Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling
This addresses the need for uncertainty-aware and physically consistent models in environmental science, though it is incremental as it adapts existing uncertainty methods to a specific domain.
The paper tackles the problem of quantifying uncertainty in deep learning models for lake temperature modeling while ensuring physical consistency, proposing a physics-guided architecture (PGA) that integrates with Monte Carlo Dropout to achieve better generalizability and match ground-truth distributions with limited training data.
To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture. This allows us to integrate such models with state of the art uncertainty estimation approaches such as Monte Carlo (MC) Dropout without sacrificing the physical consistency of our results. We demonstrate the effectiveness of our approach in ensuring better generalizability as well as physical consistency in MC estimates over data collected from Lake Mendota in Wisconsin and Falling Creek Reservoir in Virginia, even with limited training data. We further show that our MC estimates correctly match the distribution of ground-truth observations, thus making the PGA paradigm amenable to physically grounded uncertainty quantification.