Starts 13 May 2021 15:00
Ends 13 May 2021 16:30
Central European Time
Search
Search in Conferences:
Artificial intelligence for climate impacts
Zoom Meeting
Lecture 10 of series on
Environmental Meteorology: From the Fundamentals of Climate to Operational Applications
Register in advance for this meeting:
https://zoom.us/meeting/register/tJ0lcuyurDMrEtbfP9f16GRLzqF1AiT7PHN7
After registering, you will receive a confirmation email containing information about joining the meeting.
Abstract: Climate change adaptation in both public and private sectors urgently requires better risk quantification tools to inform decision-making and planning across multiple timescales. In this presentation, I will give an overview of the research activities in IBM’s “AI for Climate Impacts” research theme, an initiative to build resilience to climate change by developing AI-enhanced and cloud-enabled models to quantify climate risk. I will describe applications of AI techniques to the specific challenge of improving flood risk quantification, including the use of simulation model surrogates, automated ground truth mapping and model calibration, and machine learning approaches to quantifying and propagating multiple sources of uncertainty.
Environmental Meteorology: From the Fundamentals of Climate to Operational Applications
Register in advance for this meeting:
https://zoom.us/meeting/register/tJ0lcuyurDMrEtbfP9f16GRLzqF1AiT7PHN7
After registering, you will receive a confirmation email containing information about joining the meeting.
Abstract: Climate change adaptation in both public and private sectors urgently requires better risk quantification tools to inform decision-making and planning across multiple timescales. In this presentation, I will give an overview of the research activities in IBM’s “AI for Climate Impacts” research theme, an initiative to build resilience to climate change by developing AI-enhanced and cloud-enabled models to quantify climate risk. I will describe applications of AI techniques to the specific challenge of improving flood risk quantification, including the use of simulation model surrogates, automated ground truth mapping and model calibration, and machine learning approaches to quantifying and propagating multiple sources of uncertainty.