Large lake thermal inertia reduces annual and diurnal temperature variability across the Great Lakes basin and results in a less significant warming over the lakes than over the surrounding land. LST, as an over-lake lower boundary condition for atmospheric processes, influences the climate and hydroclimate through various multiscale lake–atmosphere interactions. Lake surface temperature (LST) is a fundamental thermodynamic variable for the regional climate, and a widely used environmental indicator for climate and environmental changes.
#Hydrodynamic ram pressure explained driver#
The integration further enhanced prediction accuracy, suggesting its potential for next-generation Great Lakes forecast systems.ĭue to their large volume and surface area, the Great Lakes are a significant driver of regional weather and climate. Finally, we developed a statistical integration of the hydrodynamic modeling and deep learning results based on the Best Linear Unbiased Estimator (BLUE). In contrast, the physics-based hydrodynamic model performed better in spring and fall yet exhibited relatively large biases during the summer stratification period. The relatively large bias in the LSTM prediction during the spring and fall was associated with substantial heterogeneity of air temperature during the two seasons. Our XAI analysis shows air temperature is the most influential feature for predicting LST in the trained LSTM. Furthermore, we employed an explainable artificial intelligence (XAI) technique named SHapley Additive exPlanations (SHAP) to uncover how the features impact the LSTM prediction. The LSTM prediction captured the LST spatiotemporal variabilities across the five Great Lakes well, suggesting an effective and efficient way for monitoring network design in assisting the ML-based forecast. Our study shows that the Long Short-Term Memory (LSTM) neural network, trained with the limited data from hypothetical monitoring networks, can provide consistent and robust performance. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection.
0 kommentar(er)
