In many real-world applications, such as climate science, intelligent transportation, sports analytics, and physics, machine learning is applied to large-scale spatiotemporal data. Such data is often nonlinear,high-dimensional, and demonstrates complex spatial and temporal correlation. Deep learning provides a powerful framework for feature extraction, but existing models are still insufficient to handle the complex structures in spatiotemporal data.
In this talk, I will show how to design deep learning models to learn from large-scale spatiotemporal data, especially for dealing with non-Euclidean geometry, long-term dependencies and incorporating logical/physical constraints. I will showcase the application of these models to a variety of problems in transportation, sports, circuit design, and aerospace control. I will also discuss the opportunities and challenges of applying deep learning to large-scale spatiotemporal data.