Deep learning for Aerosol Forecasting
This work addresses biases in aerosol forecasting for environmental and climate research, representing an incremental improvement over existing reanalysis methods.
The study tackled biases in aerosol optical depth (AOD) forecasts from reanalysis datasets by developing a hybrid deep learning model combining a convolutional neural network with MERRA-2 data, resulting in better estimates validated against ground truth measurements from AERONET sites globally.
Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth. Biases identified with the NASA Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) aerosol optical depth (AOD) dataset, against the Aerosol Robotic Network (AERONET) ground measurements in previous studies, motivated the development of a deep learning based AOD prediction model globally. This study combines a convolutional neural network (CNN) with MERRA-2, tested against all AERONET sites. The new hybrid CNN-based model provides better estimates validated versus AERONET ground truth, than only using MERRA-2 reanalysis.