Meta-LSTM in hydrology: Advancing runoff predictions through model-agnostic meta-learning

• Published in: Journal of hydrology (Amsterdam) 2024-08, Vol.639, p.131521, Article 131521
• Main Authors: Cai, Kaixuan, He, Jinxin, Li, Qingliang, Shangguan, Wei, Li, Lu, Hu, Huiming
• Format: Article
• Language: English
• Subjects: Long Short-Term Memory (LSTM); Meta-Learning; Model Generalization; Multi-Task Learning; Runoff Simulation
• ISSN: 0022-1694
• DOI: 10.1016/j.jhydrol.2024.131521

•Incorporating meta-learning into LSTM model reduces the overall PBIAS by 8.68%, improving the overall KGE by 7% compared to standard LSTM model.•Meta-LSTM model improves extreme runoff prediction, enhancing FLV by 2.73% and FHV by 11.04%, aiding in better flood management strategies.•The proposed meta-learning framework enhances performance across various deep learning models, demonstrating its versatility in runoff prediction tasks. In the field of hydrology, deep learning has become a prevalent tool for runoff simulation. However, the limitations stem from their primary focus on normality, which fails to accurately capture rare events. This study introduces a novel Long Short-Term Memory (LSTM) model, termed Meta-LSTM, which is based on the Model-Agnostic Meta-Learning (MAML) framework. The Meta-LSTM model is capable of dynamically fine-tuning its parameters to ensure effective adaptation to various runoff scenarios. From this Meta-LSTM model, the Meta-enhanced paradigm is subsequently proposed, ensuring effective adaptation to diverse models and datasets. We conducted experiments with various models on the CAMELS and CAMELS-AUS datasets. Compared to conventional deep learning models for runoff simulation, Meta-enhanced models exhibit substantial improvements. Specifically, the Meta-LSTM model reduces the PBIAS from −13.86 % to −5.18 %, increasing the Kling-Gupta Efficiency (KGE) by 7 % on the CAMELS dataset. For the Meta-GR4J-CNN model, the PBIAS decreases by 21 %, and the Nash-Sutcliffe Efficiency (NSE) increases by 2 % on the CAMELS-AUS dataset. This demonstrates the ability of the Meta-enhanced model to more accurately represent observed data without significant additional time costs. Our approach overcomes the problem of uniform training in simulations of complex scenarios and promises to significantly improve the accuracy of future hydrologic studies.