Name:Lucas Astore

Bio:

AI researcher and PhD candidate specializing in machine learning for spatiotemporal forecasting, graph neural networks, and geospatial AI.

My research focuses on developing intelligent systems capable of modeling complex real-world phenomena, including transportation networks, environmental monitoring, Earth observation, and multivariate time-series forecasting. I have experience designing and implementing deep learning architectures for forecasting tasks, with particular interest in spatiotemporal learning, graph-based methods, and privacy-preserving AI.

In addition to predictive modeling, I have experience developing Agentic AI systems using LangGraph and LangChain, including multi-agent architectures, workflow orchestration, tool integration, and automated decision-making pipelines. My work explores how large language models can be combined with specialized agents to automate complex analytical and forecasting workflows.

Currently pursuing a PhD in Computer Science / Artificial Intelligence at the Federal University of Minas Gerais (UFMG), Brazil, and working as a Visiting Researcher at the Department of Mathematics and Statistics at Victoria University of Wellington, New Zealand.

Country:Brazil

Affiliation:Federal University of Minas Gerais (UFMG)

Research interests:Machine Learning, Spatiotemporal forecasting, AI Ethics, MultiAgentic Systems