An Adaptive Grey Wolf Optimized Bidirectional LSTM Framework for Flood Risk-Oriented Rainfall Forecasting in Tropical Climate Systems

Yuslena Sari; Nurul Fathanah Mustamin; Ahmad Rusyadi; Firman Aziz

doi:10.48084/etasr.18161

Authors

Yuslena Sari Department of Information Technology, Universitas Lambung Mangkurat, Banjarmasin, Indonesia
Nurul Fathanah Mustamin Department of Information Technology, Universitas Lambung Mangkurat, Banjarmasin, Indonesia
Ahmad Rusyadi Department of Information Technology, Universitas Lambung Mangkurat, Banjarmasin, Indonesia
Firman Aziz Computer Science Department, Universitas Pancasakti, Makassar, Indonesia

Volume: 16 | Issue: 3 | Pages: 35802-35810 | June 2026 | https://doi.org/10.48084/etasr.18161

Received: 13 February 2026 | Revised: 7 April 2026 | Accepted: 17 April 2026 | Online: 6 June 2026

Corresponding author: Yuslena Sari

Abstract

This study presents a flood-oriented rainfall forecasting framework that integrates Bidirectional Long Short-Term Memory (BiLSTM) with Grey Wolf Optimizer (GWO) and Shapley Additive Explanations (SHAP)-based interpretability. The proposed approach addresses two key limitations in existing Deep Learning (DL) rainfall models: suboptimal hyperparameter selection and limited model transparency. GWO is employed to optimize network hyperparameters in a stability-aware manner, enhancing convergence behavior and reducing generalization variance. To mitigate the black-box nature of recurrent networks, SHAP analysis is incorporated to quantify feature contributions and ensure physically consistent interpretation of rainfall drivers. Experimental results demonstrate that the optimized GWO–BiLSTM model achieves superior predictive accuracy (R² = 0.912) compared to Gated Recurrent Unit (GRU) and non-optimized BiLSTM baselines. In addition to improved regression performance, the model exhibits enhanced sensitivity to extreme rainfall events, reflected by higher recall and lower false negative rates, which are essential for flood early-warning applications. Comparative analysis with recent international studies indicates that the proposed framework uniquely combines metaheuristic optimization, extreme-event evaluation, statistical validation, and explainable modeling within a unified engineering architecture. The results confirm that integrating optimization robustness and interpretable DL significantly strengthens the operational reliability of rainfall prediction systems for hydrological risk mitigation.

Keywords:

rainfall prediction, flood forecasting, Bidirectional Long Short-Term Memory (BiLSTM), Grey Wolf Optimizer (GWO), extreme event detection

References

M. Li, Y. Yao, Z. Feng, and M. Ou, "Hydrological drought prediction and its influencing features analysis based on a machine learning model," Natural Hazards and Earth System Sciences, vol. 25, no. 11, pp. 4299–4316, Nov. 2025.

V. Kumar et al., "Machine learning applications in flood forecasting and predictions, challenges, and way-out in the perspective of changing environment," AIMS Environmental Science, vol. 12, no. 1, pp. 72–105, Jan. 2025.

H. L. Cloke and F. Pappenberger, "Ensemble flood forecasting: A review," Journal of Hydrology, vol. 375, no. 3, pp. 613–626, Sept. 2009.

L. B. L. Santos et al., "Machine learning-based hydrological models for flash floods: a systematic literature review," Smart Construction and Sustainable Cities, vol. 3, no. 1, Oct. 2025, Art. no. 21.

X. Zhao et al., "A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning," Water, vol. 16, no. 10, May 2024, Art. no. 1407.

M. Cho, C. Kim, K. Jung, and H. Jung, "Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction," Water, vol. 14, no. 14, July 2022, Art. no. 2221.

M. Pan et al., "Water Level Prediction Model Based on GRU and CNN," IEEE Access, vol. 8, pp. 60090–60100, 2020.

H. Yin et al., "Rainfall-runoff modeling using long short-term memory based step-sequence framework," Journal of Hydrology, vol. 610, July 2022, Art. no. 127901.

H. Han, C. Choi, J. Jung, and H. S. Kim, "Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation," Water, vol. 13, no. 4, Feb. 2021, Art. no. 437.

K. Yokoo et al., "Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM," Science of The Total Environment, vol. 802, Jan. 2022, Art. no. 149876.

Y. Wang, Y. Huang, M. Xiao, S. Zhou, B. Xiong, and Z. Jin, "Medium-long-term prediction of water level based on an improved spatio-temporal attention mechanism for long short-term memory networks," Journal of Hydrology, vol. 618, Mar. 2023, Art. no. 129163.

D. Z. Haq et al., "Long Short-Term Memory Algorithm for Rainfall Prediction Based on El-Nino and IOD Data," Procedia Computer Science, vol. 179, pp. 829–837, Jan. 2021.

I. Chamatidis, G. Tzanes, D. Istrati, N. D. Lagaros, and A. Stamou, "Short-Term Forecasting of Rainfall Using Sequentially Deep LSTM Networks: A Case Study on a Semi-Arid Region," Environmental Sciences Proceedings, vol. 26, no. 1, 2023, Art. no. 157.

S. Dong, "Precipitation Prediction Using Long Short-Term Memory Networks: Improving Seasonal Rainfall Forecast Accuracy for Flood and Drought Prevention," in 2024 International Conference on Advances in Electrical Engineering and Computer Applications, Dalian, China, 2024, pp. 345–349.

F. Kratzert, D. Klotz, C. Brenner, K. Schulz, and M. Herrnegger, "Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks," Hydrology and Earth System Sciences, vol. 22, no. 11, pp. 6005–6022, Nov. 2018.

K. Cho et al., "Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation," in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 2014, pp. 1724–1734.

S. N. Makhadmeh et al., "Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review," IEEE Access, vol. 12, pp. 22991–23028, 2024.

K. Meidani, A. Hemmasian, S. Mirjalili, and A. Barati Farimani, "Adaptive grey wolf optimizer," Neural Computing and Applications, vol. 34, no. 10, pp. 7711–7731, May 2022.

A. Molavi and C. A. G. Santos, "Enhancing the Accuracy of Lake Water Level Prediction: A Novel Approach Using Hybrid CNN-GRU-LSTM Models and Meteorological Data," Water Conservation Science and Engineering, vol. 10, no. 2, Aug. 2025, Art. no. 91.

H. D. Nguyen, "Daily streamflow forecasting by machine learning in Tra Khuc river in Vietnam," Vietnam Journal of Earth Sciences, vol. 45, no. 1, pp. 82–97, 2023.

Y. Xu, C. Hu, Q. Wu, Z. Li, S. Jian, and Y. Chen, "Application of temporal convolutional network for flood forecasting," Hydrology Research, vol. 52, no. 6, pp. 1455–1468, Dec. 2021.

H.-W. Wang, G.-F. Lin, C.-T. Hsu, S.-J. Wu, and S. S. Tfwala, "Long-Term Temporal Flood Predictions Made Using Convolutional Neural Networks," Water, vol. 14, no. 24, Dec. 2022, Art. no. 4134.

J. Jiang et al., "Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 3108–3122, 2024.

G. Xu, Y. Shi, X. Sun, and W. Shen, "Internet of Things in Marine Environment Monitoring: A Review," Sensors, vol. 19, no. 7, Apr. 2019, Art. no. 1711.

Y. Liao, Z. Wang, X. Chen, and C. Lai, "Fast simulation and prediction of urban pluvial floods using a deep convolutional neural network model," Journal of Hydrology, vol. 624, Sept. 2023, Art. no. 129945.

K. Xie, P. Liu, J. Zhang, D. Han, G. Wang, and C. Shen, "Physics-guided deep learning for rainfall-runoff modeling by considering extreme events and monotonic relationships," Journal of Hydrology, vol. 603, Dec. 2021, Art. no. 127043.

M. H. Shahani, V. Rezaverdinejad, S. A. Hosseini, and N. Azad, "Assessing climate change impact on river flow extreme events in different climates of Iran using hybrid application of LARS-WG6 and rainfall-runoff modeling of deep learning," Ecohydrology & Hydrobiology, vol. 23, no. 2, pp. 224–239, Apr. 2023.

S. Sarkar, M. I. Khan, and R. Maity, "Deep learning reveals future streamflow characteristics change and climate sensitivity," Journal of Hydrology, vol. 660, Oct. 2025, Art. no. 133457.

B.-J. Li, G.-L. Sun, Y. Liu, W.-C. Wang, and X.-D. Huang, "Monthly Runoff Forecasting Using Variational Mode Decomposition Coupled with Gray Wolf Optimizer-Based Long Short-term Memory Neural Networks," Water Resources Management, vol. 36, no. 6, pp. 2095–2115, Apr. 2022.

H. D. Nguyen et al., "Flood susceptibility mapping using advanced hybrid machine learning and CyGNSS: a case study of Nghe An province, Vietnam," Acta Geophysica, vol. 70, no. 6, pp. 2785–2803, Dec. 2022.

N. Wang, D. Zhang, H. Chang, and H. Li, "Deep learning of subsurface flow via theory-guided neural network," Journal of Hydrology, vol. 584, May 2020, Art. no. 124700.

S. M. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions," in 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 4768–4777.

C. Molnar, G. Casalicchio, and B. Bischl, "Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges," in 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Ghent, Belgium, 2020, pp. 417–431.

M. Du, N. Liu, and X. Hu, "Techniques for interpretable machine learning," Communications of the ACM, vol. 63, no. 1, pp. 68–77, Dec. 2019.

C. Xiao, A. Duan, Y. Tang, B. Tang, Q. Wang, and X. Yang, "Machine learning prediction of summer extreme precipitation days in the middle and lower Yangtze River with SHAP explanation," Atmospheric Research, vol. 330, Jan. 2026, Art. no. 108614.

A. Dikshit and B. Pradhan, "Explainable AI in drought forecasting," Machine Learning with Applications, vol. 6, Dec. 2021, Art. no. 100192.

W. Chu, C. Zhang, H. Li, L. Zhang, D. Shen, and R. Li, "SHAP-powered insights into spatiotemporal effects: Unlocking explainable Bayesian-neural-network urban flood forecasting," International Journal of Applied Earth Observation and Geoinformation, vol. 131, July 2024, Art. no. 103972.

A. Kapoor and R. Chandra, "QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification," Journal of Hydrology, vol. 664, Jan. 2026, Art. no. 134434.

A. N. Mabdeh, R. S. Ajin, S. V. Razavi-Termeh, M. Ahmadlou, and A. Al-Fugara, "Enhancing the Performance of Machine Learning and Deep Learning-Based Flood Susceptibility Models by Integrating Grey Wolf Optimizer (GWO) Algorithm," Remote Sensing, vol. 16, no. 14, July 2024, Art. no. 2595.

Z. Cai, S. Dai, Q. Ding, J. Zhang, D. Xu, and Y. Li, "Gray wolf optimization-based wind power load mid-long term forecasting algorithm," Computers and Electrical Engineering, vol. 109, Aug. 2023, Art. no. 108769.

S. M. Lundberg et al., "Explainable machine-learning predictions for the prevention of hypoxaemia during surgery," Nature Biomedical Engineering, vol. 2, no. 10, pp. 749–760, Oct. 2018.

W. Li et al., "An interpretable hybrid deep learning model for flood forecasting based on Transformer and LSTM," Journal of Hydrology: Regional Studies, vol. 54, Aug. 2024, Art. no. 101873.

S. M. Malakouti, "Leveraging SHapley Additive exPlanations (SHAP) and fuzzy logic for efficient rainfall forecasts," Scientific Reports, vol. 15, no. 1, Oct. 2025, Art. no. 36499.

W. Almikaeel, A. Šoltész, L. Čubanová, and D. Baroková, "Hydro-informer: a deep learning model for accurate water level and flood predictions," Natural Hazards, vol. 121, no. 4, pp. 3959–3979, Mar. 2025.

G. Bertoli, K. Schroeter, R. Arcucci, and E. Caporali, "A Hybrid Machine Learning Framework for Improved Short-Term Peak-Flow Forecasting." arXiv, Jan. 14, 2026.

"Climate Data Daily IDN." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/greegtitan/indonesia-climate/data.

M. Pujara and N. Paudel, "Rainfall Prediction using Long Short-Term Memory and Gated Recurrent Unit with Various Meteorological Parameters," Nepalese Journal of Statistics, vol. 8, pp. 47–60, Dec. 2024.

S. Wijaya, T. B. Kurniawan, E. S. Negara, and Y. N. Kunang, "Rainfall Prediction in Palembang City Using the GRU and LSTM Methods," Journal of Data Science, vol. 2023, Mar. 2023, Art. no. 4.

I. Ebtehaj and H. Bonakdari, "CNN vs. LSTM: A Comparative Study of Hourly Precipitation Intensity Prediction as a Key Factor in Flood Forecasting Frameworks," Atmosphere, vol. 15, no. 9, Sept. 2024, Art. no. 1082.

Y. Wang, P. Jia, Z. Shu, K. Liu, and A. R. M. Shariff, "Multidimensional precipitation index prediction based on CNN-LSTM hybrid framework." arXiv, Apr. 29, 2025.

I. Ramli, T. Ferijal, and S. Rusdiana, "Rainfall Prediction in the Krueng Pase Watershed Using Support Vector Regression," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29894–29900, Dec. 2025.

J. Jagadeesan and R. Nagarajan, "An IoT-Driven Federated Learning Method for Rainfall Prediction Employing Attention Convolutional Recurrent Networks and Golden Jackal Optimization Techniques," Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 27858–27862, Oct. 2025.

A. Kunlerd, A. Ritthiron, and J. Kaewyotha, "An Enhanced Hybrid LSTM–Linear Regression Framework for 90-Day Rainfall Forecasting in Rainfed Agricultural Regions," Engineering, Technology & Applied Science Research, vol. 16, no. 1, pp. 31194–31202, Feb. 2026.