June 30 session – 2:00 p.m. – 3:00 p.m. : Access the webinarSession chair : Nicolas Sabouret
Harnessing Complex Systems with Agent-based Modeling, Machine Learning and High-performance Computing
In this presentation I will review efforts by our research group to formally facilitate the intersection of agent-based modeling, machine learning methods and high-performance computing, three areas of continuing general interest and growth, to tackle the intricacies of complex systems modeling.
I will provide a brief overview of agent-based modeling and discuss our widely used, free and open source Repast Suite of agent-based modeling toolkits (https://repast.github.io). I will then describe how our Extreme-scale Model Exploration with Swift (EMEWS) framework (https://emews.github.io) leverages advances in machine learning algorithms to enable large-scale model exploration of computational models, including agent-based models, on high-performance computing resources.
I will demonstrate applications of our approach across scientific domains where the three pillars of agent-based modeling, machine learning and high-performance computing provide the analytical platform for in silico experiments at the scales needed for deepening our understanding of important complex systems phenomena. Finally, I will describe future directions and our overarching goal of improving interoperability, scalability, transparency and reproducibility in complex systems modeling.