Imbalanced Multi-layer Cloud Classification with Advanced Baseline Imager (ABI) and CloudSat/CALIPSO Data
Published in IEEE International Conference on Big Data, 2022
We tackle 8-class multi-layer cloud classification using GOES ABI satellite data with CloudSat/CALIPSO ground truth. Using Random Forest with data augmentation methods (SMOTE, ADASYN, ROS), we achieved 83.6% classification accuracy for climate and weather prediction applications.
Recommended citation: L. Ding, R. Corizzo, N. Ching, S. Login, R. Yepez-Lopez, C. Bellinger, J. Gong, D.L. Wu. "Imbalanced Multi-layer Cloud Classification with Advanced Baseline Imager (ABI) and CloudSat/CALIPSO Data." IEEE Big Data 2022.
Download Paper