Climate Research

Learning Across Scales: A Physics-Informed Approach to Climate Modeling

Authors: Arantxa Vicario
Comments: 7 Pages. (Note by viXra Admin: Please submit article written with AI assistance to ai.viXra.org)

Climate modeling plays a pivotal role in understanding Earth's complex systems, but traditional methods struggle with computational demands across spatial and temporal scales. Machine learning (ML) offers a promising alternative, yet purely data-driven approaches often lack physical consistency. To address this, we propose a physics-informed approach to learning across scales in climate modeling. Our framework integrates physics-informed neural networks (PINNs) with hierarchical representations to model multiscale processes efficiently. We demonstrate improved accuracy and efficiency on benchmark climate datasets, paving the way for more reliable predictions of complex climate phenomena. These findings underscore the potential of combining ML with domain knowledge to advance climate science.
Category: Climate Research