Hybrid Model with SHAP-Enhanced Deep Neural Networks for Accurate Short-Term Rainfall

DOI

10.2991/978-94-6463-718-2_61How to use a DOI?

Keywords

Rainfall prediction; hybrid model; SHAP; deep neural networks; explainable AI; CNN; LSTM; extreme weather events; uncertainty quantification; weather forecasting; data bias mitigation; regional adaptability; computational efficiency; flood forecasting; disaster management; temporal scalability; transparency in AI; short-term rainfall forecasting; interpretable AI models; meteorological modeling

Abstract

It makes a major part of the Weather forecast which plays a vital role in disaster management, resource planning, etc. In this study, we offer a new SHAP-attached DNN-based hybrid model for accurate and interpretable short-term rainfall predictions. Model Solving Challenges: By implementing convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and SHAP (SHapley Additive exPlanations) for explainability, this solution addresses core challenges such as data bias, overfitting, and computational efficiency. The proposed approach is shown to be effective across various regions and time periods, can achieve positive results during extreme rainfall events, and, through SHAP-based analysis, provides improved interpretability, allowing stakeholders to gain actionable insights. Moreover, the model incorporates uncertainty quantification, enhancing prediction confidence and facilitating real-world applications in weather prediction systems. The novelty of this approach lies in its ability to bridge the gap between accuracy, transparency, and usability, setting a new standard for rainfall forecasting approaches.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. Savitha
AU  - V. Vennila
AU  - A. Rajivkannan
AU  - G. Sathyaseelan
AU  - M. Sathyamoorthy
AU  - V. Vasanth
PY  - 2025
DA  - 2025/05/23
TI  - Hybrid Model with SHAP-Enhanced Deep Neural Networks for Accurate Short-Term Rainfall
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 710
EP  - 719
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_61
DO  - 10.2991/978-94-6463-718-2_61
ID  - Savitha2025
ER  -