Over the past few years, I have had the chance to mentor aspiring data scientists in their job search. In that process, I have also had opportunities to reflect on my own job search process. I realized that I've been conducting my own job search with a "sniper rifle" approach. Here's what that may look like, and why it may be extra important in the lean years.

Reading about Chicxulub crater (aka. "dinosaur killer") on wikipedia (as one does), I was surprised that connecting the crater to K–Pg boundary happened much more recent than I thought. Crater was discovered in 1981; linking it to K–Pg boundary happened in 1991.

Other things that happened in 1991 …

Just realized something cool - earlier in my career, I was studying solar cell dynamics that happens at sub-nanosecond timescale. Now I'm working to find mineral deposits generated by geological processes that happened up to 1000s MYA (million-years-ago). Time scale span of >25 orders of magnitude!

The machine learning breakthroughs for the past 10 years has been primarily focused on the bits world, and more and more industries are leveraging machine learning for their competitive advantage. On the other hand, the climate change issue is, inherently, a challenge in the atomic world. Therefore, if machine learning were to make an impact to climate change, it would have to render effects in the physical world. Having attended the ICLR Workshop on "Tackling Climate Change with Machine Learning" for the past five days, I want to organize my thoughts in this post on applying machine learning to the issue of climate change.

Notes from day 5 (Cross-cutting Methods Day) of ICLR Workshop - Tackling Climate Change with Machine Learning on 2020-04-30.

Notes from day 4 (Climate Science and Adaptation Day) of ICLR Workshop - Tackling Climate Change with Machine Learning on 2020-04-29.

Notes from day 3 (Agriculture, Forestry, and Other Land Use (AFOLU) Day) of ICLR Workshop - Tackling Climate Change with Machine Learning on 2020-04-28.

Notes from day 2 (Energy Day) of ICLR Workshop - Tackling Climate Change with Machine Learning on 2020-04-27.

Notes from day 1 (Main workshop) of ICLR Workshop - Tackling Climate Change with Machine Learning on 2020-04-26.

PyVista is a Python package for 3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK). I learned how to use the package in the past few weeks, and decided to build something fun to explore Python-based 3D visualization on the web.

I had so much …