# Transferring Physical Priors into Remote Sensing Segmentation via Large Language Models Source: [Transferring Physical Priors into Remote Sensing Segmentation via Large Language Models]() Collection index: [llms.txt]() Data updated: 2026-04-01T05:00:04.436Z Authors: Yuxi Lu, Kunqi Li, Zhidong Li, Xiaohan Su, Biao Wu, Chenya Huang, Bin Liang Published: 2026-03-29T03:55:11.000Z ## Abstract Semantic segmentation of remote sensing imagery is fundamental to Earth observation. Achieving accurate results requires integrating not only optical images but also physical variables such as the Digital Elevation Model (DEM), Synthetic Aperture Radar (SAR) and Normalized Difference Vegetation Index (NDVI). Recent foundation models (FMs) leverage pre-training to exploit these variables but still depend on spatially aligned data and costly retraining when involving new sensors. To overcome these limitations, we introduce a novel paradigm for integrating domain-specific physical priors into segmentation models. We first construct a Physical-Centric Knowledge Graph (PCKG) by prompting large language models to extract physical priors from 1,763 vocabularies, and use it to build a heterogeneous, spatial-aligned dataset, Phy-Sky-SA. Building on this foundation, we develop PriorSeg, a physics-aware residual refinement model trained with a joint visual-physical strategy that incorporates a novel physics-consistency loss. Experiments on heterogeneous settings demonstrate that PriorSeg improves segmentation accuracy and physical plausibility without retraining the FMs. Ablation studies verify the effectiveness of the Phy-Sky-SA dataset, the PCKG, and the physics-consistency loss. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on OEM RGB-Only](): Semantic segmentation; OEM RGB-Only; mIoU: 41.98. - [Semantic Segmentation on iSAID RGB-Only](): Semantic segmentation; iSAID RGB-Only; mIoU: 45.23. - [Semantic Segmentation on LoveDA RGB-Only](): Semantic segmentation; LoveDA RGB-Only; mIoU: 39.72. - [Semantic Segmentation on WHU-OPT-SAR RGB-Phy](): Semantic segmentation; WHU-OPT-SAR RGB-Phy; mIoU: 42.98. - [Semantic Segmentation on SEN12MS RGB-Phy](): Semantic segmentation; SEN12MS RGB-Phy; mIoU: 43.1. ## Original sources and implementation [Original paper]() [PDF]()