Physics-informed Diffusion Generation for Geomagnetic Map Interpolation

TL;DR

This paper introduces a Physics-informed Diffusion Generation framework that improves geomagnetic map interpolation by integrating physics constraints and noise reduction techniques, leading to more accurate and physically consistent results.

Contribution

The paper presents a novel physics-informed diffusion approach with a mask strategy and physics constraints, specifically tailored for geomagnetic map interpolation, outperforming existing methods.

Findings

Superior interpolation accuracy on four real-world datasets

Effective noise elimination through physics-informed masking

Enhanced physical consistency in generated geomagnetic maps

Abstract

Geomagnetic map interpolation aims to infer unobserved geomagnetic data at spatial points, yielding critical applications in navigation and resource exploration. However, existing methods for scattered data interpolation are not specifically designed for geomagnetic maps, which inevitably leads to suboptimal performance due to detection noise and the laws of physics. Therefore, we propose a Physics-informed Diffusion Generation framework~(PDG) to interpolate incomplete geomagnetic maps. First, we design a physics-informed mask strategy to guide the diffusion generation process based on a local receptive field, effectively eliminating noise interference. Second, we impose a physics-informed constraint on the diffusion generation results following the kriging principle of geomagnetic maps, ensuring strict adherence to the laws of physics. Extensive experiments and in-depth analyses on four real-world datasets demonstrate the superiority and effectiveness of each component of PDG.