Highlights from the Invest with James West podcast with Dr. Troy Ruths, Founder and CEO of Petro.ai, and Dr. Mark Zoback, Stanford University Professor of Geophysics, Director of the Stanford Natural Gas Initiative, and Technical Advisor at Petro.ai
James West: What is geomechanics and why does it apply to the development of unconventional reservoirs?
Mark Zoback: To me, it’s the integration of the physical properties of the geologic formation, the fractures, and the other attributes that they have in a geomechanical sense. But, most importantly, it’s the forces that are acting in the rocks. That’s at the core of development of unconventional resources, because the key technology is horizontal drilling and multistage hydraulic fracturing.
Hydraulic fractures follow the stresses in the rock. In other words, once you know what the forces are, you can be predictive about what the hydraulic fractures would like to do.
JW: At this stage, how is machine learning and AI being applied?
Troy Ruths: In a previous podcast, I talked about AI being at the bottom of the pyramid. In this respect, what we’re trying to do is make it easier for the end user to get access to data types, run the interpretation, and then collaborate and predict on those within the context of geomechanics.
The other big area is fingerprinting patterns. Let’s say you have a productivity pattern or that one interval is more productive than the other. If we can tie that to a key variable going through a nice technical analysis from the perspective of geomechanics, then you can go look for that fingerprint elsewhere.
We’ve had a lot of success doing that and I think that’s two big places where AI and Machine Learning have really helped act as a catalyst for a lot of these principles that Mark has put together in the book that he just put out.
MZ: Even after a couple of hundred thousand wells, which means a couple of millions of hydraulic fractures, we still have recovery factors of only 25% for gas and less than 10% for oil. So, we’re leaving more than 90% of the oil behind.
We can take these new ideas and then using the tools of Petro.ai, test those ideas against existing data and frame the problem in a whole new way to gain understanding. It’s one thing to have an idea, but it’s another thing to know whether that idea is going to work before you try to implement that idea at scale.
That combination of bringing new ideas and then confirming the applicability of those new ideas in an area of particular interest to a particular company—that’s where we’re going to really leverage these new ideas. We can figure out what’s important and what’s not and then try to attack this recovery factor problem, because we haven’t solved that through brute force and trial and error.
All of these questions surround the idea of vertical hydraulic fracture growth. We think about hydraulic fractures growing horizontally away from the horizontal well, but they also grow vertically. That’s controlled by the forces in rock and how you do the hydraulic fracturing. Well, if hydraulic fractures are growing up, they’re not growing out. The issues of well spacing, infill drilling, and stacked pay are all linked in a three-dimensional way to a condition presented to you by the Earth. You can’t change that. But, if you can characterize it and link it to the completion process, you have a shot at optimizing.
JW: If we defined the 2017 to 2019 era in US onshore as what my colleague Steve Richardson eloquently pointed out as “the megapad misstep era.” What would you say were the reasons some of the companies erred and how they corrected course since then?
TR: There’s substantial interaction between parent wells and wells that are landed in different zones. So, the assumption that you can take a type curve and multiply it by well counts has been proven not to be a viable way to understand how you’re exploiting that cube.
When you step into that 3D problem, you need to take into account the vertical propagation of fractures and the interactions of wells that are brought online at the same time versus brought online at different times.
All of that is explainable through these concepts that Mark is talking about and is something that you can measure and actually infer ahead of time.
As we step into this next era of megapads, people are realizing that they just can’t develop intervals. They need to develop the entire pad together.
JW: So what inning do you think the North American unconventional oil and gas industry is in now in terms of drilling and completion efficiencies?
MZ: I’d say we’re in the sixth or seventh inning with respect to drilling efficiencies. It’s remarkable what’s being done out there in terms of drilling and completions efficiency, but I think we’re in the second inning when it comes to understanding about what should be done. We know how to do it. We know how to do it efficiently, but I don’t think we really understand. We have a lot of data under our belt now, but there are literally millions of wells that could be used to exploit unconventional hydrocarbons in the Lower 48. Before taking advantage of any of these opportunities, we have to start incorporating a better understanding of what to do regardless of how efficiently it could be done.
JW: How do you and the geomechanics team bring it all together at Petro.ai?
TR: You know James, we’re trying to reinvent the workflow and I think we’ve talked about this in a lot of different ways. When I put the Petro.ai team together with Mark, I wanted to provide a team and vision that our clients could get behind and really help us reinvent the workflow. It’s going to be working with our clients to understand their challenges and their assets, but also bringing a lot of these new concepts to the table.
I really think that we’re one of the few players in the space that can bring this level of insightfulness and technical expertise, while at the same time, leveraging those millions of data points that a company is sitting on.