Artificial intelligence has its sights set on America's oil and gas fields. Here's what to expect.

Evan Patrick

Large swaths of Wyoming are being developed today by extractive industries eager to tap into the state’s rich deposits of coal and natural gas.

These energy developments have picked up pace in recent years, raising questions over how people and natural resources will be affected by rising pollution and habitat changes. And soon, new technology coupled with artificial intelligence could provide some more answers.

A technique with applications that soared in recent years, Natural Language Processing, can use trained algorithms to process environmental filings and extract complex information and themes at a critical time.

What that drill project really means  

Natural Language Processing pulls out information similar to how humans get information from reading.

If developed and scaled up, it could turbo-charge critical analyses of oil and gas permit applications that companies submit under the National Environmental Protection Act. Other types of development proposals could benefit, too.

This would, in turn, help local regulators and other stakeholders in Wyoming and beyond determine whether a project will pose a threat to wildlife, water or a cultural heritage site – and to better balance industry claims.

Getting to the data that matters

Because of the onslaught of permit applications in regions such as eastern Wyoming, it’s a growing struggle to keep up with NEPA filings. The lack of standard formats for such documents makes it even harder to identify and flag potential problems.

This is where artificial intelligence comes in. By combining software and algorithms trained to “scrub” data from government websites, critical and potentially overlooked NEPA filings can be located, downloaded and processed in a matter of hours.

Future impacts of projects – such as pollution of a groundwater basin or habitat loss for an imperiled animal – can be identified and compiled on a spreadsheet, registry or an online map for everyone to see.

A new AI application

The prospect appealed to some people in the San Francisco Bay Area whom I first approached with this idea. They had an understanding of the technology and methods behind artificial intelligence, but nobody had considered it in the context of environmental permitting before.

What if local agencies could use it to streamline permitting processes for all kinds of projects? It would allow regulators to focus more of their energy on proposals that really matter.

Grueling work, big gains

My colleagues and I laid the groundwork for a Natural Language Processing project earlier this year, planning to use a trained computer program to assess future impacts on greater sage-grouse habitat in the western United States. Progress has been slow, however.

Getting artificial intelligence treatment of NEPA filings off the ground is a question of manpower, plain and simple.

It requires weeks of data entry to train algorithms, on top of high-level math and data processing skills – neither of which your typical watchdog group or local government office possesses. Many people today are too focused and worried about the rush of oil and gas developments to give artificial intelligence much thought.

But if we stop and consider what we’d gain – a grasp of what’s really happening in America’s rapidly developing rural areas – we may see just how much such advances could be worth. Advanced computer processing can help us catch problems that now fall through the cracks, and to react more quickly when we do find them.

Importantly, we’d have modern science and reliable data on our side.

Get innovation updates

We’ll send regular updates about developments in technology, science and the environment.

Thanks for subscribing to Innovation and the Environment.