Abstract
Recent advances in incorporating physical knowledge into deep neural networks can estimate previously unknown governing partial differential equations (PDEs) in a data-driven way. They have shown promising results in spatiotemporal predictive learning. However, these methods typically assume universal governing PDEs across space, which is impractical for modeling complex spatiotemporal phenomena with high spatial variability (e.g., climate). Also, they cannot effectively model the evolution of potential errors in estimating the physical dynamics over time. This paper introduces a physics-guided neural network, SVPNet, which learns effective physical representations by estimating the error evolution in physics states for correction and modeling spatially varying physical dynamics to predict the next state. Experiments carried out in four scenarios, including benchmarks and real-world datasets, show that SVPNet outperforms state-of-the-art methods in spatiotemporal prediction tasks for natural processes and significantly improves prediction when training data are limited. Ablation studies also highlight that SVPNet is powerful in capturing physical dynamics in complex physical systems.
Original language | English (US) |
---|---|
Title of host publication | 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 |
Editors | Maria Luisa Damiani, Matthias Renz, Ahmed Eldawy, Peer Kroger, Mario A. Nascimento |
Publisher | Association for Computing Machinery |
ISBN (Electronic) | 9798400701689 |
DOIs | |
State | Published - Nov 13 2023 |
Event | 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 - Hamburg, Germany Duration: Nov 13 2023 → Nov 16 2023 |
Publication series
Name | GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems |
---|
Conference
Conference | 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 |
---|---|
Country/Territory | Germany |
City | Hamburg |
Period | 11/13/23 → 11/16/23 |
Bibliographical note
Publisher Copyright:© 2023 ACM.
Keywords
- physics-guided machine learning
- spatial AI
- spatiotemporal predictive learning