Deep Learning Based Framework to Identify Undocumented Orphaned Oil and Gas Wells from Historical Maps (Bay Area Open Science Group January Meeting)
Event box
Zoom information + registration
This month the Bay Area Open Science Group will be joined by Dr. Fabio Ciulla. Dr. Fabio Ciulla is a postdoctoral research fellow in the Climate and Ecosystem Division at Lawrence Berkeley National Laboratory. He earned his M.S. degrees in Physics from the University of Rome La Sapienza and completed his Ph.D. at Northeastern University in Boston, focusing on nonlinear dynamics of diffusive phenomena on geographical networks. At Berkeley Lab, his research includes developing data-driven models to predict water quality and leveraging state-of-the-art machine learning algorithms to detect undocumented legacy oil and gas wells across the United States.
Undocumented Orphaned Wells (UOWs) in the U.S. pose environmental risks, including methane leaks and groundwater contamination. This study used historical topographic maps, available as open-source data from USGS, and a U-Net computer vision model to detect well symbols in the maps and flag UOWs when there is no match among known wells. Applied to areas in California and Oklahoma, it revealed 1,301 potential UOWs with high spatial accuracy.
Related article: Ciulla, F., Santos, A., Jordan, P., Kneafsey, T., Biraud, S. C., & Varadharajan, C. (2024). A Deep Learning Based Framework to Identify Undocumented Orphaned Oil and Gas Wells from Historical Maps: A Case Study for California and Oklahoma. Environmental Science & Technology. https://pubs.acs.org/doi/10.1021/acs.est.4c04413
Bay Area Open Science Group
The Bay Area Open Science Group is a growing community for Bay Area academics and researchers interested in incorporating open science into their research, teaching, and learning. Targeting students, faculty, and staff at UCSF, Berkeley, and Stanford, the goal of the community is to increase awareness of and engagement with all things open science, including open access articles, open research data, open source software, and open educational resources. Through this work the group hopes to connect researchers with tools they can use to make the products and process of science more equitable and reproducible.
Meetings:
We meet on the 4th Tuesday of the month, 2 - 3 PM Pacific on Zoom.
All are welcome to attend and join the conversation!
Looking for info from past meetups?
Find presentations and reflections from past meetups on Zenodo.
Contact:
Interested in joining the group or learning about future events?
Join the discussion on our Slack Channel or email Sam Teplitzky (samteplitzky@berkeley.edu).
Related LibGuide: Open Science by Sam Teplitzky
- Date:
- Tuesday, January 28, 2025
- Time:
- 2:00pm - 3:00pm
- Categories:
- Sciences