Advanced Methodologies for Time Series Analysis: From Preprocessing to Deep Learning for Event Detection and Variable Prediction


  • Carlos Cano Domingo, Barcelona Supercomputing Center


This tutorial delves into the methodologies of time series research, tailored for artificial intelligence applications. Participants will embark on a comprehensive journey beginning with data preprocessing—structuring datasets to meet AI requirements. We will explore classical statistical processing using R, setting the groundwork for advanced analysis. The tutorial then transitions to sophisticated deep learning models, focusing on the detection of hidden events and the prediction of variables within time series data. By blending traditional techniques with cutting-edge AI, attendees will gain a multi-layered skill set for tackling complex temporal data challenges. The objective is to equip researchers and practitioners with the tools and knowledge to enhance predictive accuracy and event identification in various domains.

Short Bio:

Carlos Cano Domingo is a Post-Doctoral Researcher at the Barcelona Supercomputing Center, specializing in AI for Next Generation Battery technology since 2019. He completed his PhD in Electromagnetism and AI at the University of AlmerĂ­a, focusing on Earth-Ionosphere resonances through AI. His work includes studying Schumann Resonance transient events and their implications for electromagnetic phenomena and earthquake forecasting using deep learning. Currently, his research applies AI in renewable energy and battery management, using causal inference to uncover hidden events in time series data, aiming to enhance system behavior prediction.