Near Real-Time Dust Aerosol Detection with 3D Convolutional Neural Networks on MODIS Data
This work addresses the need for near real-time dust storm detection to mitigate health and visibility issues, though it is incremental with improvements in training speed and processing.
The researchers tackled the problem of detecting dust aerosols from satellite imagery for timely alerts, achieving about 0.92 accuracy and a mean squared error of 0.014 on 17 independent MODIS scenes.
Dust storms harm health and reduce visibility; quick detection from satellites is needed. We present a near real-time system that flags dust at the pixel level using multi-band images from NASA's Terra and Aqua (MODIS). A 3D convolutional network learns patterns across all 36 bands, plus split thermal bands, to separate dust from clouds and surface features. Simple normalization and local filling handle missing data. An improved version raises training speed by 21x and supports fast processing of full scenes. On 17 independent MODIS scenes, the model reaches about 0.92 accuracy with a mean squared error of 0.014. Maps show strong agreement in plume cores, with most misses along edges. These results show that joint band-and-space learning can provide timely dust alerts at global scale; using wider input windows or attention-based models may further sharpen edges.