Deep Neural Emulator of Radiative Transfer Model for Near-Infrared Hyperspectral Simulation: Implications for Fast Satellite Retrieval of XCO 2

Carbon dioxide (CO₂), a major greenhouse gas, has a profound impact on global climate change. Satellite remote sensing is a crucial approach for monitoring the column-averaged dry-air mole fraction of CO₂ (XCO₂). Currently, XCO₂ retrieval primarily relies on fully physical algorithms, where the radiative transfer model (RTM) imposes a significant computational burden during the forward simulation process. This inefficiency limits the capability for near-real-time monitoring, especially for large-scale retrievals expected from next-generation wide-swath carbon satellites. To address this challenge, this study proposes a deep learning-based surrogate modeling approach to accelerate RTM simulations and enable fast and accurate spectral radiance prediction, thereby facilitating efficient XCO₂ retrieval. Specifically, we design a two-stage neural network surrogate model for the SCIATRAN RTM, combining an AutoEncoder and a deep neural network. The former effectively reduces the dimensionality of hyperspectral data while preserving spectral fidelity, and the latter captures complex nonlinear mapping between atmospheric/surface states and satellite-observed radiance under diverse spatiotemporal scenarios. Results demonstrate that the surrogate model significantly improves computational efficiency while maintaining high accuracy, achieving millisecond-level prediction speeds. The model performs robustly across test datasets, finer-step extrapolation scenarios, and real-conditions validation using OCO-2 observations, yielding R² values close to 1.00 and a minimum RMSE of 2.87×10⁻⁴ W/(m²∙sr∙nm). Meanwhile, we extend the surrogate model to the calculation of Jacobian matrices of atmospheric and surface parameters, demonstrating high fidelity and stability. Preliminary results demonstrate the potential of the surrogate model for XCO₂ retrieval when embedded within the ACOS retrieval algorithm. This study provides a novel and efficient solution for high-speed XCO₂ retrieval, supporting real-time CO₂ monitoring and carbon flux estimation.