Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov-Arnold Networks

2026-05-04

AI Summary

This work addresses the computational bottleneck in generating high-fidelity atmospheric correction coefficients, which traditionally rely on expensive radiative transfer models and hinder efficient preprocessing. To overcome this limitation, the authors propose pKANrtm, a physics-guided multi-fidelity surrogate model that integrates paired low-fidelity 6S and high-fidelity libRadtran simulations. Built upon the Efficient-KAN architecture, pKANrtm learns the residual mapping between fidelity levels while enforcing physical consistency constraints in coefficient space and incorporating a spectral response function-aware loss. The method consistently outperforms existing surrogates in both standard and out-of-distribution evaluations, achieving approximately four orders of magnitude faster inference per sample on GPU and enabling batch processing at tens of thousands of samples per second—thus delivering both high accuracy and exceptional computational efficiency.

Abstract

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-aware 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-consistency 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 evaluation settings, pKANrtm achieves the strongest overall predictive performance among the compared models. 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. These results indicate that physics-aware multi-fidelity pKANrtm emulation provides an accurate, physically structured, and computationally efficient strategy for atmospheric correction coefficient generation.

Problem

• atmospheric correction
• radiative transfer simulation
• multi-fidelity emulation
• computational efficiency
• remote sensing

Innovation

• physics-guided KAN
• multi-fidelity emulation
• atmospheric correction
• radiative transfer surrogate
• Efficient-KAN