A Residual-Based Hybrid BiLSTM–XGBoost Model for Multivariate Dam Fill Rate Forecasting: The Case of Istanbul
Abstract
Global climate change and increasing water demand pose serious challenges for sustainable water resource management, particularly in large metropolitan areas such as Istanbul. Accurate forecasting of dam fill rates is therefore critical for proactive water management and drought mitigation strategies. In this study, we propose a Residual-Based Hybrid BiLSTM–XGBoost (RBH-BiLSTM-XGB) model to forecast dam fill rates using multivariate time series data, including daily precipitation, water consumption, and historical reservoir levels obtained from the Istanbul Metropolitan Municipality Open Data Portal. The proposed approach combines the temporal dependency learning capability of Bidirectional Long Short-Term Memory (BiLSTM) networks with the residual error modeling strength of XGBoost, enabling the correction of systematic prediction errors produced by deep learning models. The proposed hybrid model is evaluated against standalone LSTM, BiLSTM, XGBoost, and Prophet models under different training–testing split scenarios (70–30%, 80–20%, and 90–10%). Model performance is assessed using RMSE, MAE, MAPE, and R² metrics. Experimental results demonstrate that the RBH-BiLSTM-XGB model consistently outperforms all benchmark models, achieving the lowest RMSE (0.0059), MAPE (0.66–0.86%), and the highest explanatory power (R² ≈ 0.9994). While deep learning models effectively capture long-term temporal dependencies, tree-based models such as XGBoost are shown to be effective in learning residual structures that deep networks fail to model. In contrast, the Prophet model exhibits poor performance due to its additive structure and limited capacity to represent complex multivariate interactions. The findings highlight the effectiveness of residual-based hybrid modeling for dam fill rate forecasting and demonstrate the potential of integrating deep learning and ensemble learning approaches to support data-driven and sustainable water resource management.
Keywords
Deep Learning, Sustainable water management, Time series models
Supporting Institution
This research received no external funding.
Ethical Statement
This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.
Thanks
The author do not wish to acknowledge any individual or institution.
References
- Brownlee, J. (2017). Machine learning mastery with XGBoost and Scikit-Learn. Machine Learning Mastery.
- Bulut, M. (2021). Hydroelectric generation forecasting with long short term memory (LSTM) based deep learning model for Turkey. arXiv. https://doi.org/10.48550/arXiv.2109.09013
- Canlı, H., & Toklu, S. (2021). Deep learning-based mobile application design for smart parking. IEEE Access, 9, 61171–61183. https://doi.org/10.1109/ACCESS.2021.3074887
- Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
- Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785
- EarlyStopping. (n.d.). Keras. https://keras.io/api/callbacks/early_stopping/
- Er, E. E., Üneş, F., & Taşar, B. (2022). Estimating dam reservoir level change of Istanbul Alibey Dam with the fuzzy SMRGT method. Osmaniye Korkut Ata University Journal of the Institute of Science and Technology, 5(Özel Sayı), 80-95. https://doi.org/10.47495/okufbed.1033693
- Facebook. (2017). Prophet: Forecasting at scale. https://facebook.github.io/prophet/
- Fan, D., Sun, H., Yao, J., Zhang, K., Yan, X., & Sun, Z. (2021). Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy, 220, Article 119708. https://doi.org/10.1016/j.energy.2020.119708
- Fu, R., Zhang, Z., & Li, L. (2016). Using LSTM and GRU neural network methods for traffic flow prediction. In Proceedings of the 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), Wuhan, China (pp. 324–328). IEEE. https://doi.org/10.1109/YAC.2016.7804912 Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18(5–6), 602–610. https://doi.org/10.1016/j.neunet.2005.06.042