Data Science Seminar
Time: 2 to 3 pm
Venue: NKN Hall
Approximation of Large Stiff Acausal Models
JuliaHub Inc., USA.
Simulations drive mission-critical decision making in many fields, but are prone to computational intractability, which severely limits an engineer's productivity whilst designing practical systems. These issues are alleviated by the use of approximate models called surrogates, which match the full system to high fidelity whilst being feasible to simulate. In this research, we propose a method to generate surrogates of dynamical systems with multiple widely separated timescales, called the Continuous Time Echo State Networks. We also study deployment of such systems to accelerate common tasks such as global optimization and global sensitivity analysis through practical applications from building simulation, quantitative systems pharmacology and electrical circuit design. Lastly, we examine how to data-efficiently sample a model’s input space to produce a surrogate with a desired error performance.
Bio: Ranjan is a sales engineer at JuliaHub Inc., where he helps clients use JuliaSim, a cloud-based modeling and simulation platform. He is set to graduate with a PhD in Mathematics and Computational Science from MIT in 2023, where his thesis work focused on building surrogate models for large dynamical systems that exhibit multiple timescales. He also is the lead maintainer of Circuitscape.jl, a tool used by landscape ecologists worldwide to design policy around species conservation. He has been a Julia language developer since 2015 and is also the executive chair at JuliaCon 2023.