Work

Physics-Aware Multi-Task Learning for Atmospheric Turbulence Parameterization: Auxiliary Tasks versus Architectural Conditioning

Year: 2026

Type: conference-paper

Abstract: Dynamic subgrid-scale (SGS) turbulence parameterizations in Large Eddy Simulation (LES) achieve superior physical fidelity but impose 2-4× computational overhead compared to static schemes, creating a critical bottleneck for high-resolution atmospheric modeling on HPC systems. Neural network based emulation offers a pathway to comparable accuracy at reduced computational cost, but realizing this potential requires architectures that generalize reliably across diverse atmospheric conditions and variable grid configurations.

Source: Platform for Advanced Scientific Computing Conference (PASC)

DOI: 10.1145/3815572.3815750

Authors: Sambit Kumar Panda, Todd R. Jones, Muhammad Shahzad, Bryan N. Lawrence, Anna-Louise Ellis

Institutions: University of Reading, National Centre for Atmospheric Science, Met Office

Language: English

Topic: Meteorological Phenomena and Simulations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: hybrid

Funder: University of Reading