Alouette van Hove is a first year PhD candidate at the Department of Geosciences and part of the dScience center. She has an education and work experience in environmental science, fluid dynamics and programming. These aspects come together in her PhD project on developing a reinforcement learning framework to map greenhouse gas fluxes using drone sensor data.
To date, the accurate representation of surface fluxes of greenhouse gases in climate models remains a challenge. To bridge the scale gap between site observations and climate models, a novel framework is developed to map greenhouse gas fluxes at a regional scale. The framework exploits the flexibility of drones for atmospheric measurements and uses reinforcement learning to teach the drones the optimal locations for measurements.
In this seminar, Alouette will give an outlook on the development of the framework. She will demonstrate how reinforcement learning can be used to detect greenhouse gas hotspots and discuss the challenges of using reinforcement learning for a real-world problem.
Program
11:30 – Doors open and lunch is served
12:00 – "Reinforcement learning for surface flux mapping with drones" by Alouette van Hove (PhD Candidate, Section of Physical geography and Hydrology)
This event is open for all PhD candidates and postdocs. No registration needed.
About the seminar series
Once a month, dScience will invite you to join us for lunch, soft drinks and professional talks at the Science Library. In addition to these, we will serve lunch to PhD candidates in our lounge in Kristine Bonnevies hus every Thursday. Due to limited space (40 people), this will be first come, first served. See how to find us here (download).
Our lounge can also be booked by PhDs and Postdocs on a regular basis, whether it is for a meeting or just to hang out – we have fresh coffee all day long! Read more about the seminar series here.