CuMoLoS-MAE: A Masked Autoencoder for Remote Sensing Data Reconstruction
This work addresses data corruption issues in remote sensing for atmospheric science, offering a novel deep learning-based solution with uncertainty quantification, though it is incremental in applying masked autoencoders to this domain.
The paper tackles the problem of reconstructing accurate atmospheric profiles from noisy remote sensing data by introducing CuMoLoS-MAE, a masked autoencoder that restores fine-scale features like updraft cores and provides pixel-wise uncertainty estimates, enabling improved convection diagnostics and data assimilation.
Accurate atmospheric profiles from remote sensing instruments such as Doppler Lidar, Radar, and radiometers are frequently corrupted by low-SNR (Signal to Noise Ratio) gates, range folding, and spurious discontinuities. Traditional gap filling blurs fine-scale structures, whereas deep models lack confidence estimates. We present CuMoLoS-MAE, a Curriculum-Guided Monte Carlo Stochastic Ensemble Masked Autoencoder designed to (i) restore fine-scale features such as updraft and downdraft cores, shear lines, and small vortices, (ii) learn a data-driven prior over atmospheric fields, and (iii) quantify pixel-wise uncertainty. During training, CuMoLoS-MAE employs a mask-ratio curriculum that forces a ViT decoder to reconstruct from progressively sparser context. At inference, we approximate the posterior predictive by Monte Carlo over random mask realisations, evaluating the MAE multiple times and aggregating the outputs to obtain the posterior predictive mean reconstruction together with a finely resolved per-pixel uncertainty map. Together with high-fidelity reconstruction, this novel deep learning-based workflow enables enhanced convection diagnostics, supports real-time data assimilation, and improves long-term climate reanalysis.