Comparison of Deep Learning Models in Predicting Water Deficits in Semi-Arid Regions: A Case Study of Dodoma, Tanzania
Abstract
The escalating global freshwater shortage is driven by socio-economic development, changing consumption patterns, and systemic inefficiencies, with semi-arid regions like Dodoma, Tanzania, being especially vulnerable. Traditional statistical and regression-based models for predicting water deficits have proven insufficient in capturing the complex, nonlinear interactions among climatic, hydrological, and anthropogenic factors. To address this gap, this study proposes a deep learning-based predictive framework utilising advanced algorithms, Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Deep Neural Networks (DNN) to improve the forecasting of water deficits. Using a thirteen-year (13) dataset collected from the semi-arid climate region of Dodoma, encompassing meteorological, hydrological, and socioeconomic variables. The models were trained and evaluated using performance metrics such as Root Mean Square Error (RMSE) and R-squared (R²). The DNN model demonstrated superior performance with an RMSE of 0.049 and an R² of 1.000, significantly outperforming other models. LSTM, CNN, and RNN models showed moderate to weak predictive accuracy, particularly in handling long-term dependencies and extreme deficit events. The key finding of this study is that the DNN model provides highly reliable and accurate water deficit predictions, making it the most effective among the tested deep learning approaches. This result highlights the value of incorporating deep learning into water resource planning, especially in data-scarce, semi-arid regions. The study concludes that DNN-based models should be prioritised for operational deployment in early warning systems and decision-making platforms. Future work should explore hybrid architectures, hyperparameter tuning, and integration with real-time data sources to enhance robustness and applicability
Downloads
References
Aljanabi, Q. A., Chik, Z., Allawi, M. F., El-Shafie, A., & Ahmed, A. N. (2017). Support vector regression-based model prediction of behavior stone column parameters in soft clay under highway embankment. Neural Computing and Applications, 28(Suppl 1), 67–77. https://doi.org/10.1007/s00521-016-2329-1
Allawi, M. F., Jaafar, O., Mohamad Hamzah, F., & El-Shafie, A. (2018). Operating a reservoir system based on the shark machine learning algorithm. Environmental Earth Sciences, 77(9), 366. https://doi.org/10.1007/s12665-018-7547-7
Bai, Y., Sun, Z., Zeng, B., Long, J., Li, C., Zhang, J., & Li, W. (2018). Reservoir inflow forecast using a clustered random deep fusion approach in the Three Gorges Reservoir, China. Journal of Hydrologic Engineering, 23(9), 04018041. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001683
Baldini, M., Trivella, A., & Wente, J. W. (2018). The impact of socioeconomic and behavioural factors for purchasing energy efficient household appliances: A case study for Denmark. Energy Policy, 120, 503– 513. https://doi.org/10.1016/j.enpol.2018.05.057
Cardoso, R. B., Nogueira, L. A. H., & Haddad, J. (2010). Economic feasibility for acquisition of efficient refrigerators in Brazil. Applied Energy, 87(1), 28– 37. https://doi.org/10.1016/j.apenergy.2009.07.004
Chen, L., Yan, H., Yan, J., Wang, J., Tao, T., Xin, K., & Qiu, J. (2022). Short-term water demand forecast based on automatic feature extraction by one-dimensional convolution. Journal of Hydrology, 606, 127440. https://doi.org/10.1016/j.jhydrol.2021.127440
Chunekar, A. (2014). Standards and Labeling program for refrigerators: Comparing India with others. Energy Policy, 65, 626–630. https://doi.org/10.1016/j.enpol.2013.09.058
Cialani, C., & Perman, K. (2022). Policy instruments to improve energy efficiency in buildings. DIVA. https://www.diva- portal.org/smash/get/diva2:789450/FULLTEXT01.pdf
City Population. (2023). Tanzania: Regions and cities. https://www.citypopulation.de/en/tanzania/cities/
Damigos, D., Kontogianni, A., Tourkolias, C., & Skourtos, M. (2020). Behind the scenes: Why are energy efficient home appliances such a hard sell? Resources, Conservation and Recycling, 158, 104761. https://doi.org/10.1016/j.resconrec.2020.104761
de Souza Groppo, G., Costa, M. A., & Libânio, M. (2019). Predicting water demand: A review of the methods employed and future possibilities. Water Science & Technology: Water Supply, 19(8), 2179–2198. https://doi.org/10.2166/ws.2019.122
Dikshit, A., Pradhan, B., & Huete, A. (2021). An improved SPEI drought forecasting approach using the long short-term memory neural network. Journal of Environmental Management, 283, 111979. https://doi.org/10.1016/j.jenvman.2021.111979
Environmental and Energy Study Institute. (2017). Fact sheet: Energy efficiency standards for appliances, lighting and equipment. https://www.eesi.org/papers/view/fact-sheet-energy-efficiency-standards-for-appliances-lighting-and-equipment
Fang, Z., Wang, Y., Peng, L., & Hong, H. (2021). Predicting flood susceptibility using LSTM neural networks. Journal of Hydrology, 594, 125734. https://doi.org/10.1016/j.jhydrol.2021.125734
Gil-Alana, L. A., Mudiba, R., & Zerbo, E. (2021). GDP per capita in Sub-Saharan Africa: A time series approach using long memory. International Review of Economics & Finance, 72, 175– 190. https://doi.org/10.1016/j.iref.2020.11.006
Gude, V., Corns, S., & Long, S. (2020). Flood prediction and uncertainty estimation using deep learning. Water, 12(3), 884. https://doi.org/10.3390/w12030884
Guo, F., Pachauri, S., & Cofala, J. (2017). Cost-effective subsidy incentives for room air conditioners in China: An analysis based on a McFadden-type discrete choice model. Energy Policy, 110, 375– 385. https://doi.org/10.1016/j.enpol.2017.08.029
Guo, S., Yan, D., Hu, S., & Zhang, Y. (2021). Modelling building energy consumption in China under different future scenarios. Energy, 214, 119063. https://doi.org/10.1016/j.energy.2020.119063
Herbert, Z. C., Asghar, Z., & Oroza, C. (2021). Long-term reservoir inflow forecasts: Enhanced water supply and inflow volume accuracy using deep learning. Journal of Hydrology, 601, 126676. https://doi.org/10.1016/j.jhydrol.2021.126676
Hosseini, S. H., Tsolakis, A., Alagumalai, A., Mahian, O., Lam, S. S., Pan, J., Peng, W., Tabatabaei, M., & Aghbashlo, M. (2023). Use of hydrogen in dual-fuel diesel engines. Progress in Energy and Combustion Science, 98, 101100. https://doi.org/10.1016/j.pecs.2023.101100
Hu, R., Fang, F., Pain, C. C., & Navon, I. M. (2019). Rapid spatio-temporal flood prediction and uncertainty quantification using a deep learning method. Journal of Hydrology, 575, 911–920. https://doi.org/10.1016/j.jhydrol.2019.05.087
International Energy Agency. (2023). Boosting efficiency: Delivering affordability, security and jobs in Latin America. https://iea.blob.core.windows.net/assets/c8972f43-55af-4368-83a6-865f2d17b461/Boostingefficiency_DeliveringaffordabilitysecurityandjobsinLatinAmerica.pdf
Kavya, M., Mathew, A., Shekar, R. P., & Sarwesh, P. (2023). Short term water demand forecast modelling using artificial intelligence for smart water management. Sustainable Cities and Society, 95, 104610. https://doi.org/10.1016/j.scs.2023.104610
Kim, D., Choi, S., Kang, S., & Noh, H. (2023). A study on developing an AI-based water demand prediction and classification model for Gurye Intake Station. Water, 15(23), 4160. https://doi.org/10.3390/w15234160
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Lin, C. C., Liou, K. Y., Lee, M., & Chiueh, P. T. (2019). Impacts of urban water consumption under climate change: An adaptation measure of rainwater harvesting system. Journal of Hydrology, 572, 160– 168. https://doi.org/10.1016/j.jhydrol.2019.02.053
Maity, R., Khan, M. I., Sarkar, S., Dutta, R., Maity, S. S., Pal, M., & Chanda, K. (2021). Potential of deep learning in drought prediction over different agroclimatic zones. In book: Advances in Streamflow Forecasting (pp. 415-439). Elsevier. https://doi.org/10.1016/B978-0-12-820673-7.00016-9
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in neural information processing systems 26 (pp. 3111–3119). Curran Associates, Inc.
Sahoo, S., Agarwal, A., & Sahoo, P. (2019). Water end-use estimation can support the urban water crisis management: A critical review. Environmental Science and Pollution Research, 26(7), 6934– 6948. https://doi.org/10.1007/s11356-019-04191-5
Sajadifar, S., & Marjan, N. (2024). A probabilistic Markov chain model for short-term water demand forecasting. Journal of Water Resources Planning and Management, 150(3), 04023092. https://doi.org/10.1061/JWRMD5.WRENG-5982
Shuang, Q., & Zhao, R. T. (2021). Water demand prediction using machine learning methods: A case study of the Beijing–Tianjin–Hebei region in China. Water, 13(3), 310. https://doi.org/10.3390/w13030310
Tran, V. N., Ivanov, V. Y., Nguyen, G. T., & Anh, T. N. (2024). A deep learning modeling framework with uncertainty quantification for inflow-outflow predictions for cascade reservoirs. Journal of Hydrology, 632, 130899. https://doi.org/10.1016/j.jhydrol.2024.130899
Xu, S., Chen, Y., Xing, L., & Li, C. (2021). Baipenzhu Reservoir inflow flood forecasting based on a distributed hydrological model. Water, 13(3), 272. https://doi.org/10.3390/w13030272
Yan, X., Zhang, T., Du, W., Meng, Q., Xu, X., & Zhao, X. (2024). A comprehensive review of machine learning for water quality prediction over the past five years. Journal of Marine Science and Engineering, 12(2), 324. https://doi.org/10.3390/jmse12020324
Yaseen, Z. M., Kisi, O., & Demir, V. (2016). Enhancing long-term streamflow forecasting and predicting using periodicity data component: Application of artificial intelligence. Water Resources Management, 30(12), 4125– 4151. https://doi.org/10.1007/s11269-016-1408-5
Zounemat-Kermani, M., Batelaan, O., Fadaee, M., & Hinkelmann, R. (2021). Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 598, 126266. https://doi.org/10.1016/j.jhydrol.2021.126266
Zucchinelli, M., Bianchi, M., Martini, F., & Daddi, T. (2021). Effects of different Danish food consumption patterns on Water Scarcity Footprint. Sustainability, 13(9), 4847. https://doi.org/10.3390/su13094847
Copyright (c) 2025 Nyamgambwa Sabi James, Othmar Othmar Mwambe, Gustaph Sanga, Eliphas Tongora
This work is licensed under a Creative Commons Attribution 4.0 International License.
