Enhanced IMERG SPE Using LSTM with a Novel Adaptive Regularization Method
Document Type
Article
Publication Date
4-1-2026
Abstract
Satellite-based precipitation estimates (SPE) provide essential spatial coverage and near real-time availability for hydrological applications but often exhibit systematic biases in regions characterized by complex terrain and strong climatic variability, limiting their reliability for flood-related studies. To address these limitations, this study proposes an Adaptive Regularization framework integrated within a Long Short-Term Memory (LSTM) model to enhance satellite–gauge rainfall fusion beyond conventional optimization strategies. The framework dynamically adjusts learning rate and weight decay during training based on validation performance and overfitting indicators, improving training stability, data efficiency, and model generalization across diverse precipitation regimes. The proposed approach was applied to refine Integrated Multi-satellite Retrievals for Global Precipitation Measurement (IMERG) daily rainfall estimates over the flood-prone east coast of Peninsular Malaysia. Model performance was assessed against ten optimization algorithms using correlation coefficient (CC), mean absolute error (MAE), normalized root mean squared error (NRMSE), percentage bias (PBias), and Kling–Gupta efficiency (KGE). Results show that the Adaptive Regularization framework consistently outperforms all benchmark optimizers, achieving an MAE of 6.87, CC of 0.68, NRMSE of 1.84, and KGE of 0.56. Overall, the proposed framework enhances spatial consistency and robustness across monsoon seasons, offering a scalable solution for improving SPE in flood-prone regions.
Keywords
Adaptive Regularization, east coast of Peninsular Malaysia (ECPM), IMERG, Long Short-Term Memory (LSTM), rainfall bias correction, satellite precipitation estimation
Publication Title
Water Switzerland
ISSN
2073-4441
DOI
10.3390/w18080905
Recommended Citation
Toh, Seng Choon; Wan Jaafar, Wan Zurina; Ng, Cia Yik; Soo, Eugene Zhen Xiang; Mirzaei, Majid; Teo, Fang Yenn; and Lai, Sai Hin, "Enhanced IMERG SPE Using LSTM with a Novel Adaptive Regularization Method" (2026). Research Publications (2026 to 2030). 886.
https://knova.um.edu.my/research_publications_2026_2030/886
Volume
18
Issue
8
Publisher
Multidisciplinary Digital Publishing Institute (MDPI)