🔬 The Physical World Is More Forgiving Than You Think — Anima Anandkumar, Caltech

0:00 So we you know set out looking for interesting examples and one of them was like weather modeling because the weather data is open source and so given that the data was there we were like okay let's just go try it right and that's the beauty of it to whenever data is available it's really good news but a lot of weather scientists did caution us back then this is back in 21 and they said no no no this is so difficult you know there been decades of development in traditional weather forecasting and that's very careful full bottom up physics- based modeling, right? So assuming, oh, this is the fluid dynamics, can you go predict the weather the next day and so on. And so that's how a lot of the thinking was that AI is just not going to be able to beat the decades of work in weather modeling.

0:49 but to our surprise we just went ahead we trained them we used neural operators to be able to effectively capture the phenomena and then we found that it's not only accurate it's almost as close to what the traditional weather models can do accurately but also tens of thousands of times faster so what would take a big supercomput to run can now be run and we only needed a consumer grade like GPU like you know it was a small model it fit very well. It's very fast and it's accurate. And I think that just changed everybody's thinking.

1:27 >> Welcome to Leaden Space. this is the AI for science section of Lean Space. I'm Brandon. I work on RNA therapeutics using AI and atomic AI. I'm joined by my co-host R.J. Honiki who develops spatial transcrytoics and is the CTO and founder of Mirror Omix. today we're excited to be joined by Ana Ankumar the brin professor of mathematics and computer science at Caltech. Ana has done all sorts of really cool work combining AI with basically models of the physical world. and has a really diverse background. I don't think I could even remotely cover it. but anyway, I'll let Anna introduce herselves. Thank you for coming on the show.

2:08 >> Yeah. Yeah. Thank you Brandon and R.J. It's a pleasure to be there and I really like the term latent space because that very much figures in a lot of my work because it's really you know the world is latent but yeah just as a brief introduction you know I've been working in AI for more than two decades in a way you know before even deep learning when a lot of the theoretical foundations had to be built for probabistic models I worked on them and then as deep learning started taking off. I also had a foot in industry until recently. So I was at NVIDIA, I led AI research there and before that at Amazon Web Services helped found the cloud AI team and build the first cloud AI products back almost a decade ago.

2:56 So you know like kind of having this one foot in industry and academia I think has given me a lot of interesting perspective of how to bring theory and practice together and think of AI at large scale but also AI that is principled. >> A lot of your work has been related to the modeling of physical systems using certain types of physical systems which you model with differential equations and you help model them with using machine learning. So maybe first let's go ahead and talk a little bit about that as a high level but we'll get to kind of the details about listening neural operators and some of the applications like weather later but first I'm actually really curious to hear about torch lean and how this recent work you've been doing connects with that larger research program >> to me broadly like you know my thesis is AI and science how we bring that together right so you know where I started Ed at Caltech almost a decade ago that's when you know my passion was always science was physics and but you know I was doing AI so how to bring that together was where you know the first kind of foundations got laid there and to me like you know there are several aspects to that one is people have been thinking how to use language models for science yes you can do a lot of hypothesis generation you can have ideas But ideas are not enough, right? So you can have a lot of ideas. The bottleneck is going testing and verifying that they work in the real world. And so this aspect is where a lot of my recent focus has been on how do we ensure that we can build AI that has guarantees that it will work in the physical world or any aspects in scientific domains. and and one way to think about it is you know can we model the physical world and keep the physics correct and that's where neural operators come in. The other aspect is can we verify symbolically certain aspects. for instance you know if we claim that the theorem is correct we have to go verify that you know that's where lean as a formal language can be useful for verification. So how do we bring that together with language models is where a lot of mathematical reasoning has been at the forefront. And so torch lean kind of is in that realm where we say you know not only that you want to verify mathematical statements. You may want to verify what neural networks themselves claim to deliver. You know for instance if you're now using a neural network and you want to ask whether it's going to be robust. Say you want to use a neural network in a control loop. you want to control you know whether it's a drone, whether it's a nuclear reactor. So all of this ultimately when we build AI systems with deep learning into control loops, we want robustness and so now torchan can help us do those verification seamlessly. So we can now have neural networks be part of the verification loop and have confidence that we can use them appropriately. We have already discussed on the podcast lean and and everyone should probably be familiar with neural networks. How but neural networks seem very unconstrained. What kinds of proofs are you talking about?

6:36 Are you talking about bounds on the outputs, inputs? what what can you prove with torch lane? >> Yeah, so torch lane is a an overall framework, right? So what it really enables is that you can now write neural networks essentially in lean. So instead of writing in like pietorcharge it's like a pietorch like abstraction but you can like kind of you know write it in lean and so it can be fully formalized in lean and then there are several implementations you know we have algorithms for certified robustness like crown you know those are implemented under this framework so >> sorry was it like what like crown >> crown crown is one of the u so there are different ways to bound you know for certified robustness you know how tight those bounds can be. It depends on the relaxation techniques and sort of without going into those there's many such algorithms but you know we are kind of like implementing them and enabling them in lean so we can seamlessly run both you know we can both first kind of write down torch like framework neural networks very simply right and then we can also make statements about them formally and verify them. So all of that can be brought together in one framework.

7:54 >> So what's an example of a a bound that you could claim like so we're operating a nuclear reactor, we don't want it to melt down. What are the sort of guarantees that you could provide to the out inputs and outputs that would help that not melt down? >> I mean the natural one is the certified robustness that I mentioned. So saying that if you our inputs are you know perturbed by a certain amount how much is the output going to be perturbed right this sensitivity analysis is another term and so having those kinds of bounds for different neural architecture so you kind of automatically get those bounds can then help us you know not only train neural networks to do well in a control loop but also worry about safety and robustness stability these are all part of control systems that people worry about. So that's one example of an application. So it's really more broadly the idea is you need verification in lots of scenarios that involve neural networks. So control loops are one. Another example is you know we used physics informed neural networks to say solve partial differential equations or come up with systems that that are guaranteed to satisfy certain physical laws. But we also want to verify for instance that our neural network is only trained in finite precision right. So can we overcome those requirements and what happens when we are what are the shortcomings because we are using this finite precision can we also bound those right >> so those are other kinds of bounds that work in torch lane. So all aspects of you know the effect of precision the effect of perturbation all of these we can now you know we can have algorithms that are implemented in lean that can be seamlessly now part of the verification loop.

9:50 >> So and is the descriptive power of the torch lean is that sufficient to describe basically any neural network or is there are there constraints on that? Yeah. So it's essentially a you know pytorch like you know framework right so you can just kind of nicely define neural net layers in the same way but the back end having like lean helps us formalize and prove it >> and for like transformer architecture for example is it reasonable to prove these kinds of bounds on a very large neural network. the you know there is the aspect of one is like kind of having the framework right the other is scalability low so lead still has a lot of shortcomings there it's CPU based and you know it's not like make getting that onto the GPU has a lot of nuances there so you know a lot of work needs to be done so what we've started with is a framework you know making that more efficient especially at a very large scale requires still a lot of work to be done.

10:54 >> Yeah. >> But that's true broadly for lean as well. >> I'm just trying to understand like how I imagine this. So if I were to take a let's say numerical analysis classes you know a graduate level numerical analysis class you have a differential equation you have some discretization error or something and you bound like given these properties I can bound the solution right so solving some of these physics based or AI based solutions to differential equations I think historically it's been kind of the wild west so I think you mentioned physics inspired neural networks really cool idea it'd be fun to talk about that a little But I I know that sometimes they they are particular and that people don't they don't always work and I think people don't always know when they will or won't work. I mean I'm not an expert but I'm just wondering if that's I mean your experience. and what I'm wondering is like has this helped you understand like the domain of applicability for pins or and is that sort of like the goal is like you can rigorously say like this solution will converge or is there not necessarily the same concepts of convergence in the controlled way for neural networks?

12:03 >> Yeah. So you know like physics informed neural nets are about like saying that you know I write down like a PTE partial differential equations and hopefully the optimization succeeds and I get the answer right and of course if like optimization was not at all an issue this would be universal you solve everything you know we're all happy but that's not the case and so optimization ends up being usually very difficult especially for problems that are time dependent, meaning it's not just stationary, you also have time and the time component in many cases could be turbulent. Like in the case of fluid dynamics, you know, you kind of like if you run it long enough, it can become chaotic. So you really you know have like very small fine scale effects matter and so in those cases just trying to solve a partial differential equation at all times is just hopeless like you know this is not an optimization landscape that you know I think we'll you know we can have any handle on and this is where the idea that from scratch we would be able to solve these equations using a neural is not possible. So pins don't work everywhere and our idea of neural operators came as a way to overcome this. Right? So saying you know we can't rely just on physics constraints alone to come up with answers. We have lots of data available. you know I'll talk about the weather example where we even collect data right so we don't just solve equations and have synthetic data but we also have real data by observing the weather as one example so why not make use of all of the data available.

13:54 So we don't just rely on trying to solve partial differential equations and other physical problems from scratch because it's really the datadriven approach that makes it possible to get quick answers. And so with neural operators, we can bring both of them together. We can have all the data that's available. We can utilize it. We can add physical constraints and then that overcomes the limitations that pins face. >> Can you give a little bit more intuition on the difference there and why that is possible? So I heard you mention you know in with pins you're basically just baking the physics constraints into the neural network but that this becomes unstable over time or other other variables whereas if you add a little bit of data like I I can kind of intuitively understand why that might help but can you give a little intuition for what's going on what's the difference here >> so with the pinned like you know every instance of an equation you solve from scratch right at least in the classical sense. So you start you take the specification of what equation you want to solve and you hope that the optimization landscape succeeds which many cases it doesn't. Whereas with neural operators what we do is we you know have lots of great data. So we have a training phase we teach it how to come up with solution for different instances of equation. And so just as in other supervised learning at test time you can now ask you know can you come up with an answer and you can still have physics constraints as a way to guide that. so you know can be both datadriven and physics informed together. but the benefit is because we have data you know it's like you're not stuck in an optimization landscape right so you know what the answers are during training so you are now at a better chance to come up with the right answers even at test time >> my understanding is that a neural operator is is a a function fit to to like to data or a neural network you know learns to fit functions to data is that a good intuition here.

16:05 >> Yeah. So you know neural operators are in that sense similar to you know it's the same as neural networks right you're learning on data but the difference is neural operators are you can think of it as a generalization of neural networks. So with standard neural networks the inputs and outputs are a fixed sized. So in language we have fixed vocabulary we fix what the input and output are. And same with images in computer vision in videos we assume a fixed resolution and we always you know our inputs and outputs are always at that fixed resolution. We can't change it post talk. Whereas with a lot of this physical data the idea is our world is inherently multiscale. So you should not be like deciding beforehand what the resolution is. You know maybe you have like weather data available only at coarse resolution but really the actual phenomena are happening at a finer scale right and maybe you want to after that incorporate either additional data at finer resolution or add in physical constraints at finer resolution. So we should be having that flexibility and we should really think of the world not at these fixed resolution but one that's happening infinitely you know that one the real world happens at that infinite resolution and that's what neural operators enable because they model inputs and outputs as continuous functions that can be infinitely resolved that can have infinite discretization and now we can have you know at inference time you can give it now inputs and ask for outputs at any resolution. So you're not just limited to the resolution of training that we see in standard neural networks and that's what neural operators enable. So neural operators enable us to zoom in and out as we like. So obviously that as stated that any function that that's under constrained right you could have many many functions that fit this fit the data it would be easy to overfitit.

18:11 So how do you regularize that? >> Yeah certainly like you know you know if you're asking about making predictions at a higher resolution than what's seen like what we call zero short super resolution you're kind of making some guesses right and and that's what these models are doing. they're trying to regularize and kind of smoothly extend to higher resolution. But of course, if you now give it the model additional information in terms of let's say a physical laws, so you could give it partial differential equation constraints, conservation laws and you can now enforce them at a finer resolution than the data you have. Then there's more guidance in a way. So that way it can now come up with the right answers even at higher resolution because you're you know giving it constraints at higher resolution. And so that's how we can ensure that these physics informed neural operators can work at higher fidelity and higher resolution than even the training data that was available. My understanding is a lot of your work uses a particular kind of neural operator a forier neural operator. So forier is a dual domain. It is extended across the entire domain of the inputs. That's a lot of jargon maybe can you give some intuition for why why is that important? How does that help? what I mentioned neural operators as a class of models that allow us to have any resolution input and any resolution output right and learns the mapping between them you know that's really called an operator so the mapping between function spaces so that's the reasoning behind the name neural operator and you know for neural operator was one of the early setups we or architectures we came up with And the reason why that's been so successful is because it kind of strikes a nice tradeoff between efficiency and expressivity. Right. So why is the 4year space a good one? The 4year space allows us to, you know, it's a dual space like you mentioned, but it really allows us to capture non-local phenomena, right?

20:29 So meaning something that's like non-local in the foryear domain could be even efficiently captured and a lot of phenomena like we see in nature whether it's fluid dynamics, material deformation, quantum chemistry, it's all you know there's a lot of them are non-local. You know the differential equation like the derivative is local but the inverse of it is you're kind of doing essentially integration. It's non-local, right? So the solutions are non-local and these models are able to capture that but at the same time doing foryear transform is efficient and it kind of like nicely captures a lot of inductive bias we see in many of these u natural phenomena but this doesn't mean that we are capturing the world entirely in the for basis right it's not a linear representation in the 4y year basis which is what classical numerical methods too. We add nonlinearity just as in transformer and other neural nets in between 4year layers and we also add residual collections. So all of these architectural aspects that are inspired by other neural nets that work well in other neural nets. Bringing that together really kind of helps us get best of both the world. So you can think of like if we were to use transformers and we require a very high resolution, it would become untenable because of the quadratic complexity and all connections. On the other hand, if you did that with FIA transforms, we have like quasil linear complexity and still we have global connections in a way we can model these non-local phenomena and so that's why it's a nice middle ground. So that allows you to learn from what is happening on the other like is talking weather like what's happening in Chicago may have some impact on what's happening in San Francisco maybe not but that's the idea.

22:33 >> Yeah. So that's the idea and time like kind of yes at this point may be local but eventually they have an impact in other locations and yeah so both in space and time we want to capture that dependence. >> Yeah. So what happens today in Chicago will happen will have an impact in a month in San Francisco or something like that. >> yeah so you know so there is like both the shortterm and the long-term effects. So in a short term like we think about predictable weather but longer term we're talking about climate right. So what happens you may not be able to say precisely you know what happens in Chicago what will happen in San Francisco that's like the butterfly effect on the other hand we can kind of give averages you know if there's heat wave in this kind of overall region you know we kind of have an idea that it's going to be higher than average temperatures. So those are the aspects we can capture together >> from an architectural standpoint for all the AI engineers here. Are we just talking about doing all the work in the forier domain but it's basically the same neural network but I'm just operating in the foryear domain or is there other other aspects that are con that are required in order to do this properly. So think of it I guess the maybe the easiest way to think about it is you know you can if you think of a transformer architecture instead of like the you know attention map you now have the four year but you still have other nonlinearities you have like you know the residual you have you know many other parts of the architecture still there that give it like expressivity and we have lifting to higher dimension like you know in a channel space to give it more expressivity. So all of those kind of best principles are are still available. but the foryer helps us capture that all to all you know dependence without requiring very huge complexity that I see transformers that makes sense. The other advantage is that it gives you the natural multiscale what's sort of a implicit cutoff is you know the sort of if you have a signals background or physics background you might ask you know in linear if you're doing everything linearly there's a maximum frequency and you know below you know above that you can't represent anything. but how does that how does adding these other architectural changes in a nonlinear domain actually affect you know your choice of of frequency bounds and >> yeah no that that's a great question and that's where the expressivity comes in right otherwise if you're just taking a 4year transform of a signal and trying to represent it you know that's what numerical methods have also attempted to do and that requires very fine discretization and that's why it's very expensive to do the simulations in a classical way and instead if you want to move away from that and say we want to learn the features which is what deep learning is all about then we cannot force it to be only in the 4year domain we have to give it nonlinearity to figure out what the right basis for you know the best basis to represent the signals are and so that's the kind of like nice kind of combination we have that it's like all these nonlinearities will help it kind of you Find the right latent space.

25:55 No pun intended. This is the radio. It is the radio and so you know the the and if you do for in that latent space you know that may be a more efficient way to represent. So that's one way of thinking because you know first of all we're lifting the signal to more dimensions. Even if the signal is two or three dimensions we are now lifting it to much higher dimension. So in that space the idea is it's easier to learn and we're doing it as a nonlinear lifting right so there's already a latent space there and then we are doing further nonlinear transformations in between our 4year transforms so that means we are saying yes you know maybe with these limited number of frequency modes it's not expressive enough but when I add nonlinearities I can you know I can kind of nice more nicely capture them.

26:47 >> Yeah. Yeah. So you started your career back before neural networks were I guess taken off right. So I think back then people really did think a lot about you know appropriate basis sets and you know function expansions and orthogonal polomials or whatever. How does that evolution from you know your research standpoint like as the community has evolved from that to oh just screw it throw it all in. It seems like you still like believe in at least some of those concepts as being guiding principles.

27:19 Do you think that that that there is actually so lessons to be taken from you know classical mathematical like rigorous mathematical techniques that you can use those techniques to actually help improve modeling of the real world even if you still are just throwing the kitchen sink at things? >> No, I think it's a it's a nice I think there's a trade-off involved. I mean it's funny my undergraduate thesis more than two decades ago now was on fractional 4year transform right so and and so yes I mean by themselves like you know that wasn't enough to do computer vision but I was curious okay what are these techniques and how well do they work and so you know I'm completely with you that we cannot just force ourselves to use stone age techniques or classical techniques right I mean so we have to have feature learning we have to have flexibility, expressivity, you know, they have to be easily optimized. So all of these aspects are very important with deep learning. But when it comes to the physical world and physical data, it's never going to be as plentiful as we see with language models because we are, you know, our weather model like had about like 50,000 samples, right? 50,000 samples of fairly high resolution like global weather maps but it's nothing like what we see with language and in other domains it's even less because it's so expensive to simulate and the real data may just not be available and so here we have to think about the inductive biases more we have to add in the physics constraints cannot be just reliant on data and that's where I think a little bit more thinking of the architectural design comes up. the other aspect is computational complexity. So think about language.

29:09 It's just one dimension and even there the context length you know we are getting to millions and we are struggling right. I mean on the other hand now we're thinking about not just 2D 3D even 4D you know 3D and time and if each of the dimension is even a few hundred grid points which is where you know industrial scale starts at like like a thousand grid points in each dimension we're talking like hundreds of billions to even a trillion context length right so forget ever having a transformer for anything of this scale all of the world's compute will not be enough and first of all they all have to be colloccated to be able to ever do this so that's why we need other architectures >> but I would push back a little bit right we have the vision and video language models right and they use they basically learn a mapping >> but the resolution is very low that's the key like for the physical world the resolution what do I we require I mentioned like thousand by thousand by thousand by thousand so there you know the if you count that that's like already in hundreds of mill billions.

30:19 >> Yeah. >> So so you know we are not doing that high resolution when we think about images and videos correctly. >> I have a friend and >> and the video is also like auto reggressive. So it's essentially only like you only need to do the next step >> right yeah but you're learning I mean like generally you're learning a code book right? So you have you're kind of learning the bias of the latent space or the the real world to the latent space and and and so that if there is a like a compression that you can do from the physical world into the latent space then then you know these auto reggressive techniques have been successful.

30:57 >> Yeah. But the idea is you know a lot of these auto reggressive and you know techniques for vision and video models are for mostly like you know looking good right so they are like not for very precise simulations and there you know be having that higher resolution and details is really important and so we need to at least take in the data of that high resolution right so we need to be able to process that and reason over them and so this This is where a lot of the bottleneck is because we, you know, cannot afford to just throw away everything and say, "Oh, let's just like have 100 grid points in each dimension or 50 grid points because there just isn't enough detail to correctly model phenomena like fluid dynamics, plasma, how materials deform. So all of this requires high fidelity and for that we need high resolution." My understanding you have a thesis that AI needs, you know, to incorporate the physical world into it in order to scale and be accurate going forward. Many people have this thesis. You are somewhat unique in that you have several examples of applying neural operators to the physical world in this way and then it seems like you're constructing a thesis around your experience here. Can you share with us some of the really interesting and exciting looking things that you've done using neural operators and other techniques?

32:32 >> Yeah, I mean you know for us when we started with like neural operators for partial differential equations but also more broadly you don't even need to assume they're partial differential equations right could be any spatial temporal or data at multiple scales. So we you know set out looking for interesting examples and one of them was like weather modeling because the weather data is open source it's available called the five from the ECMWF the European agency for global weather modeling and so given that the data was there we were like okay let's just go try it right and that's the beauty of it whenever data is available it's really good news but a lot of weather scientists did caution us back then this was back in 21 and they said no no no no this is so difficult you know there have been like decades of like development in traditional weather forecasting and that's very careful bottomup physics-based modeling right so assuming oh this is the fluid dynamics can you go predict the weather the next day and so on and so that's how a lot of the thinking was that AI is just not going to be able to beat the you know decades of work in weather modeling but to our surprise we just went ahead we trained them we used neural operators to be able to effectively capture the phenomena and then now we to our surprise we found that it's not only you know accurate it's almost as close to the what the traditional weather models can do accurately but also tens of thousands of times faster.

34:11 So what would take a big supercomput to run can now be run and we only needed a consumer grade like GPU like you know it was a small model it fit very well it's very fast and it's accurate and I think that just changed everybody's thinking you know after that deep mind Huawei many others followed us a year later released their own models we were the first to actually open source our weather model forecast net and do it permissively so that's what allowed companies, weather agencies, everybody to build on us. And so, you know, it's been a really interesting revolution to see that the weather models are now out there. weather agencies are adopting them. And it allows us to now have small weather agencies in the global south, for instance, have the same kind of fidelity that very big agencies were in the past only able to do, right? So it's democratizing weather modeling. And so that's just one example of where there's been very quick rapid progress and a paradigm shift in terms of saying that oh now we can have AI as a reliable way to do weather modeling. I saw that, you know, the the models that you mentioned, you made an insight that nobody else had and that people were able to devise other mechanisms to kind of follow behind you, but there was some sort of shift in thinking that was required here. And was it it was it simply we believe that there's enough structure in this data to learn and that people are just doing it wrong and people found other ways to learn the structure but that your method was very so let me let me clarify right so there is you know first of all the very first work was to just say that you know look traditionally this has been done with so trying to solve partial differential equations each time doing it again and again whereas AI learns from data learns patterns and can be just as accurate but fast and then the next iterations was to say you know how do we make it even more accurate and there's the aspect that you know there is the short-term weather like what is predictable for the next 2 weeks and then there's the long-term you know going to subseasonal to ultimately climate modeling and traditionally what people did was to have different models for these different scenarios. So there's a different kind of system that works for short-term, another system works for long-term. But to me, there's only one earth. You know, if you want a foundation model, if the claim is that it should be able to do both very short-term as well as very long-term together. And that's where in forecast net 3, the latest iteration of the model, we're able to do both. And that's because you also, you know, incorporate the sperical geometry of the earth. And so with a lot of the other architectures that have been getting fairly good accuracies for the short-term weather when you run them for longer term when you run them for like several months to even year even before that it just very quickly blows up right because it assumes the world is a rectangle which it isn't. And so incorporating all of the geometry and that information into neural operators means that we can faithfully run the same model also longer term and you make this into a climate model. This is where the Allen AI Institute has now built climate models based on our neural operator architecture and that's the only one that works as an AI emulator. Right?

37:55 none of the other architectures work for climate because climate requires us to assume the world is a globe and that if you are repeatedly rolling out you kind of keep that information whereas if it's like a narrow surrogate that's what I consider a weather model you just narrowly look at a few metrics many different architecture should do the job right but if you are asking one architecture do a range of different tasks like a foundation model. That's where incorporating the geometry of the earth which is that it's a sphere and using neural operator as an efficient way to do that enables us to accomplish that.

38:39 >> Yeah. So forecast net you said trained on 50,000 data points. Can we just talk about like what does this look like? Like what does the data input look like? What are you actually trying to predict from here? And then what is sort of the like the large scale you know you said you you're going from weather to climate what does it look like to do that generalization because I could imagine if you have 50,000 data points these are you know some high resolution in North America then you know they might even depend on the local geography like like if you are always modeling you know Kansas does this going to transfer to you know let's say the Swiss Alps or something and then does that transfer to you know the Himalayas is >> so first of all to clarify we are training it on the global weather model right so we have all the information around the earth and then we are you know asking it to predict like given the current weather like say wind conditions humidity and so on what happens you know in an auto reggressive way and it's every 6 hours so what happens in the next 6 hours and so on and you roll out and you train the model to predict and and so you know you can have the potential actually the same model predict forever, right? So, and but the predictability window is like the weather and if you want to go beyond you if to do what we call ensembles meaning you have like a probabistic estimate of what happens in several months to years and that's how you get a climate model.

40:09 >> Okay. So you have you actually have an ensemble of these local predictors and then you use the some sort of statistics on the ensemble to get a climate prediction. >> Yeah. So you kind of like have several rollouts essentially. You have several trajectories of rollouts and then you get >> and so is actually pretty key here. >> Yes. And that's why that's the biggest bottleneck with traditional climate modeling that it's so expensive to do even one single run. you have to do long trajectories very very high resolution and you know that's why we don't have a lot of very high resolution ability to do climate change predictions for instance >> so how do you validate climate so you do lots of rollouts and you look at sort of how things evolve kind of in aggregate I mean ni said butter butterfly effect locally I think we can believe even a perfect climate model or perfect weather model would only give you maybe 2 weeks before it sort of it's becomes non-computable. So you do lots of rollouts there's some chaos you you average all these things how do you actually validate that this works over long enough times scales. Yeah. And and it's a tricky question, right? So for instance, you have to kind of ensure that you satisfy all of the physical constraints and if you just do a standard roll out, that is, you know, likely not going to happen. And so some of the ongoing research we're doing is how do you kind of enforce the right physical constraints as you do the rollouts? Like you don't want to, you know, completely wash out the fine details because then it's not accurate.

41:49 but on the other hand if you keep them you maybe physically they're invalid. So this is still an open problem and that's what makes it difficult that you want AI to be fast and you want to be able to do these long climate simulations and at the same time be able to have full confidence in them. But these are things we are working on. though. >> I don't know if this falls into weather or climate, but we recently just had one of the most extreme heat waves in the history of modern climate data, right?

42:21 in the just right here in the kind of southwest United States, I'm wondering were did you I I don't know if you were involved in this in regularly, but do you know if you or anyone actually modeled that or predicted that correctly? >> Yeah. Yeah. So we have I know I don't have information on this specific one but we've tested in our latest forecast net 3 model extreme weather events of all kinds right and that's the key like you know that's where you need probabistic answer so having just one deterministic output and saying that this is the weather is not enough when we are looking at extreme events so we need careful probabistic calibration and we show that we are able to capture those well and I think that was the surprise Even in our very first attempt that we visualize certain hurricanes and storms and it was able to do well which is very surprising because you would think that rare events are not something AI would do well right it would do well on typical events but I think this is where more broadly the lesson is the physical world may be more forgiving because you know where there are extreme events like hurricanes that have very specific physical signature Right? So it's like extreme but in a very specific way. So maybe you don't need as many samples because the physical world has a lot of structure and that's something we see this again and again that there is a lot of structure in so many other examples. You know I talk about plasma in fusion reactor. you know we barely have a few thousand samples but we are able to accurately predict events like disruption very well and we are able to do that a million times faster than what traditional simulations were able to do to me yes all these sound very surprising but it's because I think the nature helps us a lot you know it has a lot of latent space structure that's that I don't think traditional numerical meth methods are able to uncover because they are focusing more on correctness that in any scenario you should be able to solve these equations. On the other hand with AI it's learning from data.

44:34 It's uncovering the structure. It's uncovering how easy or kind of tractable these problems are and that's what we are seeing in many cases. >> Yeah, I I've had of a a similar analogy. So from you know my own domain is probably closer to computational biology but you know alpha fold is the obvious like really exciting development in the community. So the solving protein structure prediction and of course all the caveats of what was actually solved. I think we discussed this in a in a previous episode with the Boltz team.

45:06 Encourage listeners to to listen to that if they want more. But one of the I think key points about protein structure is that it really is constrained by physics. And that's why it was in some sense one of the the few big wins in the field of biology which is otherwise very complex and we've had trouble generally speaking making a lot of success and it seems like problems which are solved by differential equations or I say modeled well by differential equations have a lot more room for also integrating these techniques as a general form there was a question there So, so, so getting back to my question, we have climate or weather and climate, we have plasma, we have, biology, and I know that you, you prepared for us a few visualizations.

45:58 Can you can you just share with us, what does that look like? You know, what are the so the visualizations and then what is the thread that runs through here? And I think maybe the the listeners will already have a hint about that, but I'd be really excited to see that. >> Yeah, I can certainly share some of them. I mean this one is just kind of showing that you know we have world at different scales, right? And these are examples of phenomena happening at different scales from atomic to protein to even planetary scales like the weather we talked about and you know we need to capture all of that. That's what neural operators are designed to do.

46:43 and you can you know feed in data these different scales and that's really like the aspect that makes a lot of the physical world problems hard that need for fine scale. You know, we talked about how a lot of traditional computer vision video models are just designed to make things look visually good and that requires low enough resolution. It's tractable, auto reggressive. It's enough that you know it works out. It's short enough videos. But that's not how a lot of the physical simulation for you know industrial scale high fidelity work. you really need high resolution the you know the atmosphere is one example like you depending on the resolution you observe different phenomena can be captured so you just miss that out if you don't have that high resolution and now the question is with AI can we do this much faster than what we could with traditional simulation and this one with neural operators is kind of showing that you know if you use the standard neural network and you had a fixed number of pixels like you're seeing on this side and you zoom in it gets blurry right that's the end of it there's nothing beyond those fixed resolution that you can capture but the idea is with neural operators because it's a function space representation meaning you can keep zooming in you can add it the relevant details either by giving it data at higher resolution or physical constraints at higher resolution you can kind bring that multiscale phenomena together.

48:23 >> So where where are the physical constraints? I mean I assume physical constraints here are like local simulating you know fluid equations or some sort of isnamic >> could be right. So it could be of any nature. The idea is now you can add like conservation laws for instance in an incompressible fluid. You can add like material deformation like how things stretch. So or it can be a full partial differential equation. So that's also an interesting question. We've been researching how is the curriculum of different physics like you may you know some physics may be very hard to impose or add as a loss function others may be easier so you also need to kind of you know think about what what to impose you know >> so and the intuition is here is that when I'm adding a physical constraint I'm adding it to the loss function is that more or less what's happening >> yeah because that's what is tractable you know making it a hard constraint is not tractable whereas adding it as a loss function and of course there's still the balancing of that loss with the data we have so we have to you know do that in the appropriate way >> right >> yeah so as I mentioned the this is the example of the weather model where here we are showing how we are able to capture like atmospheric rivers which is the phenomena we see here in California you know resulting in large storms I think we are we have one expected later this week. So, >> we'll hold you to that.

49:56 >> So, the idea of like, you know, why I showed this is this kind of global phenomena, right? These are like thousands of miles wide. So, you really need non-local models that capture these very large span phenomena and do that accurately and that's what our neural operators are able to do. So, so the training data for this is you were talking about this a bit before, but I'm still like wondering what is this? This is weather satellites or is there groundbased data? Is it some hybrid of the two?

50:28 >> It's it's kind of a combination of different sources. So, it's what we call reanalysis data. So this is historical weather data >> that is in a way reanalyzed meaning that the s raw satellite data is combined with essentially what the physics solvers tell you together assimilated and so this is a made available by the weather agencies and we can train on them. So you're saying that they take a lowresolution data set which is compiling all of the world's data set, you know, all of our meteorological data we have across the world.

51:03 >> and then they do short time simulations using physics-based, you know, classical techniques to to fill in the details. Yes. >> and you can do that over short time spans, but as you go farther, it breaks down very quickly. So you're amortizing that across all the everyone would have to do that and so somebody does it and then you are able to take advantage. >> Yeah. I mean this is data right that's already prepared. But the idea is already this data simulation with physics kind of makes our model physics informed implicitly. So it's able to kind of you know keep that information and that's why maybe that's one reason maybe it does well on even extreme weather events. Yeah. So this is just showing that we our model is available in ECMWF which is the weather agency like you know the European weather agency and so this was launched like more than 2 years ago but you know I think fall 2023. So you know I think ECMW of making these AI based weather models available to the public to me was a very big step because that's where you know everybody could see what's happening. There were several hurricanes like for instance there was hurricane Lee and that's where the public could see what are these weather models doing.

52:28 For instance, our forecast net was able to correctly predict that the hurricane making the landfall several days earlier compared to the standard weather forecasting models. And so the idea that these models could be very good for extreme weather events and do early prediction, you know, both for human lives, for economic costs is a very big deal. And so that's when the public kind of got a lot more I think buy in and from weather scientists because of how well it was doing in these events. And this is what I was talking about in a ensemble prediction both for extreme weather or if you're thinking about climate. It's not just about looking at one trajectory, right? Because you know, unless you're somebody with a Sharpie somehow saying where hurricane is going to go, no, pun intended. But you know what you really want is a probistic prediction. meaning, you know, I'm going to try different adding noise levels to my initial condition. What the when the weather when the hurricane is forming in the Caribbean, I'm going to add some noise because anyway it's noisy. I don't know truly what the measurement there is and then I'm going to look at what happens to the possible hurricane tracks and then I can come up with a probability of landfall in different regions and that's how I can do risk assessment. And so this is where it gets even more expensive for traditional weather models because you have to run all of these ensembles. And now AI weather models being so fast, tens of thousands of times faster means we can now do very large ensembles. And this is a very big improvement in terms of what we can do for risk assessment. Have you gone through and done let's say looked over the historical hurricane maps and then tried to do ensemble predictions and calibrated how often your predictions are like a >> code. Yeah. So in forecast net 3 paper there are you know we have metrics of like extreme weather events and ensemble prediction and in fact we've trained the model to do good ensemble prediction and so this is where the calibration matters for for these kind of events. what was the sort of key insights or developments in forecast net 3 in versus two versus the first version.

54:52 >> Yeah. So the first version was kind of the you know the using like the FIA neural operators but we didn't incorporate the sperical geometry right in this next version we said I think you know it's important that the world is a sphere because first of all otherwise it's distorted so you kind of are not predicting >> dumb question but if it wasn't spherical what did you do like a mercurator projection or something? Yeah, the standard like kind of the you know like as you all and all the other weather models do the same right so they just kind of have the standard projection and then you know predict the weather and which is okay for short-term prediction but when we you know our goal was to have the same model also do longer term and that's when incorporating the sperical geometry added this additional stability we could do longer rollouts and then in forecastet 3 the idea was it's not just about deterministic prediction. We want to get ensemble predictions right. So we have to train them based on this objective that we get the probabistic predictions correct as well.

55:57 >> How long are you predicting out? and how many roll outs are you doing? >> Yeah. So the I know roll out is how long you predict right? So each step is 6 hours and then you predict for however long you want. You know you just have to roll out. Sorry. How many how many examples in the ensemble do you have? >> So, and again that's our choice. We can have like ensembles of different levels. So, we I think it's like a few tens or something like is what we are currently you know shown but you can do much larger too >> and that's adequate to get out how far my intuition is. the longer you want to predict the more >> so not necessarily it's really like about again calibrating the ensembles and ensuring that they have the right spread rather than you know so >> okay so so you have tens of these models or examples in your ensemble and that even with a very very long roll out that's adequate. So again like you know there's as I said a lot of still outstanding questions to do very very long rollouts right because you you do need to incorporate like the physical constraints in a way to ensure that that's something that we are actively researching now but these models that we have are able to do the longest rollouts compared to any of the other weather models that completely ignore spherical assumption and a range of other things. So when you say inc incorporate physical laws for climate over long times I mean what does that look like? Because there's a lot of local conservation which may be just broken if you take an ensemble of average even though any given snapshot is respects that.

57:43 >> No the idea is to make sure you look at each ensemble member and it respecting the physics. >> Okay. Okay. You're not assuming the ensemble had you're not deriving a like coarse grained like equivalent of a probability or something >> because then you would lose that you know resolution and the f >> okay >> that's a little confusing to me wait so you're so it's not an average how are you combining the ensemble >> no you are doing the average but you're predicting each one >> oh you're predicting each one separately okay yeah >> so each one is independently satisfies these constraints but the ensemble >> it does not yeah which >> and and so that's how you ensure physical biology.

58:22 >> Yeah. So when you go on a sphere you operate in do you use basically spherical harmonics or some sort of okay yeah you have a spherical basis for which is actually very natural with 48 is probably much harsher if you're doing >> other exactly so that's where the you know like the fierer saves us can incorporate these geometries well and and so I think be very faithful to you know what the globe is >> yeah arguably it's much more natural than than like market projection or whatever other >> yeah which >> it's like greenland becomes huge so that is a different story but but that yeah but I think that this is where I think the aspect of you know more broadly incorporating more of geometry and information about the domain becomes a lot more important in for the physical world right so this is me again emphasizing that we need to incorporate more of the structures because one is the data is limited and the Other is a lot of what we are asking is extrapolation. You know to go beyond than what the it's trained on. You know we're just training it to predict the next six hours and maybe do a little bit of multi-step fine-tuning for auto reggressive rollouts, right? So we're not training it to do very long like a climate simulation because that's just too expensive. But we hope magically it works well and it cannot if you just say I'm just going to put a standard transformer or whatever else there and it won't work out. So we add in more of the domain constraints like spherical geometry. We add in maybe more of the physics in certain ways and that's where it becomes more interesting algorithmically as well. You know there's more involved design here. So the time scale that you train on, how long is that >> to predict for the next six hours?

60:16 >> Oh, so only six hours. >> Yeah. And a little bit of multi-step fine-tuning like kind of like >> Yeah, I said that. Okay, understood. >> So which is very surprising, right? >> Yeah, that is very surprising. I would have expected it was weeks or months. >> No, and then it kind of just works well even for like now we are showing for several months that it's able to do that. >> The number of steps is on the hundreds or and that your your foyer basis it's it's many times the the the sort of base harmonic >> I mean this is like that's in space right so we're talking roll out is auto reggressive in time >> no but like in in time maybe I'm misunderstanding here because it's a in fora domain right >> no no in time it's not that's what I'm saying it's autorecursive >> oh oh I understand okay >> so it's space it is interesting Okay, what's the angular resolution >> at least in in this scenario in other cases we also have in time is also represented in the for domain and that's a question as well can we do that but in this example it's auto >> regressor got it >> what's the angular resolution that you use for for this in in you know in the spherical version >> yeah so it's so all of the data that's available is like I think a quarter like 0.25 25 degrees. So >> in terms of L maybe or I mean in terms of like a spherical harmonic frequency or and >> so this is like oh you mean like how many modes we utilize I think we so for that resolution and we essentially utilize I think most of only a few of them we'll leave out I forget the details but >> I'm just curious like what is the actual angular resolution on the globe that you are resolving to or maybe just the the physical resolution >> I mean that's what that because that's the data we at right. So right now the data we get is like a quarter like 0.25° >> oh okay like 0.25 25 solid angle >> I think kind of comes out to like I don't know 700 by few thousand like resolution so but this is already standard like kind of process >> yeah and just trying to understand like how large of the basis do you need to represent that >> yeah I mean that's really depends on the resolution and and the idea is you know right now our weather data is just limited by this resolution but if you could you know you could like kind of do synthetic climate simulations of even higher resolution, right? And that's kind of the next thing on how to combine these together.

62:51 >> Do you think you can predict with super resolution be and basically resolution lower than the data provided? >> Again, like yes, we can always predict them with the neural operators. but you know, you do want to incorporate more of the physical constraints to ensure that they are valid. >> Okay. So at can we talk about some of the other >> Yes. Yes. So I know it's a lot. >> so this is just showing like how you know what I described that the on the left where the world is being assumed it's a rectangle it blows up very quickly and on the right because we assumed the world was a sphere it kept rolling it out and it kept being stable.

63:34 So >> I still see a little bit of a singularity there at the right >> and it's still like you know so the idea is yes because it's a very long roll out and we have no guardrails of physics we are not you know kind of projecting it to the right physics right this is full extrapolation but the idea is the sphere assumption stabilizes it to a much greater extent >> compared to the left it's a much better but if you're you're in the south pole you're still not going to get >> exactly so it's the poles are the hard part so So this is the example of the fusion reactor. So this is a tok and we are able to model the complex plasma evolution and do this a million times faster than what we could do with traditional simulations. And this was in a way we're creating a digital twin of the plasma right and then we can you know do further things like right now we are as a next step looking at like control but with a full valid physics like being able to prevent disruptions ideally and make fusion sustainable.

64:39 >> So are you simulating MHD equations here or sorry mneto hydrodnamics equations? Yes. Okay. Yeah. And then so for in context disruption in this case is this phenomenon which plagues which plagues plasma physicists where at some point your entire plasma collects in a little tiny beam and then shoots a strong you know right to your containment vessel and it >> and it can damage the reactor and that's the that's a big bottleneck because then you have to kind of shut it down before that happens and then plus it's no longer possible to have a sustainable fusion. So there's a lot of open challenges here but the idea is you know it's very expensive to go do physical experiments. The more you can capture that in the digital twin but ensure physical validity the more you can even do design and other considerations in the digital realm. You know we can hopefully make advances and these are the first steps towards that. The goal is that if you have one of these events that you can somehow adjust the the the magnetic field so that it contains that and and stabilizes it.

65:48 >> Yes. And that's the next step we're doing now. We are looking at like designing both the control and the simulation together. >> Are you working with this specific lab? I'm just curious. So this one was with the UK atomic energy agency and now we're also working with a few others here in the US as well. So we are you know kind of getting the information from many different approaches of fusion itself. So this is the tok. We're also working with stellarators. We are working with different >> stellarators are are tricky.

66:21 >> Yeah. >> But the idea is ideally you know like our goal is to be able to design them in the digital twin. So can we come up with good designs that would make it maybe more practical >> and so that's I think also a good thing as an AI person and much more like you know agnostic and not picking a winner beforehand right like I like to work with different approaches you know and see whether AI can accelerate all of them and then we can kind of you know not prematurely rule out one approach over the other so that's what AI enables us to be more kind of taking risks and exploring different approaches as opposed to in the physical world trying to build any of these. You kind of have to cut a lot of the risky ones and say I'm only going to do this because this the most likely to work. I noticed over your career you started out spending a lot of time on you know really theoretical foundations mathematics of machine learning and maybe I don't know something like six eight years ago you started working really working a lot on applications and branching out in a diverse set of problems. What sort of prompted that shift in your your your approach and what you're looking at? I mean, so you're still working on very hard math problems as well, like for example, the the torch lean work, but the the applications have really grown and I'm wondering what what prompted that and like what were some of the lessons you've learned since then?

67:53 >> Sure. I mean to me it's like you know I feel like I've grown along with AI, right? So when AI was you know in this where neural nets were not working because there wasn't enough data and all kinds of other reasons you know then you kind of have to build the theoretical foundations and try to hope that that leads you to a place where you know you get algorithms to work right and and and and you know back then like tensor methods was with that idea that you know pre-deep learning we still wanted structure we have probabistic models like latent durishlay allocation for topic modeling and solving those were hard but now tensor methods gave us a way to be very practical it's parallel and can be done at large scale but still has nice theoretical basis so those were you know was starting off and then as deep learning started taking off and we could see that it works well in practice and yes there is little bit of maybe theoretical understanding but not a whole lot because of the way how complex it is to me theory should not be a constraint right it should be an enabler and so that's where a lot of like the exploration was oh to make this work well in practice and into Amazon web services then Nvidia so really like making things work at scale and really kind of getting hands dirty right was kind of like where a lot of the development is and now I see a full circle because a lot of d purely datadriven approaches in a way seeing saturation right so now we want to ask okay either make them more hardware efficient right there's a lot of now room to kind of say can we now you know make them much more energy efficient or hardware efficient so that's one aspect but the other is areas like this where in the physical world we don't have enough data we are asking for hard extrapolation you know we want to think of doing discovery by nature it's about extrapol population. So we will never have data about a new discovery. Right?

70:00 That's my definition. And so there we need to again go back to thinking in principled ways in the whether it's architecture design, algorithm design, the right loss functions. So we need to be much more mindful. So I see that coming up full circle because all of the things that work with deep learning, let's take them but make them a bit more principled. There's several other applications which seem very natural. I'm wondering if you've worked on these or did I just miss some papers if I did I'm sorry. so some examples are design of like electromagnetic circuits I think is a big one. or maybe not a big one but I think will be coming up in the near future. Design of let's say materials design of let's say dissipation in heat sinks or or any sort of like fluid flow. As I'm going through what differential equations do I know electromagnetism, I know diffusion equations you know MHD. Yeah. I'm wondering some of the other domains that are >> yeah I mean to me there is just endless possibility right. So there you know as like you can just have this work on any data and we have several other examples.

71:15 So this was like you know being able to ask can we sequester carbon dioxide underground and model how carbon dioxide expands or you know what is the pressure buildup in these reservoirs and you know can we kind of model how they migrate over several decades and so this one we were able to do much faster than what traditional simulations could do. I mean the other aspect is being able to do all kinds of geometric shapes like you know being able to model aerodynamics in cars, planes and so on.

71:50 And so again this is a nice example of a latent space because you can transform a car or any other shape to a donut and then model on the donut and then transform the donut back to the car as well. >> You didn't turn it into a coffee cup. Isn't that the classic joke? Your donut and your coffee cup. >> Exactly. So the idea of like a latent space to handle all kinds of different geometries and and be able to capture the physics there in the latent space well means we can now have a model that generalizes across a lot of different geometries. And my understanding that the maybe the larger vision here is that you can train a foundation model in the sense of being able to model many different physical phenomena with the same model. And so you may fine-tune or there may be some kind of prompt that you give it to have it understand the particular geometry. But that that you you know sort of on all these different physical problems you train and then and then you have your particular one and you're able to model that very effectively.

72:56 >> Yeah. I mean that's really the future right because we have foundation models for language maybe vision but not for physics. So you know the idea is instead of like right now what we've seen are narrow surrogates and we're trying to broaden their scope more and more but ideally we have much broader models that can work on a range of phenomena but also multifysics. So not just have like one single physics but coupled physics the real world has all of the physics kind of coming together in coupled ways.

73:28 So can we bring all that together? So that's one aspect like you know have foundation models that can do design that can do simulation but the other aspect that's really interesting is the inverse problem right so can I now not just simulate but ask what is the best design and then these kinds of like models can like do simulation but you can even do that implicitly and come up with the best design rather than in the earlier era of it was humans trying to come up with design then you go and try to simulate or go to the wind tunnel whatever physical testing and validate that but now you have AI come up with optimized designs but you have the guardrails of physics so you have models that are accurate in physics you have the confidence they work well so you're kind of able to do that as well in the same model >> is there reason have you seen any evidence that you talked about these like sort of multifysics being able to transfer or that that you may be able to generalize to sort of unseen physics.

74:37 >> So I mean you know like the physics by nature if it's completely unseen it's not possible to transfer right I mean I mean if you're saying that we're going beyond the standard model there's absolutely no data that's not possible. but if you're asking about like you know for instance like you know there is the like say I've like you know shown it examples of like just how the heat propagates and there other examples of how the material like stretches and now there is coupling like because of heat there's also stretching or kind of the joint phenomena you could like now hope to fine-tune with much fewer samples because it kind of individually knows this phenomena then combining them together. Maybe it can't do it from scratch because that's still too much to ask. It's highly nonlinear and coupled but it can do it with fewer examples.

75:32 And we've seen evidence of that in a lot of our papers that you able to kind of essentially build up a curriculum. And that's what we see again and again in many of these examples that you know the real world we can kind of control a lot of curriculum and say you know let's kind of build in like modules and put them together and that's what it now allows us to do in a systematic way here. I guess the design aspect I don't know if you wanted to show very quickly.

76:03 So this one was like you know looking at like designing the mask for inverse lithography meaning now this is an inverse design problem and we are also able to do that for designing gates in quantum dots. this is like nonlinear photonics and all of this what is common is the idea that you know there's a forward model that is simulating the physics but now what we want is the inverse design like the problem that of we can optimize the best design and humans are usually not good at this right we are not good at like looking at highly nonlinear phenomena and say oh somehow maybe this combination of all these gates coming together helps pull the electrons together in a quantum gate. And so our collaborators were struggling to do that manually and with AI we're now able to come up with very u efficient designs but also those we know actually work because we have already the simulation as part of the loop saying that they work well. So I think these are examples where we see that it's not just about simulation. It's about really novel designs and novel discoveries that enable us to move the needle of innovation itself.

77:23 >> Each one of these examples takes a lot of domain knowledge. How could somebody take your basic research if a domain expert and and quickly get started applying neural operators and the other frameworks that you've developed to their problem? >> Yeah, you know, neural operators are an open-source library. It's extensively already adopted. It's part of the PyTorch ecosystem. It's, you know, used by a number of not only researchers but also in companies. We have a lot of documentation there. So I encourage people to go there. We have like you know many different architectures, examples, recipes. So I think that's a great place to get started.

78:08 >> You recently joined the UN scientific advisory board. I know we're running out of time, but maybe just can you quickly give a bit of the story behind this and what you hope to accomplish. >> Yeah. Yeah. You know, I'm really honored to be part of that advisory board for the UN and in these tricky times with a lot of geopolitics there, you know, which again I'm not the expert on that. But when it comes to, you know, aspects, especially related to AI, having scientists in the room is something that, you know, I think is very important. I hope I can have an unbiased view and try to provide scientific evidence for any aspect. Right? We want to think about how AI impacts globally like you know how do we ensure the benefits of AI reach everybody how do we democratize access to AI how do we ensure the unintended consequences and harmful impacts can be controlled I think these are just the beginning aspects of course the other side when it comes to weather models I'm already excited like you know there are there is a push to seeing how we can have better weather climate modeling So then or food you know like using weather for better agriculture. So all these aspects are also where UN has a lot of dedicated agencies and people on the ground across the world. So I'm looking forward to contributing and being part of this.

79:31 >> You know looking you know looking at your career and how you you know talk and what you work on it seems like you very much are a person who likes to solve concrete problems. you don't like to philosophize about things which and you're also seem I think maybe more optimistic than a lot of people in the AI space. you have a very hope like hopeful view of the world. I think not honestly always true. what are the ways that you can uniquely bring that viewpoint to the board versus maybe some you know >> Yeah.

80:02 >> Thank you. I I you know to me I think as I said I tried to be unbiased and as a scientist and as a scientist I I think that there's a lot of beneficial aspects of AI that are sometimes missed when we think of only the harmful impacts right and and especially that is with respect to AI for science because a lot of regulatory frameworks equate AI with language models and yes language models can you know manipulate people can have all these kinds of harmful impacts that we should think about controlling. But AI for science is different. So I think this oneizefits-all is where a lot of problems come up. So we have to be mindful that there is you know AI that can change the world with new discoveries and we should enable people around the world to not only benefit from them but also be able to do research you know have access to AI that they can go innovate and use them in interesting ways. One question that we have been trying to ask every guest is if you could pick a bottleneck in your domain that you could magically remove, what would that be and why?

81:18 >> More compute, you know, that's >> I know that's an easy one, maybe a lazy one, right? because you know and and you know of course our compute that we have is growing so much more than even a few years ago thanks to Nvidia thanks to others >> again >> so no comments on that but what I mean by that is also like for research enabling more and more compute you know it's very important I know there are national labs building more supercomputers you know hoping that we can have more compute for research.

81:55 But I think you know without that we cannot experiment, we cannot innovate. I think this is a part that I push a lot and you know I think I cannot emphasize that it's so critical. >> If you had a call to action or something that you would like people to do or think about or or learn about, what would that be? >> Yeah. So you know you can go to neural operator libraries so you can kind of hands-on play with different architectures recipes you know look at use cases but also think about like you know AI for science is not just language models and agents yes that's one aspect of it but ultimately you know those are still like external rappers in a way right until we have AI that fully understands the physical world not just as symbols but as one that can simulate and design and control based on that.

82:52 You know, there's a big piece missing. So that's the other aspect that I think that people should really think about AI for the physical world in this way. >> Anime, this has been so fascinating. I'm I'm excited to check out neural operators myself. I have some ideas in my head already. I really appreciate you taking the time to sit down with us. >> Thank you, Ar. Thank you, Brandon. I really enjoyed it and we really dug deep into a number of things. So, I appreciate you doing that. Thank you.

83:23 >> Thank you.