Wow, as both Mechanical Engineer(specialized in energy field) and Software Engineer, this was my dream to I want to work on :) I feel very lucky to came across to your channel.
Thank you for the detailed and informative video. Easily saved me from weeks of literature survey effort by providing a review of selected papers across various ML + CFD applications. All the papers mentioned seem like great starting points to delve into the field.
I’m an undergraduate major in fluid mechanics and my instructor studies both machine learning and turbulent flows. It’s good to know this topic has such good prospects
When I first took a lesson of feedback/trained neural network a quarter century ago, I didn't think that it could incorporate existing knowledge. Thanks to this presentation, I learned that it has actually been done.
Stumbled across your channel looking to brush up basics of ML in Fluids, coincidentally after reading the review article you co-authored. Super clear and easy to understand lecture! One thing I would appreciate is a references list of the papers you reference in the video in the video description. Thanks a lot for the video!
This linked vid is some kind of weird thing, but it did put the idea of using a steadily rising pure tone soundtrack over a video as a possible embedded time index.... not sure if it makes more sense than a frame count... but it is interesting. Aside from that though... weird. Oughtta prolly delete.
could you please tell me more about your studies? i have a Ms in CFD and looking for the next step in my studies...very interested in ML, DL and their application in CFD
Thank You For The Brief Summary Of Field. I Enjoyed Your Overview Perspective Of The Basic Subject Matter. The Presented Information Flowed Well Towards Summation And Sufficiently Outlined The General Scope Of Functional Applications. In My Sincere Opinion, Well Done.
Beautiful lecture, Steve. One of my dream projects is to combine topology optimization with fluid mechanics to iterate and develop wing profiles and structures. I'll be looking up on the ways to "bake in" known data to help with the code. Thank you!
This was wonderful to help me in describing my current work challenges with ignorant executives. Beautifully done. The best by far I've ever seen. Kudo's to you!
Thanks so much for making these videos available to the public! I'm currently going through your "Data-Driven Science and Engineering" book in group meetings at UC Berkeley, and these videos are a great additional resource
Thank you so much for providing such an understandable integration of the concepts. I am a Clinical Psychology Ph.D. student (with a career history as a commercial pilot). I am fascinated by the combination of fluid mechanics and psychology (the invisible biology) and what machine learning can provide to the field of psychology in the near future. The psychology field is behind... way behind, on organizing the quant and qual data into usable models--but this gives me a little hope. :)
I would disagree that we have enough data for fluid mechanics unlike other popular problems like image recognition. Fluid problems in general are very complex and unique and as soon as one changes certain conditions, machine learning models become useless. But there is a lot of scope for control problems using reinforcement learning which as such does not solely rely on data.
Machine learning does not only refer to neural networks. Brunton's own method SINDy doi.org/10.1073/pnas.1517384113 has proven useful in identifying the dynamics of fluids solely from data. There is an entire field of research dedicated to developing fluid models strictly from data. I would not write it off so easily.
@@John_Graff Thanks -- I agree, there is such a diversity of methods. Although there is no "silver bullet", there are lots of things to try in different circumstances.
This is a subtlety we think about a lot about actually. Fluids data are vast in some dimensions and sparse in others. Many types of machine learning won't generalize well to new parameter values, but there is a lot of work on methods that do generalize. In fact, fluids is one of the big motivating field to develop new and better techniques.
Thank you for this video. This helped equip me with at least a rudimentary knowledge of the topic that enabled me to ask the questions I needed to ask. You helped me get a job.
Idea - If you define differential equations as loop functions. Ex. y[0] = ...; loop (dydt = y ; y: = y +dydt*dt) then we there should exist loop(loop(loop(...))) functions since that belongs to xyz space. Three loops to initialize a 3D volume.
As someone who transitioned from FEM to ML Engineering, it was funny at first to notice similarities and think, ‘Hey, I’ve seen that before!’ I believe the reason AI isn’t widely used in FEM/CFD today is because, in fact, it was already being utilized early on, just under a different name.
This is exactly the type of video ive been wanting to see. Can we set up a zoom? I would love to talk to you and ask some questions. My name is Isaac Castro I am 21 and about to start my masters program in applied math. In my own time I have been working with machine learning and simple fluid equations. Would love to talk and ask some questions. Let me know!
This is indeed the tip of the iceberg. This topic has been discussed for the last twenty years in the field of turbulent combustion. I hope you mention them in your new review paper.
Hi, first of all I would like to thank you for that great content you are offering for free on UA-cam! I have two questions regarding any kind of reduced order models (built with AE or POD): 1) if you are decomposing the problem into time and space and you say you use "snapshots" of different moments in time, I wonder how do you get the different snapshots at different points in time WITHOUT doing the the high fidelity simulation for the whole timespan? Because in any numerical simulation I know you use one timestep after another and can't skip any timestep... And with doing the whole high fidelity simulation I wonder why would like to built a reduced order model at all? 2) Assuming one can do simulations of different snapshots: How should one space the snapshots values of the high fidelity simulations across the interval of the time/parameter space? For example if I have an intervall from 0 to 1000 and I want 10 modes, do I want modes at 0, 100, 200, ... or unequally spaced points? Is there a literature for this kind of problem? I would be very thankful for an answer and looking forward hearing from you! Kind regards, Daniel
Nice talk Sir. Still, there is a lot more to be done for depicting the turbulent behavior as it's the last Unresolved Mystery of Classical Physics. It's just the beginning of a new era where we are trying to approach the same old problem but with the new tools at hand. Moreover, sir could you please recommend any book that brings together both the topics i.e AI & CFD?
Thank you Steve, if you could please elaborate on this and show us some practical examples/applications that we can do using python/matlab it would be great.
In the example on extrapolation at 23:10 we clearly see a tendency from snapshots a to b, as from the extrapolations b to c. In e) we see clearly a sudden increase in the flow field. My understanding is that this could not be predicted because the snapshots represent only a part of the flow, so unseen fluctuation affect what is visible in this limited windows (more so if these are 2d images of a 3d flow field). This makes sense?
Thanks for the great video. It's very fascinating to hear neural nets constrained by physics principles. How much of background knowledge of fluid mechanics is needed to get started with this kind of problems? (if the current background is computer science and machine learning)
Some solid math background (ODEs and PDEs) would definitely be helpful. Getting up to speed on the fluid dynamics is a bit of a steep learning curve, but definitely possible. I should have some basic fluids videos at some point soon.
Excellent video. Can you please make videos solving problems using ML? I'm asking for Live programming recording. This will be a great help as it will focus on "how" simulations are performed. Cheers
Great work. What is your opinion about the Material Point Method(MPM) to model high-level behavior of fluid dynamics? Ppl are modeling fluid motion behavior using this method in recent papers.
Sounds promising but, Is it really possible to construct generalized models for wide range of fluid flows? given that the physics of fluids is very complicated unlike other fields where ML is being applied. But ML can definitely help us observe some generalized patterns in the fluids (like Kolmogrove's 5/3rd law) that we previously didn't saw or know about. ML algorithms can also help us quickly build custom turbulence models for specific flows that we are interested to learn about with a benefit of lower simulation times. But we need a lot of data.
Very good question. We already have a generalized model for a wide range of fluid flows (the Navier-Stokes equations). I think that one promising area is using ML to build better closure models so we can simulate turbulent systems accurately but with much less compute power.
Would There Then Be A Better Way, Utilizing High Dimensional Modalities, To Fine Tune A Surface To Produce Specific Fluid Dynamic Superstuctures Which Could Be Leveraged To Reduce Drag In Specific Fluids And Conditions?
Is there a way to implement pytorch in OpenFOAM? It would be cool if there is a way to use the output of every step in OpenFOAM sn input for neural network so that it gets better with every simulation. And when it is finally trained you can use the neural network as a solver in OpenFOAM again... :-)
Thanks a lot for the nice lecture, really appreciate it. Could you please let me know how can we try to solve parabolic PDEs or try to predict if the system can show the Turing patterns or not? Could you please let me know from where can I start to know how to solve PDEs in ML? I have so many questions that it is embarrassing for me to type all of them. Once again, love your lectures. Thank you.
Great lecture. Can someone please give insight on how industrial CFD will be changed with ML progressing in fluid mechanics. How prepared an CFD engineer should be in future?. Thank you
Thanks this is a very inspiring video. Could ML for Fluid Mechanics be used to train neonatal artificial respiration systems for best parameterization of air flow intensity with respect to the very small sensible patients lungs - to avoid too strong air flow caused by inaccurate manually parametrization ? I learned that manually parametrizion seems to quit difficult with the risk to be not exactly enough so that early born babies lungs have much higher risk to be negative effected by artificial respiration.
Interesting application. I have heard about a lot of work on computational fluid dynamics (CFD) to simulate these various flows. With enough data and "expert" designed solutions, ML might be able to learn some of these solutions.
Wow, as both Mechanical Engineer(specialized in energy field) and Software Engineer, this was my dream to I want to work on :) I feel very lucky to came across to your channel.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
hi how are you
Merhaba, size birkac soru sormak istiyorum. LinkedIn üzerinden iletişime geçebilir miyiz?
can we connect please?
I've just started my PhD on ML in CFD, thanks for the insight!
Thank you for the detailed and informative video. Easily saved me from weeks of literature survey effort by providing a review of selected papers across various ML + CFD applications. All the papers mentioned seem like great starting points to delve into the field.
The modern professors like you are making things easier for new researcher like me, thank you very much for this lecture series.
Wonderful lecture
I am really interested in this integration between fluid mechanics and machine learning.
I hope this series will continue
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
I’m an undergraduate major in fluid mechanics and my instructor studies both machine learning and turbulent flows. It’s good to know this topic has such good prospects
When I first took a lesson of feedback/trained neural network a quarter century ago, I didn't think that it could incorporate existing knowledge. Thanks to this presentation, I learned that it has actually been done.
You are a great inspiration. It's absolute pleasure of watching your lectures and learning.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
This lecture is pure gold. Having experience with both deep learning and cfd this seems somehow both achievable and straight out of a sci-fi movie
Stumbled across your channel looking to brush up basics of ML in Fluids, coincidentally after reading the review article you co-authored. Super clear and easy to understand lecture!
One thing I would appreciate is a references list of the papers you reference in the video in the video description.
Thanks a lot for the video!
This is an outstanding lecture.
Thanks!
This linked vid is some kind of weird thing, but it did put the idea of using a steadily rising pure tone soundtrack over a video as a possible embedded time index.... not sure if it makes more sense than a frame count... but it is interesting.
Aside from that though... weird. Oughtta prolly delete.
@@johnalley8397 just report the dude, it's spamming the comment section
It's an outstanding lecture. I got into PhD in HPC-CFD and want to use ML,DL, ANN/CNN in CFD. Looking forward to work with you in future Sir.😁
could you please tell me more about your studies?
i have a Ms in CFD and looking for the next step in my studies...very interested in ML, DL and their application in CFD
I am surprised by the fact that this lecture is free. Really great content and clear explanation.
Thank You For The Brief Summary Of Field. I Enjoyed Your Overview Perspective Of The Basic Subject Matter. The Presented Information Flowed Well Towards Summation And Sufficiently Outlined The General Scope Of Functional Applications. In My Sincere Opinion, Well Done.
Beautiful lecture, Steve. One of my dream projects is to combine topology optimization with fluid mechanics to iterate and develop wing profiles and structures. I'll be looking up on the ways to "bake in" known data to help with the code. Thank you!
This was wonderful to help me in describing my current work challenges with ignorant executives. Beautifully done. The best by far I've ever seen. Kudo's to you!
Thanks so much for making these videos available to the public! I'm currently going through your "Data-Driven Science and Engineering" book in group meetings at UC Berkeley, and these videos are a great additional resource
Nice! Glad they are helping
Finally some coherent talk on integration for both.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Inspiring speech of a trending field of computational engineering.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Greeeat!! I read this year's Raissi and Karniadakis' paper in Science and I definitely want to know more
That's a super interesting paper!
Thank you so much for providing such an understandable integration of the concepts. I am a Clinical Psychology Ph.D. student (with a career history as a commercial pilot). I am fascinated by the combination of fluid mechanics and psychology (the invisible biology) and what machine learning can provide to the field of psychology in the near future. The psychology field is behind... way behind, on organizing the quant and qual data into usable models--but this gives me a little hope. :)
An excellent method of presentation and description of the knowledge.
A most excellent video lecture, perfect for an introduction to fluid mechanics research.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Fantastic presentation Steve. Curiosity rules! Grateful.
Thank you for your wonderful lecture, Dr. Brunton. This is what I really want to learn.
Wonderful!
This is absolutely brilliant and inspiring. Thank you such a detailed introduction to ML for Fluid Mechanics
I would disagree that we have enough data for fluid mechanics unlike other popular problems like image recognition. Fluid problems in general are very complex and unique and as soon as one changes certain conditions, machine learning models become useless. But there is a lot of scope for control problems using reinforcement learning which as such does not solely rely on data.
I agree
Machine learning does not only refer to neural networks. Brunton's own method SINDy doi.org/10.1073/pnas.1517384113 has proven useful in identifying the dynamics of fluids solely from data. There is an entire field of research dedicated to developing fluid models strictly from data. I would not write it off so easily.
@@John_Graff Thanks -- I agree, there is such a diversity of methods. Although there is no "silver bullet", there are lots of things to try in different circumstances.
This is a subtlety we think about a lot about actually. Fluids data are vast in some dimensions and sparse in others. Many types of machine learning won't generalize well to new parameter values, but there is a lot of work on methods that do generalize. In fact, fluids is one of the big motivating field to develop new and better techniques.
Thank you for this video. This helped equip me with at least a rudimentary knowledge of the topic that enabled me to ask the questions I needed to ask. You helped me get a job.
I am loving this channel
So glad to hear that!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Thank you very much, such an inspiring talk and insightful overview.
Glad you enjoyed it!
Idea - If you define differential equations as loop functions. Ex. y[0] = ...; loop (dydt = y ; y: = y +dydt*dt) then we there should exist loop(loop(loop(...))) functions since that belongs to xyz space. Three loops to initialize a 3D volume.
thank you for presenting such an interesting topic
Thanks, for Integrating my two favourite fields of study. ❤❤
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Fantastic overview, watched your video because I was getting stuck in my model I might change direction.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
This is such a great video of top view of ML in FM. Loved it!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
As someone who transitioned from FEM to ML Engineering, it was funny at first to notice similarities and think, ‘Hey, I’ve seen that before!’ I believe the reason AI isn’t widely used in FEM/CFD today is because, in fact, it was already being utilized early on, just under a different name.
I am working a atmospheric modelling. It's my pleasure to be here. I hope I will meet you in future.
Superb. This is simply one of the best UA-cam I ever watched ! Thanks for sharing..
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Simply amazing! Can't wait to watch more!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
got this recommended after watching your Von Karman and IPAM lectures :)
great stuff !
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Im an ex FEA simulation engineer doing Data Science. I never thought these two fields could work together
Brilliant presentation, thanks for sharing!
Can you please make videos on non-linear control systems.
This would be great
In the works!
This is exactly the type of video ive been wanting to see. Can we set up a zoom? I would love to talk to you and ask some questions. My name is Isaac Castro I am 21 and about to start my masters program in applied math. In my own time I have been working with machine learning and simple fluid equations. Would love to talk and ask some questions. Let me know!
Could the internet hold my B@llz? I am U(t), the only perfect non-linear control system.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
This is an excellent introduction, thank you very much, I found it tremendously helpful.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Wow. At about 15 minutes that noise and "corrupted pixels" in the images produces noise in the transcoding and UA-cam compression algorithm. Crazy.
Wild!
meta
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Very very nice end examples of inspiration
Thank you UA-cam for letting me find this.
So nice explanation. I can't help myself subscribing your channel!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
You are just great!
Kindly share more videos on this topic
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
This is indeed the tip of the iceberg. This topic has been discussed for the last twenty years in the field of turbulent combustion. I hope you mention them in your new review paper.
This is really interesting and worth investigating.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Hi,
first of all I would like to thank you for that great content you are offering for free on UA-cam!
I have two questions regarding any kind of reduced order models (built with AE or POD):
1) if you are decomposing the problem into time and space and you say you use "snapshots" of different moments in time, I wonder how do you get the different snapshots at different points in time WITHOUT doing the the high fidelity simulation for the whole timespan? Because in any numerical simulation I know you use one timestep after another and can't skip any timestep... And with doing the whole high fidelity simulation I wonder why would like to built a reduced order model at all?
2) Assuming one can do simulations of different snapshots: How should one space the snapshots values of the high fidelity simulations across the interval of the time/parameter space? For example if I have an intervall from 0 to 1000 and I want 10 modes, do I want modes at 0, 100, 200, ... or unequally spaced points?
Is there a literature for this kind of problem?
I would be very thankful for an answer and looking forward hearing from you!
Kind regards,
Daniel
Impressive lecture, thank you very much !
Many thanks!
This was much needed thank you 😀
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Great job as always Steve! :)
Thanks!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Steve I can't follow half of what you are saying... but I LOVE these videos!!!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
A really wonderful Lecture. Thank you for this!
Thank you so much, Steve!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
This looks interesting, awesome and tough at the same time. Wow!
Fantastic video!
Glad you like it!
This is EXACTLY what I was looking for...
you are so great lector. thank you for videos
I love this video! I will check out the papers. Thanks
Awesome, thanks!
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Nice talk Sir. Still, there is a lot more to be done for depicting the turbulent behavior as it's the last Unresolved Mystery of Classical Physics. It's just the beginning of a new era where we are trying to approach the same old problem but with the new tools at hand. Moreover, sir could you please recommend any book that brings together both the topics i.e AI & CFD?
Really Enjoyed this video! Thank you
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Thanks for posting this video
Thank you Steve, if you could please elaborate on this and show us some practical examples/applications that we can do using python/matlab it would be great.
Will do, but might take some time.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
@@elaiottoiale4216 its said that 404.
Very nice video , thank you very much Steve. I just have a question the input to the deep learning model will be just pictures ??
In the example on extrapolation at 23:10 we clearly see a tendency from snapshots a to b, as from the extrapolations b to c. In e) we see clearly a sudden increase in the flow field. My understanding is that this could not be predicted because the snapshots represent only a part of the flow, so unseen fluctuation affect what is visible in this limited windows (more so if these are 2d images of a 3d flow field). This makes sense?
Thank you steve. I was wondering if a control engineer has to know machine learning not to fall behind.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
@Steve Brunton, What would be the best book to learn machine learning for a beginner?
Thank you a lot!
Great video
God help and guide you
Which are good universities for studying "Machine Learning for Fluid Mechanics"? Can anyone explain?
Thanks for the great video. It's very fascinating to hear neural nets constrained by physics principles. How much of background knowledge of fluid mechanics is needed to get started with this kind of problems? (if the current background is computer science and machine learning)
Some solid math background (ODEs and PDEs) would definitely be helpful. Getting up to speed on the fluid dynamics is a bit of a steep learning curve, but definitely possible. I should have some basic fluids videos at some point soon.
Excellent video. Can you please make videos solving problems using ML? I'm asking for Live programming recording. This will be a great help as it will focus on "how" simulations are performed. Cheers
very inspiring lecture !
Can you make complete playlist for CFD ?
Really nice lectures!!!!!!
So cool lecture, thanks👍
Great work. What is your opinion about the Material Point Method(MPM) to model high-level behavior of fluid dynamics? Ppl are modeling fluid motion behavior using this method in recent papers.
Love to see you standing in Earthrise lmao, looked slick
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Can anyone please suggest to me a book to read or a course to enroll in to develop a skill in machine learning-aided cfd?
God knows how many times I've seen this video.
*raises. RAISES the question! Begging the question is akin to tautology in logic.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
Sounds promising but, Is it really possible to construct generalized models for wide range of fluid flows? given that the physics of fluids is very complicated unlike other fields where ML is being applied. But ML can definitely help us observe some generalized patterns in the fluids (like Kolmogrove's 5/3rd law) that we previously didn't saw or know about. ML algorithms can also help us quickly build custom turbulence models for specific flows that we are interested to learn about with a benefit of lower simulation times. But we need a lot of data.
Very good question. We already have a generalized model for a wide range of fluid flows (the Navier-Stokes equations). I think that one promising area is using ML to build better closure models so we can simulate turbulent systems accurately but with much less compute power.
Would There Then Be A Better Way, Utilizing High Dimensional Modalities, To Fine Tune A Surface To Produce Specific Fluid Dynamic Superstuctures Which Could Be Leveraged To Reduce Drag In Specific Fluids And Conditions?
Perhaps Some Answers To That Lay Openly Observable In Nature?
Thanks Steve
Is there a way to implement pytorch in OpenFOAM? It would be cool if there is a way to use the output of every step in OpenFOAM sn input for neural network so that it gets better with every simulation. And when it is finally trained you can use the neural network as a solver in OpenFOAM again... :-)
Dear Steve Brunton, Thanks for the great lecture. Any suggestions on datasets to train these flow models
Johns Hopkins and Stanford both have open data sets for training.
@@Eigensteve Thanks
Thanks a lot for the nice lecture, really appreciate it. Could you please let me know how can we try to solve parabolic PDEs or try to predict if the system can show the Turing patterns or not? Could you please let me know from where can I start to know how to solve PDEs in ML? I have so many questions that it is embarrassing for me to type all of them.
Once again, love your lectures.
Thank you.
Great lecture. Can someone please give insight on how industrial CFD will be changed with ML progressing in fluid mechanics. How prepared an CFD engineer should be in future?.
Thank you
Thanks this is a very inspiring video.
Could ML for Fluid Mechanics be used to train neonatal artificial respiration systems for best parameterization of air flow intensity with respect to the very small sensible patients lungs - to avoid too strong air flow caused by inaccurate manually parametrization ?
I learned that manually parametrizion seems to quit difficult with the risk to be not exactly enough so that early born babies lungs have much higher risk to be negative effected by artificial respiration.
Interesting application. I have heard about a lot of work on computational fluid dynamics (CFD) to simulate these various flows. With enough data and "expert" designed solutions, ML might be able to learn some of these solutions.
Interesting that when discussing the corruption of flow paper, the video quality seemed to drop, compression I imagine?
Neat! I hadn't noticed this before.
ua-cam.com/video/DsmhKZvKyi8/v-deo.html
how would guide someone who wants to get into this area of reasearch
I have a question, I'm now confused about ai for CFD. like POD, dmd, on my opinion, it's just cfd with data. So where is the inteligent?
Great thanks!
Can you suggest some accessible textbooks on the subject?
Great....From where should I learn ML for FM?
i love the black background