Emulation of Forward Modeled Top-of-Atmosphere MODIS-Based Spectral Channels Using Machine Learning

Abstract

Satellites provide invaluable data regarding climate and weather patterns on a global scale. Satellite observations are crucial in studies aimed at understanding and monitoring the Earth's atmosphere and surface properties. The forward modeling problem computes radiances or reflectances based on surface and atmospheric state knowledge using radiative transfer modeling (RTM). RTTOV, a widely utilized RTM, serves both operational and research applications. This study presents a machine learning (ML) emulator designed to significantly accelerate the acquisition of satellite observations across 36 spectral channels. The ML model predicted 369 303 points across these 36 channels in less than 14 s, showcasing its potential over the much more costly RTTOV emulations. We employ supervised learning to compare the performance of three ML models: Random forest (RF), neural networks (NN), and convolutional neural network (CNN). These models were trained on high-resolution large-eddy simulations in a realistic weather prediction setting over Germany and forward-simulated MODIS-based spectral channels. Our approach achieves strong correlations between predicted and reference data across most of the 36 channels in the test dataset. The R2 metric averaged across the 36 channels is 0.91 for the RF model, 0.93 for the NN model, and 0.90 for the CNN model. The normalized RMSE averaged across the 36 channels is 4.07% for the RF model, 3.69% for the NN model, and 4.35% for the CNN model. We discuss the performance of the models in the validation and combined test dataset, as well as in independent channels and timesteps to understand how robust the model is to different data distributions. Overall, the results highlight the potential of ML to replace costly RTM models while maintaining high accuracy in emulating radiance and reflectance. In addition, we generated visible satellite images from the predictions to qualitatively inspect the models' performance.