Computational Intelligence Techniques Applied to a Preliminary Exploration of Climatic Traits using Meteosat Water Vapor Images

Meteorological satellites are crucial for understanding and forecasting the flow dynamics of the General Atmospheric Circulation System. They produce large amounts of image information whose analysis and interpretation poses numerous challenges. A collection of computational intelligence techniques are used for investigating the structure of a large series of water vapor (WV) band images from ESA Meteosat satellites from 2009-2020. They include the use of the Visual Information Fidelity image quality measure, intrinsic dimensionality, Uniform Manifold Approximation and Projection (with density information) and deep learning (variational autoencoders, convolutional neural networks and transfer learning). The variational autoencoder extracted features that characterize Water Vapor dynamics, distinguished different season patterns, exposed their interrelationships and provided highly effective classification features. Dimensionality reduction was highly instrumental applied to the VAE's latent spaces, and to VIFp image disimilarity analysis in a novel approach applied to major geographical areas. Supervised classification with deep learning and with the XGBoost algorithm on VAE's latent space, produced highly accurate models for predicting seasons. This computational intelligence approach provided insights about atmospheric dynamics as seen from the WV band images and suggested possible weather-teleconnection processes, as well as new ways for finding signs of unusual climate behavior.