Useful Resources from the 2020 AGU

The annual AGU conference was online this year due to COVID-19 and held between December 1-17. This exended time allowed for expanded scientific sharing. While we could go see posters and scientific talks galore, the conference also gave helpful technical talks and workshops on multiple scientific tools, such as popular research tools like machine learning, or techniques for better communicating science to the general public and to other scientists.

Our group had a meeting where we discussed talks, posters, and workshops that made our AGU experience memorable. Check out some of the links, videos, and review papers that we thought were  interesting!

 

AGU Videos:

1. Elizabeth Barnes. Explainable AI for the Geosciences. https://agu.confex.com/agu/fm20/meetingapp.cgi/Session/105991 or https://drive.google.com/file/d/1XFyX08xJOw8s_bPV2kcyMjSXDqYgqDeb/view?usp=sharing

2. Amy McGovern. Peering inside the Black Box of Machine Learning for Atmospheric Science. https://agu.confex.com/agu/fm20/meetingapp.cgi/Paper/665847

3. David Hall. Explaining the Frontiers of Deep Learning for Earth System Observation and Prediction. https://agu.confex.com/agu/fm20/meetingapp.cgi/Paper/696238

4. Elizabeth Barnes. Leveraging Interpretable Neural Networks for Scientific Discovery. https://agu.confex.com/agu/fm20/meetingapp.cgi/Paper/670855

5. Melissa Marshall. Powerful Posters: Tips & Tricks. https://projection.zoom.us/rec/play/wiQSJFtUp6EVQr2M-cf0AhNqfoYxQAWYoLS-S7ZW2IJ2cVgcMuTb4GLsxy5pZ4aYtEaCsEHf0IR-HiI5.tZvC0pTT2IkO5jLL

6. Melissa Marshall. Present Your Science: Transforming Technical Talks. https://projection.zoom.us/rec/play/GKfVVYJDMZiHLnLjdmS2zT6PczH8dwl-aJ58lr9kGGBeMU4wpVL0TqYLnKCvqjxiUcK6I1N5HT4K7dPf.AFXK1Lfcc47OORza

7. Tutorial on Machine Learning and Deep Learning for the Environmental and Geosciences. https://drive.google.com/file/d/1cCNuOXCAmr1f9Dbi3L498uNSUrV62Mtg/view?usp=sharing

Interesting Papers:

 

1. McGovern et al. 2019. Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning. (BAMS)

2. Ebert-Uphoff and Hilburn 2020. Evaluation, Tuning, and Interpretation of Neural Networks for Working with Images in Meteorological Applications. (BAMS)

3. Toms, Barnes, & Ebert-Uphoff 2020. Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability. (JAMES)

 

 

Cool Websites:

https://www.nationalacademies.org/based-on-science

https://skepticalscience.com/