Dr. David John Gagne II is a Machine Learning Scientist II and head of the Machine Integration and Learning for Earth Systems (MILES) group at the NSF National Center for Atmospheric Research (NCAR) in Boulder, Colorado. He has led the development of machine learning systems that enhance understanding and prediction of high impact weather and critical Earth system processes. He received his Ph.D. in meteorology from the University of Oklahoma in 2016 and completed an NCAR ASP Postdoctoral Fellowship before assuming his current role. He is a NSF AI2ES AI Institute leader and a NSF LEAP Science and Technology Center member. He is a WMO Nowcasting and Mesoscale Research Working Group member, chaired the American Meteorological Society Artificial Intelligence Committee, and serves as an editor for the AI for the Earth Systems journal, and has led summer schools, short courses, and hackathons.

Frequently Asked Questions

Q: What do you like to be called?

A: I prefer either David John or DJ. My last name is pronounced GAHN-yay. 

Q: What are good resources for learning about Artificial Intelligence and Machine Learning?

A: I recommend the following books, most of which are freely available online:

• An Introduction to Statistical Learning by G. James et al. (https://www-bcf.usc.edu/~gareth/ISL/)
• The Elements of Statistical Learning by T. Hastie et al. (https://web.stanford.edu/~hastie/ElemStatLearn/)
• Deep Learning by I. Goodfellow et al. (https://www.deeplearningbook.org/)
• Deep Learning with Python by F. Chollet (https://www.manning.com/books/deep-learning-with-python)
• Interpretable Machine Learning by Christoph Molnar (https://christophm.github.io/interpretable-ml-book/)

Q: What are some examples of machine codes applied to weather problems?

A: I have developed some tutorials on machine learning for weather problems using Jupyter Notebooks. You can find them below:

• AMS Short Course on Machine Learning in Python for Environmental Science Problems: https://github.com/djgagne/ams-ml-python-course
• Swirlnet Deep Learning Tutorial: https://github.com/djgagne/swirlnet
• California Rainfall Prediction Hackathon: https://www2.cisl.ucar.edu/events/workshops/climate-informatics/2017/hackathon