Applications of artificial intelligence to satellite data for extreme weather forecasts

Lead Research Organisation: Imperial College London
Department Name: Dept of Physics

Abstract

The frequency and resolution of Earth Observation data of clouds and other atmospheric/ocean variables is rapidly growing. To optimally deploy this information there is emerging interest to apply new approaches in machine learning to this data for faster weather forecasting suitable for emergency response and other applications. In this multidisciplinary project you will research the possibility of combining machine learning, the latest Earth Observation data and state of the art numerical weather prediction models to anticipate changes in weather. We are particularly interested in better forecasts for high impact extreme weather such as tropical cyclones, storms, cold and heat spells. The project meets two of the UKs industrial strategic priorities: the exploitation of satellite earth observation technology through the application of artificial intelligence. The industrial partner will make a contribution of £1000 per annum to the student and in-kind contribution in terms of annual industrial placement and expertise in artificial intelligence.

Publications

10 25 50
 
Description Tropical cyclones effect the atmospheric environment over much larger spatial scales than we previously thought and this may contribute to our understanding of the frequency of tropical cyclone occurrence. Additionally, understanding this environmental effect can improve our forecasts for individual tropical cyclones.
Exploitation Route We could try to determine the spatial extent of a tropical cyclones effect on the ocean
We could try to determine the temporal extent of the tropical cyclones effect on the atmosphere, how long does it take for the atmosphere to return to its baseline state?
We could try to determine the temporal extent of the tropical cyclones effect on the ocean, how long does it take for the ocean to return to its baseline state?
We could relate the pattern of the cyclone's effect on the atmosphere to cyclone properties such as intensity, rainfall, size and movement.
Sectors Aerospace, Defence and Marine,Agriculture, Food and Drink,Communities and Social Services/Policy,Creative Economy,Environment,Financial Services, and Management Consultancy,Government, Democracy and Justice,Transport

 
Description Imperial outreach programme - community center visit 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Increase the awareness of school children aged 5-10 of the effects of climate change. The topic in this instance was the effect upon biodiversity.
Year(s) Of Engagement Activity 2018