Timezone: »

Ice Core Dating using Probabilistic Programming
Aditya Ravuri · Tom Andersson · Ieva Kazlauskaite · William Tebbutt · Richard Turner · Scott Hosking · Neil Lawrence · Markus Kaiser

Ice cores record crucial information about past climate. However, before ice core data can have scientific value, the chronology must be inferred by estimating the age as a function of depth. Under certain conditions, chemicals locked in the ice display quasi-periodic cycles that delineate annual layers. Manually counting these noisy seasonal patterns to infer the chronology can be an imperfect and time-consuming process, and does not capture uncertainty in a principled fashion. In addition, several ice cores may be collected from a region, introducing an aspect of spatial correlation between them. We present an exploration of the use of probabilistic models for automatic dating of ice cores, using probabilistic programming to showcase its use for prototyping, automatic inference and maintainability, and demonstrate common failure modes of these tools.

Author Information

Aditya Ravuri (University of Cambridge)
Tom Andersson (British Antarctic Survey)
Tom Andersson

I am a Data Scientist at the BAS Artificial Intelligence Lab (AI Lab) and funded by the Alan Turing Institute’s AI for Science programme. In my work, I aim to enable scientific progress through the application of machine learning algorithms to large datasets from climate models, satellites, and in-situ stations. I’m working on combining satellite and surface station data to inform weather sensor placement in Antarctica. My other research work involves the development of a deep learning-based sea ice forecasting system, ‘IceNet’ (initial study published in Nature Communications, for which I was awarded the World Meteorological Organization Young Scientist of the Year Award 2022).

Ieva Kazlauskaite (University of Cambridge)
William Tebbutt (University of Cambridge)
Richard Turner (University of Cambridge)
Scott Hosking (British Antarctic Survey)
Neil Lawrence (University of Cambridge)
Markus Kaiser (Monumo)

More from the Same Authors