Journal Article

Hydroformer: Frequency Domain Enhanced Multi‐Attention Transformer for Monthly Lake Level Reconstruction With Low Data Input Requirements

Zhang, Wenqian, Shi, Yang, Wang, He, Wu, Yue, Xu, Jiaqi, Wei, Jiahua, Hou, Minglei, Hou, Shengling

2024

Overview

Lake level changes are critical indicators of hydrological balance and climate change, yet long‐term monthly lake level reconstruction is challenging with incomplete or short‐term data. Data‐driven models, while promising, struggle with nonstationary lake level changes and complex dependencies on meteorological factors, limiting their applicability. Here, we introduce the Hydroformer, a frequency domain enhanced multi‐attention Transformer model designed for monthly lake level reconstruction, utilizing reanalysis data. This model features two innovative mechanisms: (a) Frequency‐Enhanced Attention (FEA) for capturing long‐term temporal dependence, and (b) Causality‐based Cross‐dimensional Attention (CCA) to elucidate how specific meteorological factors influence lake level. Seasonal and trend patterns of catchment meteorological factors and lake level are initially identified by a time series decomposition block, then independently learned and refined within the model. Tested across 50 lakes globally, the Hydroformer excelled in reconstruction periods ranging from half to three times the training‐test length. The model exhibited good performance even when training data missing rates were below 50%, particularly in lakes with significant seasonal fluctuations. The Hydroformer demonstrated robust generalization across lakes of varying sizes, from 10.11 to 18,135 km2, with median values for R2, MAE, MSE, and RMSE at 0.813, 0.313, 0.215, and 0.4, respectively. Furthermore, the Hydroformer outperformed data‐driven models, improving MSE by 29.2% and MAE by 24.4% compared to the next best model, the FEDformer. Our method proposes a novel approach for reconstructing long‐term water level changes and managing lake resources under climate change. Plain Language Summary Lake water levels, as key indicators of hydrologic dynamics and catchment balance, are vital for understanding climate impacts and managing water resources. However, the lack of continuous measurements for most global lakes, combined with the inability of traditional data‐driven models to effectively decipher complex interactions with catchment hydrological processes, leads to significant gaps in generalizability, accuracy, and reconstructive length. Given these limitations, accurate monthly reconstructions of lake level remain a persistent challenge. To address this, we develop Hydroformer, an innovative frequency domain enhanced multi‐attention Transformer model, utilizing reanalysis data for monthly lake level reconstruction. It employs two innovative attention mechanisms: Frequency‐Enhanced Attention for capturing long‐term temporal dependencies and Causality‐based Cross‐dimensional Attention for cross‐dimensional causal dependencies between catchment meteorological factors and lake level. Through a decomposition block, the model efficiently recognizes and refines inherent seasonal and trend patterns, leading to a comprehensive understanding of lake behaviors. Through testing on 50 global lakes, the Hydroformer has exhibited exceptional performance in reconstructing water levels for lakes ranging from 10.11 to 18,135 km2, adeptly handling short‐term, long‐term, and varying proportions of data gaps. It notably outperforms supervised data‐driven models. This positions it as a vital instrument for monthly lake level reconstruction, showcasing the power of integrating advanced artificial intelligence techniques in hydrological modeling. Key Points A novel frequency domain enhanced multi‐attention Transformer model, Hydroformer, has been built for reconstructing monthly lake level using reanalysis data The model accurately extends reconstructions 2–3 times the training data length, excelling with less than 50% missing training data Hydroformer surpasses advanced AI‐based models, improving MSE and MAE by over 20% and demonstrating strong generalization across lakes of varying sizes

• Publisher: John Wiley & Sons, Inc,Wiley
• Subject: Artificial intelligence / Catchments / Causality‐based Cross‐dimensional Attention (CCA) mechanism / Climate change / Decomposition / domain / Frequency domain analysis / Frequency‐Enhanced Attention (FEA) mechanism / Hydrologic models / Hydrologic processes / Hydrology / Indicators / Lake level changes / Lake level reconstruction / Lake water / Lakes / Multi‐Attention mechanism / Pattern recognition / Reconstruction / Seasonal variations / time series analysis / Training / Transformer‐based model / water / Water level fluctuations / Water levels / Water management / Water resources / Water resources management / Watersheds