Neven Fučkar (neven.fuckar[at]ouce.ox.ac.uk)
The scientific questions that will be studied:
– Detection and classification (supervised and unsupervised) of anomalies in observed, reconstructed and modelled sea ice variables.
– Comparison of machine learning, statistical and dynamical predictions.
– Attribution of sea ice trends and extreme events to anthropogenic forcing factors.
– How does sea ice variability and predictability evolve with global climate change?
The processes that will be investigated:
– Sea-ice-atmosphere-ocean interaction
– Influence of the atmosphere and oceans on formation of sea ice modes of variability and extreme events
– Storage and release of climate signals in sea ice variables with climate memory effects (thickness, volume and enthalpy)
The type of analyses that will be conducted:
– Analysis of CMIP6 simulations, and related large ensembles, observations and reanalysis products.
– Multi-method detection and attribution of trends and extreme events.
– Tools: K-means clustering, SOM analysis, mixture models, kernel methods, …
Examples of active projects
• How the structure and occurrence of Arctic SIT modes of variability evolves in CMIP6 projections
• Attribution of Arctic SIE extremes in today’s climate and at the end of 21st century.
References:
Reichstein, M., et al. 2019: Deep learning and process understanding for data-driven Earth system science. Nature, 566, 195–204. https://doi.org/10.1038/s41586-019-0912-1
Kim, Y. J., Kim, H.-C., Han, D., Lee, S., and Im, J.: Prediction of monthly Arctic sea ice concentration using satellite and reanalysis data based on convolutional neural networks, The Cryosphere Discuss., https://doi.org/10.5194/tc-2019-159, in review, 2019.
Fučkar, N.S., Guemas, V., Johnson, N.C. et al. 2019: Dynamical prediction of Arctic sea ice modes of variability, Clim Dyn 52: 3157. https://doi.org/10.1007/s00382-018-4318-9