Leveraging AI for Disaster-Resilient Infrastructure Mitigation Planning
With increased frequency and severity of disasters, mitigation planning in critical infrastructures such as transportation and water systems in a key strategy in improving resilience and reducing the potential threats to society. However, identifying the most cost-effective mitigation investments requires reasoning about complex infrastructure networks and connectivity, as well as limited budget resources. In this talk, I will present our AI approaches for two important use cases. First, I will demonstrate approaches for maximizing mobility in road networks with respect to flood hazards, and our ability to combine machine learning predictive models with planning optimization. Second, I will present our work in Los Angeles on scalable Mixed-Integer Programming approaches to mitigation planning for water infrastructure resilience to earthquakes.
Bistra Dilkina is an Associate Professor of Computer Science at the University of Southern California and the co-Director of the USC Center for AI in Society (CAIS). She is an AI expert with a focus on discrete optimization, network design, and the integration of machine learning and combinatorial optimization. Dilkina is one of the faculty leaders in the young field of Computational Sustainability, fostering research on use-inspired computational methods to help solve some of the key challenges concerning environmental, economic, and societal issues on the path towards a sustainable future. She has made key contributions on using Artificial Intelligence for biodiversity conservation, disaster-resilient infrastructure mitigation planning, and climate impacts.