Differentiable Physics-informed Graph Networks
This work addresses the challenge of leveraging physics in AI for domain-specific applications like climate prediction, though it appears incremental in its approach.
The authors tackled the problem of incorporating implicit physics knowledge into deep neural networks by proposing Differentiable Physics-informed Graph Networks (DPGN), which significantly improved climate prediction tasks.
While physics conveys knowledge of nature built from an interplay between observations and theory, it has been considered less importantly in deep neural networks. Especially, there are few works leveraging physics behaviors when the knowledge is given less explicitly. In this work, we propose a novel architecture called Differentiable Physics-informed Graph Networks (DPGN) to incorporate implicit physics knowledge which is given from domain experts by informing it in latent space. Using the concept of DPGN, we demonstrate that climate prediction tasks are significantly improved. Besides the experiment results, we validate the effectiveness of the proposed module and provide further applications of DPGN, such as inductive learning and multistep predictions.