Scientists have recently introduced a new algorithm that combined deep learning and transfer learning to improve aerosol monitoring on China’s FY-4A satellite.
The study, published in the journal engineering, was conducted through a collaborative effort by the Institute of Atmospheric Physics of the Chinese Academy of Sciences, National Satellite Meteorological Centre, the Harbin Institute of Technology and other institutes said on Monday.
Scientists believed that accurate measurements of atmospheric aerosols were pivotal in understanding Earth’s radiation balance, climate change, and air quality.
Aboard China’s geostationary meteorological satellite FY-4A, the Advanced Geostationary Radiation Imager, AGRI, scans China every five minutes, providing crucial data for monitoring aerosol spatiotemporal variations.
However, the inflexibility of traditional physical retrieval algorithms, coupled with the insufficient number of ground-based sunphotometer sites.
It posed challenges in meeting the extensive sample requirements for machine learning in aerosol optical depth, AOD, retrieval.0000000000
In response to these challenges, the scientists developed an innovative AOD retrieval algorithm that combines deep learning and transfer learning.
READ ALSO: Reps to enact law on untapped mineral resources
The new algorithm incorporated key concepts from the dark target and deep blue algorithms to facilitate feature selection for machine learning and indicated that Independent validation confirmed that the algorithm was highly accurate in estimating AGRI aerosol levels.
The results showed a strong correlation with expected values, indicating the algorithm’s reliability in predicting aerosol optical depth.
“Our study showcases the significant potential of merging the physical approach with deep learning in geoscientific analysis.
“The proposed algorithm holds promise for application to other multi-spectral sensors aboard geostationary satellites”, the lead author, Fu Disong from the IAP said.
Credible news.ng
