Physics-informed Diffusion Generation for Geomagnetic Map Interpolation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Wenda, Zheng, Tongya, Chen, Kaixuan, Liu, Shunyu, Jiang, Haoze, Hao, Yunzhi, Miao, Rui, Ren, Zujie, Song, Mingli, Shi, Hang, Chen, Gang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912866515288064
author Li, Wenda
Zheng, Tongya
Chen, Kaixuan
Liu, Shunyu
Jiang, Haoze
Hao, Yunzhi
Miao, Rui
Ren, Zujie
Song, Mingli
Shi, Hang
Chen, Gang
author_facet Li, Wenda
Zheng, Tongya
Chen, Kaixuan
Liu, Shunyu
Jiang, Haoze
Hao, Yunzhi
Miao, Rui
Ren, Zujie
Song, Mingli
Shi, Hang
Chen, Gang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00709
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics-informed Diffusion Generation for Geomagnetic Map Interpolation
Li, Wenda
Zheng, Tongya
Chen, Kaixuan
Liu, Shunyu
Jiang, Haoze
Hao, Yunzhi
Miao, Rui
Ren, Zujie
Song, Mingli
Shi, Hang
Chen, Gang
Artificial Intelligence
Machine Learning
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.
title Physics-informed Diffusion Generation for Geomagnetic Map Interpolation
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.00709