The Exchanges

Q week, Greg Mulholland, the CEO of Citrine Informatics, describes the many ways that artificial intelligence is pushing the performance of clean energy and climate technologies and helping clean up the materials that make the world around us. So at a very basic level, like, what is the materials industry? It's this vast industry. Um, how big is it, when we say the materials industry, like, what are we talking about?

A It's all of the stuff that we make other things out of. And so, that could be building materials, you know. What are the panels you're using in your, your house to, to hang the walls? You know, drywall and roofing materials and these kinds of things. It could be semiconductors. Uh, like where I came from. It could be batteries. Batteries are just stacks of materials arranged in clever ways. Uh, solar panels. But it's also the titanium that the new iPhone is made out of, and, and the vehicle bodies of cars. It's really everything that makes up everything that you buy. And so, from a size and scale standpoint, there are very few, if any, uh, industries that are bigger than materials. Just building materials alone is about a 1.2 trillion dollar industry. The whole U.S. economy is about 23 trillion. So, you know, you can kind of see that when you start adding up all of the input materials to making those end products that we use, it's, it's a really huge number, and that doesn't even start to touch things like toothpaste and shampoo, which are really just formulated materials that you're using to an end.

AI assessment note: “It's all of the stuff that we make other things out of.”

Q And how often are we discovering and creating new materials?

A Discovering new materials, what that is, depends on who you ask. Because, say, Your favorite, uh, laundry detergent company, it's a chemical, but, or, or Apple, comes up with a new metal, right? They're gonna make the new iPhone out of some metal alloy that's, that no one has ever made before. Well, in all likelihood, they're using something that we know pretty well. The newest iPhone was titanium. It is titanium. And they used Ti-Six-Four. So it's aluminum and titanium mixed together in that ratio. And you have this, this new material. That's kind of an edit on an old one. Fundamentally new materials are pretty rare and usually in really advanced disciplines. Solar, for example, um, batteries. But new, fundamentally new materials often win Nobel Prizes. So if you think about kind of the cadence by which we invent something totally new, it's pretty infrequent. It's measured indefinitely in years and sometimes in decades. With that said, every single day there are scientists all over the globe Trying to come up with the next generation of, of a material that maybe they know pretty well, but it's a new enhanced version, a more recyclable plastic or a lighter weight alloy. And that work is just as important if very much more frequent than the fundamental new discoveries.

AI assessment note: “the cadence by which we invent something totally new, it's pretty infrequent.”

Q it look like in terms of competition? Um, you know, Microsoft is using AI. They most recently found a new solid state electrolyte for batteries. Google DeepMind is, um, using artificial intelligence for materials exploration, testing the stability of materials. There's a ton of activity right now. How much of it is Collaborative. How much of it feels competitive? Like, how do you see this landscape starting to shape up?

A Yeah, so it's, it's interesting that, you know, both of those examples you mentioned are really exciting. Um, you know, the, what I will say is the, the world of, of machine learning and materials, I mean, there was a period where I could say that, that I or someone on my team knew literally everybody in the field because it was just a tiny field. That, that's not true anymore, but, you know, we're lucky to know many of the people involved in those research efforts you mentioned. I don't consider them competitive. Um, when you look at, take the Google example, um, with the, the, I believe they call it Genome Project, which is, um, its materials project at Berkeley coupled with Google at DeepMind, or DeepMind at Google, they discovered 380,000 or so new stable materials that were expected to be stable, at least. They haven't made them all yet. That's fundamental work. Stability does not tell you whether the thing is going to hold up in a crash test. It doesn't tell you whether it's going to be safe for a human to use or touch.

AI assessment note: “I don't consider them competitive. Um, when you look at, take the Google example”

Q So I want to talk about the importance of materials in the context of the energy transition. What are some examples of important materials innovations that have pushed clean energy forward?

A Materials are the fundamental technology that power the, the clean energy revolution. Um, they are the things that are going to help us decarbonize our impact on this planet, and there are a few particular cases, uh, that I think are worthy of highlight. On the generation side, there's things like solar cells. Solar cells are just simple, layered materials that interact with one another in a particular way to generate electrons. There are, and by the way, some of those innovations, perovskite solar, disensitized solar, even, I mean, basic silicon solar cells have been refined with new materials technologies over time. You then look at things like wind. Well, wind generation is, you know, you've got magnet technology that's really critical, also critical for the EV revolution. You've got light weighting. You don't want your turbines to be heavy, that's wasting good energy. And you need to make sure your, your materials are anti-corrosion, because a lot of times these things are at sea, In the salt water, and they need to be something that can be robust to that, ah, to that sort of environment. But maybe most excitingly, and the area of hottest debate right now, ah, is batteries. You know, lithium ion has long been seen as the winner in, in kind of the battery wars, but lithium ion doesn't do full justice to the diversity of materials that are, that are in our batteries. In China…

AI assessment note: “On the generation side, there's things like solar cells... perovskite solar... batteries”

Q So how exactly is Citrine using AI? Like, how does the model work? It's there to help researchers not replace them, right? And, like, how does that co-discovery process work? How do you explain the results? And you just walk me through, like, yeah, exactly how the model, model works.

A Yeah, so, so it's actually fairly simple, and at least superficially fairly simple. You can think of AI, and Citrine's AI in particular, as a really basically perfect lab assistant. They never get tired, they never show bias, they weight all data appropriately, and they start a conversation with you about what experiment you should do next and how you should seek to get to the goal that you, you are trying to get to. Um, so the way that works is first, as with all AI, we start with data. Now Citrine, uh, has collected data over time, but the reality is the companies that work in, in various materials areas are the ones that have the most valuable data. And so that's the first piece is, you know, kind of being able to bring a company's data into our private platform without sharing it with anybody so that the AI can learn from it for their benefit. But the problem is, as I mentioned before, the problem is that there are, the data volumes are small. So very often, a citrine materials development project starts with 25 or 50, maybe a hundred data points. My team is overjoyed when we see a hundred data points. It's like an infinity, almost, of data for us. And that is a good starting point. But, I think anybody who knows anything about AI knows that a hundred is not really an AI-learnable volume of data. That's just not what people do. So, we take advantage of the other advantage t…

AI assessment note: “You can think of AI, and Citrine's AI in particular, as a really basically perfect lab assistant.”

Q So what are some of the tangible results? Any particularly interesting breakthroughs or aha moments for some of the researchers using the platform? Have any of these common sustainable materials as well?

A I will say the first, uh, most exciting type of result, and this, this gets to my heart and soul as a scientist and engineer, um, is when we reveal something to someone that they're an expert in, but they didn't understand. So we worked with a, a, a group doing research in, um, In fuel cell materials. And these materials, this was truly breakthrough stuff. They were, you know, and, and real experts doing it. And, you know, they, they used our system, and it highlighted that the polarizability of the crystal structure that they were using was actually one of the most important things to consider in whether the, the fuel cell would work, um, and, and perform at the level that was expected. And the researcher that was leading this effort said, you know, and, and she is brilliant, one of the top minds in the field. She said, You know, I don't know that I ever would have thought of that particular characteristic. It may, it makes perfect sense, and I'm going to use it going forward, but I don't know that I ever, ever would have thought that. So, sometimes it's just about illustrating to someone what the relationships are into the material so they can think about it in a better way. More concretely, we have done work with, ah, battery companies, for example, where, ah, there are, ah, oftentimes, fire concerns about a, ah, a particular battery. Obviously, nobody wants their batteries …

AI assessment note: “it highlighted that the polarizability of the crystal structure that they were using was actually”

Q is focused on the use of AI for drug discovery, for directing Hollywood-style movies, for sorting through legal documents and writing legal briefs. And materials discovery is a very interesting application, one that you have actually been working on for years. A decade. When did you suddenly realize that machine learning could actually be really helpful in discovering new materials and helping with these complex engineering challenges and, and decisions?

A So, it was in 2013 that we realized that, that AI could be, uh, have such a strong effect. I don't think we, even at that time, even in our wildest dreams, realized what effect it would have. You know, look, I, I think over the last year and a half, we've seen AI just rise, like you said, in, in every domain, but in science, AI is sort of a different question, and the reason is that when you go into Hollywood scripts, right, you know, for every movie that gets made, I have no idea how many they reject, but it's a lot, um, and then, you know, you look at open, what OpenAI is doing, and they're basically scraping the whole internet With some caveats, but, you know, they're, they're reading everything, and they're doing it basically for free, and so when you can learn from everything that's ever been said, whether it's somebody being crass on, on Twitter slash X, or somebody being funny on, you know, a bulletin board somewhere, or a Facebook post to your family, they're reading all of this stuff, and they're able to learn what voices sound like, and that's really the core of what ChatGPT and those things are doing. In science, we have a totally different way of working. The narrative we build is very much around the scientific peer review process, right? We have journal articles that come out, and people write a whole narrative, and every solar paper starts with something to the e…

AI assessment note: “So, it was in 2013 that we realized that, that AI could be”

Q So, this process is iterative. It's rare to find some new material that hasn't been discovered yet, but I'm really interested in how this process works. If I went into one of these research labs, like, who's involved? How much time is it taking? What are the costs associated with iterating on these materials?

A Yeah, so, you know, the, the people developing new materials are incredibly smart, incredibly highly trained people. Um, these folks usually identify as material scientists, sometimes as chemical engineers, chemists, um, in some cases biologists, actually. You know, there's a lot of cool biology in materials these days. But what they are typically doing is one of two things. The simplest version is Someone, someone comes to them and says, hey, I have a customer who really wants a better solar cell or a better, you know, a slightly tweaked version of an alloy or a ceramic or a battery. And they take the lessons they've learned from college and grad school and in their professional careers. And they say, well, you know, if you add a little more lithium to the thing, or you sprinkle in a little silicon, you will get a better performance. And it's funny. Uh, there are times where I've heard very serious scientists just refer to that as pixie dust. How do you magically sprinkle on something that will enhance your performance a little bit? And in some cases, that's very doable. But usually that's doable for a while, not forever. So the other thing that people are constantly researching is breakthrough materials. You know, how do I make the, the disruptive battery, or the disruptive solar cell, or, or whatever the thing might be, And both of these approaches have pretty similar risks.…

AI assessment note: “these folks usually identify as material scientists, sometimes as chemical engineers, chemists”