MAR 01, 2021 11:46 AM PST

Automating the forecasting of oil and gas reserves

A study published in the journal Applied Energy describes a series of algorithms developed by Texas A&M researchers that can be used to predict subterranean oil and gas reserves. The algorithms intend to automate the process of characterizing features such as porosity and permeability of rocks in the underground environment that provide key information to quantifying natural resource reserves.

"Subsurface systems that are typically a mile below our feet are completely opaque,” explains associate professor Siddharth Misra, who teaches in the Department of Geology and Geophysics. “At that depth, we cannot see anything and have to use instruments to measure quantities, like pressure and rates of flow. Although my current study is a first step, my goal is to have a completely automated way of using that information to accurately characterize the properties of the subsurface."

With that in mind, Misra’s team developed a reinforcement-based machine-learning algorithm. This kind of machine-learning may sound familiar to anyone who has trained a pet before, for, in this system, the algorithm is rewarded for favorable predictions and penalized for unfavorable ones; this ultimately helps it to learn to make decisions based on the feedback it receives.

"Imagine a bird in a cage. The bird will interact with the boundaries of the cage where it can sit or swing or where there is food and water. It keeps getting feedback from its environment, which helps it decide which places in the cage it would rather be at a given time," Misra elaborated. "Algorithms based on reinforcement learning are based on a similar idea. They too interact with an environment, but it's a computational environment, to reach a decision or a solution to a given problem."

It turns out that this kind of reinforcement-based learning is quite effective (for pets, humans, and algorithms!). The researchers report that that within a mere 10 iterations of reinforcement learning, the algorithm was able to rapidly and accurately forecast the properties of simple subsurface environments.

"A subsurface system can have 10 or 20 boreholes spread over a two- to five-mile radius. If we understand the subsurface clearly, we can plan and predict a lot of things in advance, for example, we would be able to anticipate subsurface environments if we go a bit deeper or the flow rate of gas at that depth," Misra said. "In this study, we have turned history matching into a sequential decision-making problem, which has the potential to reduce engineers' efforts, mitigate human bias and remove the need of large sets of labeled training data."

Misra says his team hopes to continue developing these algorithms to improve their accuracy and efficiency within more complex environments. In addition to predicting oil and gas reserves, he says the algorithms can also forecast seismic hazards and groundwater reserves.

Sources: Applied Energy, Science Daily

About the Author
  • Kathryn is a curious world-traveller interested in the intersection between nature, culture, history, and people. She has worked for environmental education non-profits and is a Spanish/English interpreter.
You May Also Like
AUG 15, 2021
Plants & Animals
The Killer Instinct of a Dainty Flower is Finally Exposed
AUG 15, 2021
The Killer Instinct of a Dainty Flower is Finally Exposed
The exotic Venus flytrap is a famous carnivorous plant that's easy to identify. But it seems that another carnivorous pl ...
SEP 07, 2021
Plants & Animals
All dogs may be descended from the same 23,000-year-old Siberian ancestor
SEP 07, 2021
All dogs may be descended from the same 23,000-year-old Siberian ancestor
New research suggests that all modern dogs are descended from the same 23,000-year-old Siberian ancestor
SEP 08, 2021
Plants & Animals
Are the skeletons of macaque hybrids distinct?
SEP 08, 2021
Are the skeletons of macaque hybrids distinct?
New research sheds insight into the evolution of the human pelvis by using macaque hybrid models.
SEP 29, 2021
Space & Astronomy
When a Meteor Destroyed an Ancient City, It May Have Inspired Biblical Tales
SEP 29, 2021
When a Meteor Destroyed an Ancient City, It May Have Inspired Biblical Tales
This meteor may have caused a blast as large as the one in the Tunguska Event, and totally flattened a city.
OCT 21, 2021
Chemistry & Physics
The Threat of Satellite Swarms
OCT 21, 2021
The Threat of Satellite Swarms
Gazing up at the night sky as a child, I loved to point out the satellites blinking in the night sky. Often, I could see ...
OCT 26, 2021
Earth & The Environment
Glomalin, The Protein that Can Heal the Earth
OCT 26, 2021
Glomalin, The Protein that Can Heal the Earth
Soil quality is growing ever more important as we attempt to feed the growing world population. Our soils are being degr ...
Loading Comments...