A Novel Deep Learning Model for Mining Nonlinear Dynamics in Lake Surface Water Temperature Prediction

Abstract

As one of the critical indicators of the lake ecosystem, the lake surface water temperature is an important indicator for measuring lake ecological environment. However, there is a complex nonlinear relationship between lake surface water temperature and climate variables, making it difficult to accurately predict. Fortunately, satellite remote sensing provides a wealth of data to support further improvements in prediction accuracy. In this paper, we construct a new deep learning model for mining the nonlinear dynamics from climate variables to obtain more accurate prediction of lake surface water temperature. The proposed model consists of the variable correlation information module and the temporal correlation information module. The variable correlation information module based on the Self-Attention mechanism extracts key variable features that affect lake surface water temperature. Then, the features are input into the temporal correlation information module based on the Gated Recurrent Unit (GRU) model to learn the temporal variation patterns. The proposed model, called Attention-GRU, is then applied to lake surface water temperature prediction in Qinghai Lake, the largest inland lake located in the Tibetan Plateau region in China. Compared with the seven baseline models, the Attention-GRU model achieved the most accurate prediction results; notably, it significantly outperformed the Air2water model which is the classic model for lake surface water temperature prediction based on the volume-integrated heat balance equation. Finally, we analyzed the factors influencing the surface water temperature of Qinghai Lake. There are different degrees of direct and indirect effects of climatic variables, among which air temperature is the dominant factor.

Keywords

• deep learning
• lake surface water temperature prediction
• nonlinear dynamics
• Attention-GRU