2021-04-22, 20:30–21:00, Track 2
Attend this talk to learn about ongoing and future work using deep learning techniques to remotely sense and assess building damage post-natural disaster, using Python.
Artificial intelligence, including machine learning and deep learning, have been increasingly utilized for humanitarian applications, from combating climate change to assessing car accidents. Specifically in the domain of geoscientific analysis, deep learning-based remote sensing has yielded many promising humanitarian applications and results. The occurrence of natural disasters is increasing in frequency and intensity due to climate change, and efficient and accurate computational methods of assessing the building damage caused post-disaster must be in place. This assessment aids in the allocation of resources and personnel. Using Python, we can develop convolutional neural networks and other deep learning architectures to detect and classify levels of infrastructure damage to inform disaster relief and recovery programs. A popular data source for doing so is real-time satellite imagery, which is much more easily gathered than data from on the ground. Other data sources include social media posts.