These algorithms helped scientists find between five and 19 million tons of lithium. We also look at why geos should make sure our voices are heard as geothermal tech continues to develop.
There were some big developments in the world of technology and innovation this week! Unless you’ve been living under a rock—again always possible and understandable with geos, who love rocks that much—you’ve heard about the lithium discovery under Arkansas. We go a bit deeper into that as well as take a look at a steaming hot topic of today: geothermal! Let’s dive in.
Sarah Compton
Editor, Enspired
These AI Algorithms Drove the Recent Arkansas Lithium Discovery
Deemerwha Studio/Shutterstock.com
A hitch in the giddy-up of electric vehicle adoption is the sheer volume of lithium required, but the recent discovery in southeastern Arkansas might change that.
Driving the news: A group of researchersat the USGS used an AI algorithm called a random forest to estimate the in-place volume of lithium in the Smackover formation in Arkansas. They estimated there was somewhere between five and 19 million tons of lithium there.
Why it matters: If this lithium is commercially viable, it would provide nine times the projected demand for EVs in 2030.
Additionally, the random forests technology they used to make the discovery was an interesting example of how AI is being used in upstream energy.
I hopped on Phind.com to learn more about random forests and a combination of responses from IBM, Wikipedia, and other sites was given. Here’s what I learned:
Random forests combine the output of multiple decision trees to reach a single result.
Decision trees start with a basic question and ask a series of questions to determine an answer.
An example from IBM.com was a decision reflecting the process behind the question, “Should I go surfing?” Inputs to arrive at a “yes” or “no” answer included high/low wind conditions and direction.
Why random forests? The researchers tuned their model using the tidy-models framework in R to test XGBoost, K-nearest neighbors, and random forest algorithms, and since the random forest algos had higher accuracy and lower bias, that was used to train the final model and predict lithium concentrations.
While the estimates are exciting, the researchers were sure to point out that these were in-place estimates only. Future work will have to include studies on what is technically recoverable.
IMAGE Highlight with Joe Zhou, SVP Earth Data Americas, Viridien
Ali Sloan with AAPG visited with Joe Zhou at IMAGE to talk about Viridien’s new Laconia 3D sparse OBN survey in the Gulf of Mexico, which uses innovative imaging technologies to pinpoint complex sub-salt geometries.
There’s a lot of excitement around geothermal, and for a good reason, but the oil and gas industry needs to be part of the conversation so messaging is accurate. The opportunity to transfer skills, tech, and learnings from oil and gas—especially on the geoscience side—to geothermal is massive, but caution is warranted.
Jamie Beard, the founder of Project InnerSpace, which aims to kickstart geothermal drilling by using expertise from oil and gas, sat down for an interview with Clean Energy and had good insights.
Her main point:
The oil and gas industry’s enthusiasm and expertise in testing and adopting new technologies could help quickly propel geothermal forward in a manner similar to the Shale Boom.
The tech that helped us during the Shale Boom is quite similar to the tech geothermal needs.
BUT… she also said some things that set off warnings in my head.
The warnings are related to challenges. Here are some of my thoughts on what Beard shared in the interview:
Depth and temperature. Oil and gas can drill to depths where geothermal can be useful, but rarely do we drill deep and hot. Heat requires different materials and the typical sensors we use to guide our drilling won’t work, or work very poorly, at temperatures useful to geothermal.
Yes, we can learn from fracking, but fracking was not profitablefor a while. We need to make sure we help out with economic evaluations, using lessons learned about where the biggest cost efficiencies might exist and looking at how we can maximize production.
Fracking impacts the reservoir we drill into— from pressure gradients to produced fluids. For geothermal, the temperature impacts are going to be a big driver, and some fracking fluids, like cross-linked gels, have temperature dependent behaviors.
Petroleum geoscientists have a lot of skills that transfer to geothermal nicely, such as finding, defining, and exploiting reservoirs, and we have the skillset to be cognizant of where and how the differences in tapped resource (heat vs hydrocarbons) will drive differences in operational behaviors.
We definitely should make sure our voices and insights are heard in these conversations as processes and technologies continue to develop.
👍 If you enjoyed this edition of Enspired, consider supporting AAPG's brand of newsletters by forwarding to a friend or colleague and signing up for our other newsletters here.
➡️ Was this email forwarded to you? Sign up for Enspired here.
✉️ To get in touch with Sarah or suggest a topic for Enspired, send an email to editorial@aapg.org.
AAPG thanks our advertisers for their support. Sponsorship has no influence on editorial content. If you're interested in supporting AAPG digital products, reach out to Melissa Roberts.
.png?upscale=true&width=220&upscale=true&name=Sarah-Compton-Headshot-Signature%20(1).png)
