Loading Events

Increasing Our Societal Resilience to Physical Climate Risks Using Earth Observation

Webinar Speaker:

Subit Chakrabarti

Affiliation:

Floodbase

About the Webinar

Over the last thirty years, the amount of human development has exponentially increased in every part of the world. Meanwhile, extreme weather events such as tropical storms, wildfires, earthquakes, and dangerous temperatures, have become more frequent, and more severe due to climate change. This confluence results in far higher levels of short term and long term physical risk to property, human lives and livelihood than previously encountered. It may not be immediately obvious but a lot of the institutions which allow communities to prosper require robust, tractable estimates of physical risk and close monitoring of hazardous events. For example, a regional bank with a narrow lending portfolio can be driven to bankruptcy if its assets (loan repayments) collapse in value simultaneously as its collateral, or a refugee camp being built on a floodplain could severely compromise relief efforts.

Earth observation is one of the best tools we have to measure and mitigate physical risk, and subsequently, respond to natural hazards when they happen. It enables precise monitoring of environmental changes, facilitates early warning systems for impending hazards, and offers critical insights for vulnerability assessments. This talk reviews the developments in the use of computer vision and earth imagery in the public and private sector to address physical risk. Challenges that are yet to be adequately addressed will also be discussed, along with a way forward for propagating recent developments to organizations that can make a difference on the frontlines.

 

About the Speaker

Subit is VP of Technology at Floodbase where he manages a team of scientists and engineers with the goal of producing high-quality maps of peak flood extent relevant to the needs of disaster responders, flood managers, and insurers. His technical expertise and interest is in developing novel spatio-temporal machine learning methods applicable for large-scale earth imagery. He has a PhD in Electrical Engineering from the University of Florida where his thesis focused on machine learning-based superresolution of microwave imagery for land surface and biophysical models. Prior to Floodbase, Subit worked as a data scientist at Indigo Agriculture and Telluslabs on machine learning-based mapping of crop types, regenerative farming practices and crop yields using satellite imagery.

Recorded Webinar

Looking for an older Event? See our Past Events. Events prior to April 2024 can be found in our Events Archive.