AI pinpoints renewable energy resources » Albuquerque Journal

………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ………. ……….

Copyright © 2020 Albuquerque Journal

All across New Mexico, a powerful energy source seethes in the Earth’s solid crust. Much of the state’s dramatic landscape, with its vast extinct volcanic caldera in the Jemez Mountains, the string of spikey volcanic necks standing tall in the Rio Puerco, Albuquerque’s lineup of volcano cones and lava escarpment – just to name a few – all hint at the presence of underground magma.

This bright orange molten rock is produced primarily by melting rocks in the Earth’s mantle, heated by the Earth’s core, which formed from star material when our planet was created. Decaying, naturally radioactive materials like uranium and potassium, along with other natural processes, also heat the core. According to the Union of Concerned Scientists, the energy given off by magma is impressive – the heat emitted within 33,000 feet of the Earth’s surface contains 50,000 times more energy than all the oil and natural gas resources in the world.

In the 1970s, scientists at Los Alamos advanced geothermal drilling technologies in order to mine heat from rocks cooked by magma to generate electricity. Today, energy companies drill deep underground in order to access superheated water in naturally occurring reservoirs. That superhot water and steam gush upward through another well into a generating station, where they drive turbines to make electricity.

……………………………………………………….

This form of geothermal energy produces no pollution, is renewable and sustainable (the water is recycled over and over), and compares favorably in cost to other forms of renewable energy.

There’s just one drawback – finding it.

Although traditional means of seeking out geothermal resources were successful at first, identifying such sites has become much more difficult and more expensive because most of the “hot spots” have already been discovered and mined.

Searching for hot rock turns out to be a risky financial proposition. Two to five out of every 10 possible sources of geothermal energy have ended up being unproductive, and that’s after investors spend $2 million to $5 million to build wells and generating stations. If a well stops producing heat before a company recovers its investment or makes a profit, it’s money down the drain.

To be blunt, the odds are stacked against alternative-energy explorers. That is, until now.

Rather than rely on humans to ascertain the key subsurface characteristics that make for ideal geothermal prospects, scientists at Los Alamos National Laboratory aim to dramatically improve geothermal exploration through machine learning – computer programs that can process vast amounts of data, learn from it, and then automatically modify their algorithms to analyze it with increasing accuracy and efficiency.

Rather than a team of scientists and engineers poring over huge stacks of images, maps and other data to hypothesize which sites are likely the best, these mountains of information are instead fed to a computer. New and powerful algorithms and statistical models – simplified and mathematically formalized ways to approximate reality – learn how to accurately and quickly identify new geothermal locations ideal for further exploration.

The computer’s learning never stops. As more information comes in, computer scientists feed it into the computer, which assimilates it and incorporates it into the existing data. As a result, the computer automatically improves its assessments based on new experiences, thus improving the odds when it comes to finding sources of hot dry rock that can produce sustainable geothermal energy for long periods of time.

……………………………………………………….

Machine learning is patterned after the human brain. As an example, think about how people have learned to halt at all stop signs. We learned this behavior as children, when our parents or other authority figures taught us the benefits of stopping at the red octagon-shaped sign with white lettering. Over time, we have learned through experience the benefits of obeying these signs (such as by avoiding accidents that result from not stopping), reinforcing our behavior. This idea of automatically learning the basics and then reinforcing them through experience is essential to how a machine artificially learns.

With funding from the Department of Energy’s Geothermal Technologies Office to apply machine-learning techniques to geothermal exploration and production, the Los Alamos team has worked on determining which data is ideal for a computer to learn from, as well as developing the fundamental algorithms, or computer instructions, and statistical models that will serve as the computer’s brain.

The team applied these techniques to data collected in a study area located in southwestern New Mexico and found unique signatures – various characteristics of the geology that are critical for discovering geothermal resources. Moreover, the algorithms the team used identified an association between New Mexico’s geothermal data with different geothermal provinces, such as the Colorado Plateau and the Basin and Range. Establishing these associations enables artificial intelligence to discover unknown geothermal resources in New Mexico.

According to the Energy Information Administration, nine western states, including New Mexico, together have the geothermal resources to provide more than 20% of the country’s electricity needs. With machine learning applied to geothermal exploration as one way to unearth harder-to-discover resources, the Department of Energy anticipates a significant increase in production from geothermal reservoirs. Having a better idea of where to look is a great place to start.

Velimir “Monty” Vesselinov of the Computational Earth Science group at Los Alamos National Laboratory is the principal investigator on a project researching geothermal resources in New Mexico. Other team members from the same group at Los Alamos are Richard Middleton and Maruti Mudunuru, both of whom contributed to this article.