License
Copyright (c) 2025 Mohammad R.M. Behbahani, Javad Teymoori
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All the published articles are licensed under the terms of the Creative Commons Attribution Non-Commercial License (CC BY-NC 4.0) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
