Climate scientist - Understanding sea ice changes through machine learning, climate modelling, and remote sensing
About
Welcome! I'm a postdoctoral research associate at Princeton University, working within the Geophysical Fluid Dynamics Laboratory (GFDL) Ocean and Cryosphere division.
My work primarily seeks to improve our understanding of sea ice predictability across different timescales, so that we can develop prediction tools that better serve society. To achieve this, I use Machine Learning (ML) algorithms as tools to improve observations over sea ice, and also help bridge the gap between
observations and sea ice model physics. I am currently hired under the M2LInES initiative (Multi-scale Machine Learning In coupled Earth System modeling),
which is a programme dedicated to the improvement of climate model physics through novel ML techniques. For more information on my research activities, you can check out my
academic CV, or my Google Scholar.
I am also currently in the process of developing a series of educational Python notebooks which cover the fundamental concepts of various statistical and ML methodologies.
The aim is to cover concepts related to linear algebra, as well as supervised/unsupervised learning techniques; starting from linear regression and working towards deep neural networks. These notebooks will be routinely uploaded to the Code page of this website.