Aerosol type classification with machine learning techniques applied to multiwavelength lidar data from EARLINET Abstract. Aerosol typing is essential for understanding atmospheric composition and its impact on the climate. Lidar-based aerosol typing has been often addressed with manual classification using opti...

🚀 New paper out in Atmospheric Chemistry and Physics!

We present a machine learning approach for aerosol type classification using multiwavelength lidar data from the EARLINET network.

📄 Read it here: acp.copernicus.org/articles/25/...

#Aerosols #Lidar #MachineLearning #EARLINET #DeepAtmo #JdC

The kick-off meeting of the #DeepAtmo (Deep Learning for Atmospheric Components Classification and Aerosol Typing using Remote Sensing Measurements) project took place this morning at @iista.bsky.social 📡👩‍🔬

Great to have Diego Loyola, the Director of the Atmospheric Processors Department at @dlr-en.bsky.social visit to #GFAT. He delivered a talk on satellite sensors and exchange opportunities in the context of #IISTA Unidad de Excelencia #deepAtmo project. A fantastic collaboration opportunity!