Title: Uncertainty Quantification in Deep Spatiotemporal Forecasting and Decision Making

Abstract: Deep learning is gaining increasing popularity for spatiotemporal forecasting. However, prior works have mostly focused on point estimates without quantifying the uncertainty of the predictions. In high-stakes domains, being able to generate probabilistic forecasts with confidence intervals is critical to risk assessment and decision making. In this talk, I will present (1) a systematic study of uncertainty quantification (UQ) methods for deep spatiotemporal forecasting. We analyze UQ methods from both the Bayesian and the frequentist point of view, casting in a unified framework. (2) Interactive Neural Process (INP), an interactive framework that integrates Bayesian active learning, stochastic simulation and deep sequence modeling. We propose a new acquisition function that can quantify the uncertainty of deep learning models to query new data. We demonstrate the use case of our methods on COVID-19 forecasting and scenario creation. Bio: Dr. Rose Yu is an assistant professor at the University of California San Diego, Department of Computer Science and Engineering. She was a Postdoctoral Fellow at the California Institute of Technology. Her research focuses on advancing machine learning techniques for large-scale spatiotemporal data analysis, with applications to sustainability, health, and physical sciences. A particular emphasis of her research is on physics-guided AI which aims to integrate first-principles with data-driven models. Among her awards, she has won Faculty Research Award from Facebook, Google, Amazon, and Adobe, Several Best Paper Awards, Best Dissertation Award in USC, and was nominated as one of the ’MIT Rising Stars in EECS’.

Bio: Dr. Rose Yu is an assistant professor at the University of California San Diego, Department of Computer Science and Engineering. She was a Postdoctoral Fellow at the California Institute of Technology.  Her research focuses on advancing machine learning techniques for large-scale spatiotemporal data analysis, with applications to sustainability, health, and physical sciences. A particular emphasis of her research is on physics-guided AI which aims to integrate first-principles with data-driven models. Among her awards, she has won Faculty Research Award from Facebook, Google, Amazon, and Adobe, Several Best Paper Awards, Best Dissertation Award in USC, and was nominated as one of the ’MIT Rising Stars in EECS’.