Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov–Arnold Networks
Remote Sensing · 03.06.2026 · 18 (11) · 1826
DOI: 10.3390/rs18111826 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.06.2026. Verfasst von Md Abdullah Al Mazid und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation under Grant.
Abstract (Originalsprache)
Atmospheric correction is a critical preprocessing step in optical remote sensing, but repeated high-fidelity radiative transfer simulations remain computationally expensive for dense look-up-table generation, sensitivity analysis, retrieval support, and operational preprocessing. This study presents a physics-guided multi-fidelity surrogate framework for emulating atmospheric correction coefficients using paired 6S and libRadtran simulations. Atmospheric and geometric states are sampled using Latin Hypercube Sampling, and both radiative transfer models are evaluated under matched conditions for Sentinel-2 bands using spectral-response-function-aware coefficient generation. The high-fidelity targets are path reflectance, total transmittance, and spherical albedo. A physics-guided Kolmogorov–Arnold Network, termed pKANrtm, receives the atmospheric state and low-fidelity 6S coefficients, predicts the residual relative to libRadtran, and reconstructs the high-fidelity coefficients. The pKANrtm model uses an Efficient-KAN architecture and is trained with a physics-guided penalty applied in the original coefficient space. The proposed model is evaluated against state-of-the-art regression-based RTM surrogates. Across both standard and out-of-distribution (OOD) evaluation settings, pKANrtm achieves the strongest overall predictive performance among the compared models. Band-wise analysis shows that most Sentinel-2 bands are accurately emulated, while absorption-sensitive bands remain comparatively challenging. Runtime benchmarking demonstrates substantial acceleration relative to libRadtran, with GPU inference providing approximately four orders of magnitude single-sample speedup and batched inference reaching tens of thousands of samples per second. As an initial real-scene validation, the trained pKANrtm correction was applied to a Sentinel-2A acquisition over the Gobabeb RadCalNet site, demonstrating that the learned residual correction improves downstream surface-reflectance retrieval beyond synthetic RTM-to-RTM coefficient emulation. These results indicate that physics-guided multi-fidelity pKANrtm emulation provides an accurate, physically structured, computationally efficient, and practically useful strategy for atmospheric correction coefficient generation.
Förderung
- National Science Foundation under Grant
Zitieren
APA
Mazid, M. A. A., & Rishe, N. (2026). Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov–Arnold Networks. Remote Sensing, 18(11), 1826. https://doi.org/10.3390/rs18111826
Vancouver
Mazid MAA, Rishe N. Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov–Arnold Networks. Remote Sensing. 2026;18(11):1826. doi:10.3390/rs18111826
BibTeX
@article{Mazid2026,
author = {Mazid, Md Abdullah Al and Rishe, Naphtali},
title = {Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov–Arnold Networks},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {11},
pages = {1826},
doi = {10.3390/rs18111826}
}
EUVIMED