RfGANNNet 2.0: A Hybrid AI Framework Integrating Random Forests, Spatio-Temporal Graph Convolution, and Physics-Guided GANs for High-Resolution Rainfall Forecasting

Subham Pandey; Tooba Afzal; Mishkaat Anjum; Warisa Anwar; Tasfiya Khanam; Merajuddin

doi:10.55524/ijircst.2025.13.3.16

Abstract

Accurate rainfall forecasting underpins effective water resource management, disaster mitigation, and agricultural planning. This paper proposes RfGANNNet 2.0, a hybrid AI framework that combines Random Forests, Spatio-Temporal Graph Convolutional Networks (ST-GCN), and Physics-Guided Generative Adversarial Networks (GANs) to deliver high-resolution and generalizable rainfall predictions. We present a comprehensive review of AI-driven techniques from 2018 to 2025, including ensemble models such as AdaNAS, deep learning architectures like ConvLSTM and Temporal Fusion Transformer (TFT), and spatio-temporal attention mechanisms. The model integrates satellite and radar remote sensing data, addresses limitations related to data sparsity, and incorporates Explainable AI methods (e.g., SHAP, LIME) to interpret model outputs. Extensive evaluations using benchmark datasets and metrics such as RMSE, MAE, and AUC highlight the robustness and accuracy of the proposed approach. Future research directions include real-time edge computing, adaptive transfer learning, and advanced data fusion to improve operational readiness and performance in extreme weather scenarios.

Keywords

Rainfall forecasting, hybrid AI models, spatio-temporal modeling, Random Forest, Generative Adversarial Networks (GANs), Graph Convolutional Networks (GCN), AdaNAS, Temporal Fusion Transformer (TFT), ConvLSTM, Explainable AI (XAI), Remote sensing data.

References

C. M. Liyew and H. A. Melese, “Machine learning techniques to predict daily rainfall amount,” J. Big Data, vol. 8, p. 153, 2021. Available from: https://doi.org/10.1186/s40537-021-00545-4
X. Ling, C. Li, F. Qin, L. Zhu, and Y. Huang, “Two-stage Rainfall-Forecasting Diffusion Model,” 2024. Available from: https://doi.org/10.48550/arXiv.2402.12779
O. Kandasamy and M. N. Maragatham, “Rainfall prediction using the Coimbatore region,” Atmospheric Research, 2023. Available from: https://doi.org/10.2166/wcc.2025.576
G. Nearing et al., “AI Increases Global Access to Reliable Flood Forecasts,” arXiv preprint, arXiv:2307.16104, 2023. Available from: https://doi.org/10.48550/arXiv.2307.16104
Ü. Ç. Büyük?ahin and ?. Ertekin, “Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition,” arXiv preprint, 2018. Available from: https://doi.org/10.1016/j.neucom.2019.05.099
V. Kumar et al., “A Comparison of Machine Learning Models for Predicting Rainfall in Urban Metropolitan Cities,” Sustainability, vol. 15, 2023. Available from: http://dx.doi.org/10.3390/su151813724
F. Kratzert et al., “Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks,” Hydrol. Earth Syst. Sci., vol. 22, no. 11, pp. 6005–6022, 2018. Available from: https://doi.org/10.5194/hess-22-6005-2018
M. T. Sattari et al., “Evaluation of Feature Selection Methods in Estimation of Precipitation Based on Deep Learning Artificial Neural Networks,” Water Resour. Manage., vol. 37, pp. 5871–5891, 2023. Available from: https://doi.org/10.1007/s11269-023-03563-4
Y. Wang et al., “Multidimensional precipitation index prediction based on CNN-LSTM hybrid framework,” arXiv preprint, arXiv:2504.20442, 2025. Available from: https://doi.org/10.48550/arXiv.2504.20442
B. S. Patro and P. P. Bartakke, “Daily rainfall prediction using long short-term memory (LSTM) algorithm,” J. Agrometeorol., vol. 26, no. 4, pp. 509–511, 2024. Available from: https://doi.org/10.54386/jam.v26i4.2745
M. Waqas et al., “Artificial intelligence and numerical weather prediction models: A technical survey,” Natural Hazards Research, 2024. Available from: https://doi.org/10.1016/j.nhres.2024.11.004
X. Shi et al., “Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting,” Adv. Neural Inf. Process. Syst., vol. 28, 2015. Available from: https://doi.org/10.48550/arXiv.1506.04214
S. Kim et al., “DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data,” arXiv preprint, arXiv:1711.02316, 2017. Available from: https://doi.org/10.48550/arXiv.1711.02316
P. Das et al., “Hybrid physics-AI outperforms numerical weather prediction for extreme precipitation nowcasting,” arXiv preprint, arXiv:2407.11317, 2024. Available from: https://doi.org/10.48550/arXiv.2407.11317
X. Li et al., “Hybrid CNN-LSTM models for river flow prediction,” Water Supply, vol. 22, no. 5, pp. 4902–4919, 2022. Available from: https://doi.org/10.2166/ws.2022.170
A. Devda et al., “Enhanced Precision in Rainfall Forecasting for Mumbai: Utilizing Physics Informed ConvLSTM2D Models for Finer Spatial and Temporal Resolution,” arXiv preprint, arXiv:2404.01122, 2024. Available from: https://doi.org/10.48550/arXiv.2404.01122
L. Guo, Y. Pu, and W. Zhao, “CNN-BiLSTM Daily Precipitation Prediction Based on Attention Mechanism,” Atmosphere, vol. 16, no. 3, p. 333, 2025. Available from: https://doi.org/10.3390/atmos16030333
S. An et al., “Deep learning for precipitation nowcasting: A survey from the perspective of time series forecasting,” arXiv preprint, arXiv:2406.04867, 2024. Available from: https://doi.org/10.48550/arXiv.2406.04867
R. Yang et al., “Interpretable Machine Learning for Weather and Climate Prediction: A Survey,” arXiv, 2024. Available from: https://doi.org/10.48550/arXiv.2403.18864
D. Wolfensberger et al., “RainForest: a random forest algorithm for quantitative precipitation estimation over Switzerland,” Atmos. Meas. Tech., vol. 14, no. 4, pp. 3169–3193, 2021. Available from: https://doi.org/10.5194/amt-14-3169-2021
M. T. Anwar et al., “Rainfall prediction using Extreme Gradient Boosting,” J. Phys.: Conf. Ser., vol. 1869, no. 1, p. 012078, 2021. Available from: https://doi.org/10.1088/1742-6596/1869/1/012078
Z. Li et al., “RAINER: A Robust Ensemble Learning Grid Search-Tuned Framework for Rainfall Patterns Prediction,” arXiv, 2025. Available from: https://doi.org/10.48550/arXiv.2501.16900
Y. Wen et al., “AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts,” arXiv, 2023. Available from: https://doi.org/10.48550/arXiv.2312.16046
P. Bhasme, J. Vagadiya, and U. Bhatia, “Enhancing predictive skills in physically-consistent way: Physics Informed Machine Learning for Hydrological Processes,” arXiv preprint, arXiv:2104.11009, 2021. Available from: https://doi.org/10.48550/arXiv.2104.11009
K. Bansal et al., “RfGanNet: An efficient rainfall prediction method for India and its clustered regions using RfGan and deep convolutional neural networks,” Expert Syst. Appl., vol. 235, p. 121191, 2024. Available from: https://doi.org/10.1016/j.eswa.2023.121191
A. Dube et al., “Evaluating the performance of two global ensemble forecasting systems in predicting rainfall over India during the southwest monsoons,” Meteorol. Appl., vol. 24, pp. 230–238, 2017. Available from: https://doi.org/10.1002/met.1621
F.-H. Zhang and Z.-G. Shao, “T-GRF: Spatiotemporal graph neural networks for rainfall forecasting,” Digital Signal Process., vol. 136, p. 103989, 2023. Available from: https://doi.org/10.1016/j.dsp.2023.103989
P. Demetrakopoulos, “Short-term Precipitation Forecasting in The Netherlands: An Application of Convolutional LSTM Neural Networks to Weather Radar Data,” arXiv preprint, arXiv:2312.01197, 2023. Available from: https://doi.org/10.48550/arXiv.2312.01197
M. Agarwal, P. Das, and U. Bhatia, “Spatially Regularized Graph Attention Autoencoder Framework for Detecting Rainfall Extremes,” arXiv preprint, arXiv:2411.07753, 2024. Available from: https://doi.org/10.48550/arXiv.2411.07753
T. Vandal and R. Nemani, “Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow,” arXiv preprint, arXiv:1907.12013, 2019. Available from: https://doi.org/10.48550/arXiv.1907.12013
J. Liu et al., “STFM: Accurate Spatio-Temporal Fusion Model for Weather Forecasting,” Atmosphere, vol. 15, no. 10, p. 1176, 2024. Available from: https://doi.org/10.3390/atmos15101176

Cites this article as

S. Pandey, T. Afzal, M. Anjum, W. Anwar, T. Khanam, Merajuddin, "RfGANNNet 2.0: A Hybrid AI Framework Integrating Random Forests, Spatio-Temporal Graph Convolution, and Physics-Guided GANs for High-Resolution Rainfall Forecasting", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-13, Issue-3, Page No-95-105, 2025. Available from: https://doi.org/10.55524/ijircst.2025.13.3.16

Corresponding Author

Subham Pandey

B. Tech Scholar, Department of Computer Science and Engineering, Integral University, Lucknow, India

Download Full Paper

Download PDF

No. of Downloads: 40 | No. of Views: 670

Spectral Geometric Regularization: Towards Isometric Invariance for Domain-Generalized Learning

Kalyan Chakravarthy Kodela, Rohith Vangalla.

September 2025 - Vol 13, Issue 5
Performance Evaluation of Ultrasonic Obstacle Detection and Real-Time GPS Tracking in an IoT Smart Shoe for Visually Impaired Navigation

Juanda Hakim Lubis, Akhyar Lubis, Fajrul Malik Aminullah Napitupulu, Nahdah Salsabiil Damanik, Lathifah Tsamratul Ain.

September 2025 - Vol 13, Issue 5
A Systematic Review of the Impact of DNS-Layer Security Mechanisms on Internet Network Performance and Threat Mitigation

Noah K. Bamfo, Christian Avornu, Abigail Nanayaa Otchill, Hassan Cessi Ibrahim, Ramini Nikhil Sai.

September 2025 - Vol 13, Issue 5

RfGANNNet 2.0: A Hybrid AI Framework Integrating Random Forests, Spatio-Temporal Graph Convolution, and Physics-Guided GANs for High-Resolution Rainfall Forecasting

Citations

Download Full Paper PDF

Total View 670

Total Download 40