Using Deep Learning to Predict Wildfires with Feng Yan

Today we're joined by Feng Yan, Assistant Professor at the University of Nevada, Reno. Feng led a session at re:Invent on ALERTWildfire, a camera-based network infrastructure that captures satellite imagery of wildfires. ALERTWildfire was built to serve a few purposes, including the discovery of wildfires, the ability to scale resources accordingly, monitoring the behavior of said fires, assist in evacuations, and ensure contained fires are thoroughly monitored until completely put out. In our conversation, Feng details the development of the machine learning models and surrounding infrastructure used in ALERTWildfire. We also talk through problem formulation, challenges with using camera and satellite data in this use case, and how he has combined the use of Infra-as-a-Service and Function-as-a-Service tools for cost-effectiveness and scalability.