Saved in:
Bibliographic Details
Main Authors: Yu, Zhenyu, Idris, Mohd. Yamani Idna, Wang, Pei, Xia, Yuelong, Ma, Fei, Qureshi, Rizwan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.06176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915331478388736
author Yu, Zhenyu
Idris, Mohd. Yamani Idna
Wang, Pei
Xia, Yuelong
Ma, Fei
Qureshi, Rizwan
author_facet Yu, Zhenyu
Idris, Mohd. Yamani Idna
Wang, Pei
Xia, Yuelong
Ma, Fei
Qureshi, Rizwan
contents We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike traditional empirical indices or black-box learning models, SatelliteFormula combines a Vision Transformer-based encoder for spatial-spectral feature extraction with physics-guided constraints to ensure consistency and interpretability. Existing symbolic regression methods struggle with the high-dimensional complexity of multi-spectral data; our method addresses this by integrating transformer representations into a symbolic optimizer that balances accuracy and physical plausibility. Extensive experiments on benchmark datasets and remote sensing tasks demonstrate superior performance, stability, and generalization compared to state-of-the-art baselines. SatelliteFormula enables interpretable modeling of complex environmental variables, bridging the gap between data-driven learning and physical understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06176
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
Yu, Zhenyu
Idris, Mohd. Yamani Idna
Wang, Pei
Xia, Yuelong
Ma, Fei
Qureshi, Rizwan
Computer Vision and Pattern Recognition
We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike traditional empirical indices or black-box learning models, SatelliteFormula combines a Vision Transformer-based encoder for spatial-spectral feature extraction with physics-guided constraints to ensure consistency and interpretability. Existing symbolic regression methods struggle with the high-dimensional complexity of multi-spectral data; our method addresses this by integrating transformer representations into a symbolic optimizer that balances accuracy and physical plausibility. Extensive experiments on benchmark datasets and remote sensing tasks demonstrate superior performance, stability, and generalization compared to state-of-the-art baselines. SatelliteFormula enables interpretable modeling of complex environmental variables, bridging the gap between data-driven learning and physical understanding.
title SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.06176