Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network
This work addresses the need for efficient lake temperature estimation in hydrological and ecological domains, representing an incremental improvement by combining existing Bayesian neural network components for a specific application.
The paper tackles the problem of accurately estimating lake surface water temperature by proposing a Bayesian spatio-temporal graph convolutional neural network, which achieves homogeneously good performance across the entire lake surface despite sparse training data, as demonstrated through quantitative comparisons with a state-of-the-art Bayesian deep learning method.
Accurate lake temperature estimation is essential for numerous problems tackled in both hydrological and ecological domains. Nowadays physical models are developed to estimate lake dynamics; however, computations needed for accurate estimation of lake surface temperature can get prohibitively expensive. We propose to aggregate simulations of lake temperature at a certain depth together with a range of meteorological features to probabilistically estimate lake surface temperature. Accordingly, we introduce a spatio-temporal neural network that combines Bayesian recurrent neural networks and Bayesian graph convolutional neural networks. This work demonstrates that the proposed graphical model can deliver homogeneously good performance covering the whole lake surface despite having sparse training data available. Quantitative results are compared with a state-of-the-art Bayesian deep learning method. Code for the developed architectural layers, as well as demo scripts, are available on https://renkulab.io/projects/das/bstnn.