PHASE: Physics‑Integrated, Heterogeneity‑Aware Surrogates for Scientific Simulations

ICLR 2026 Conference Submission15081 Authors

Keywords: Physics-informed deep learning, Scientific machine learning, Surrogate modeling, Earth system modeling

Abstract: Large‐scale numerical simulations underpin modern scientific discovery but remain constrained by prohibitive computational costs. AI surrogates offer acceleration, yet adoption in mission‑critical settings is limited by concerns over physical plausibility, trustworthiness, and the fusion of heterogeneous data. We introduce PHASE, a modular deep‑learning framework for physics‑integrated, heterogeneity‑aware surrogates in scientific simulations. PHASE combines data‑type–aware encoders for heterogeneous inputs with multi‑level physics‑based constraints that promote consistency from local dynamics to global system behavior. We validate PHASE on the biogeochemical (BGC) spin‑up workflow of the U.S. Department of Energy’s Energy Exascale Earth System Model (E3SM) Land Model (ELM), presenting—to our knowledge—the first scientifically validated AI‑accelerated solution for this task. Using only the first 20 simulation years, PHASE infers a near‑equilibrium state that otherwise requires more than 1,200 years of integration, yielding an effective reduction in required integration length by at least 60×. The framework is enabled by a pipeline for fusing heterogeneous scientific data and demonstrates strong generalization to higher spatial resolutions with minimal fine‑tuning. These results indicate that PHASE captures governing physical regularities rather than surface correlations, enabling practical, physically consistent acceleration of land‑surface modeling and other complex scientific workflows.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 15081