Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems

TL;DR

The paper introduces the Adaptive Physics Transformer (APT), a neural operator that efficiently models complex subsurface energy systems by combining local and global attention mechanisms, outperforming existing methods and enabling scalable, high-resolution simulations.

Contribution

It presents the first neural architecture that learns from adaptive mesh refinement simulations, integrating local and global features for subsurface modeling.

Findings

APT outperforms state-of-the-art models in subsurface tasks.

It demonstrates robust super-resolution capabilities.

APT enables cross-dataset learning for large-scale applications.

Abstract

The Earth's subsurface is a cornerstone of modern society, providing essential energy resources like hydrocarbons, geothermal, and minerals while serving as the primary reservoir for $CO_2$ sequestration. However, full physics numerical simulations of these systems are notoriously computationally expensive due to geological heterogeneity, high resolution requirements, and the tight coupling of physical processes with distinct propagation time scales. Here we propose the \textbf{Adaptive Physics Transformer} (APT), a geometry-, mesh-, and physics-agnostic neural operator that explicitly addresses these challenges. APT fuses a graph-based encoder to extract high-resolution local heterogeneous features with a global attention mechanism to resolve long-range physical impacts. Our results demonstrate that APT outperforms state-of-the-art architectures in subsurface tasks across both regular and irregular grids with robust super-resolution capabilities. Notably, APT is the first architecture that directly learns from adaptive mesh refinement simulations. We also demonstrate APT's capability for cross-dataset learning, positioning it as a robust and scalable backbone for large-scale subsurface foundation model development.