CuMoLoS-MAE: A Masked Autoencoder for Remote Sensing Data Reconstruction

TL;DR

CuMoLoS-MAE is a novel deep learning model that reconstructs atmospheric data from remote sensing instruments, accurately restoring fine-scale features, quantifying uncertainty, and supporting improved climate and weather analysis.

Contribution

It introduces a curriculum-guided masked autoencoder with Monte Carlo sampling for uncertainty quantification in atmospheric data reconstruction.

Findings

High-fidelity reconstruction of atmospheric features

Effective uncertainty quantification at pixel level

Enhanced capabilities for climate reanalysis and real-time diagnostics

Abstract

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.