University of Cambridge > Talks.cam > CEDSG-AI4ER > Probabilistic machine learning as an algorithmic interface to weather model and environmental data

Probabilistic machine learning as an algorithmic interface to weather model and environmental data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tudor Suciu.

As the volume of data we collect and generate skyrockets, how can we maximise the utility of this data for the purposes of environmental science and management? In this talk I will outline the challenge of our current situation, and why I think probabilistic machine learning should be part of the solution (I get the feeling you won’t be a tough crowd on this point!). I will share examples from my research at the University of Exeter and the Met Office, including quantile regression forests for weather forecast post-processing, and Bayesian deep learning for end-to-end modelling of environmental variables – atmospheric and lithospheric. The insights from these projects contribute to the idea of ‘algorithmic interfaces’ as key to the future provision of environmental information.

This talk is part of the CEDSG-AI4ER series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity