Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00007
F. Orland, Kim Sebastian Brose, Julian Bissantz, F. Ferraro, C. Terboven, C. Hasse
In High-Performance Computing, new use cases are currently emerging in which classical numerical simulations are coupled with machine learning as a surrogate for complex physical models that are expensive to compute. In the context of simulating reactive thermo-fluid systems, the idea to replace current state-of-the-art tabulated chemistry with machine learning inference is an active field of research. For this purpose, a simplified OpenFOAM application is coupled with an artificial neural network. In this work, we present a case study focusing solely on the performance of the coupled OpenFOAM-ML application. Our coupling approach features a heterogeneous cluster architecture combining pure CPU nodes and nodes equipped with two Nvidia V100 GPUs. We evaluate our approach by comparing the inference performance and the communication our approach induces with various machine learning frameworks. Additionally, we also compare the GPUs with NEC Vector Engine Type 10B regarding inference performance.
{"title":"A Case Study on Coupling OpenFOAM with Different Machine Learning Frameworks","authors":"F. Orland, Kim Sebastian Brose, Julian Bissantz, F. Ferraro, C. Terboven, C. Hasse","doi":"10.1109/AI4S56813.2022.00007","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00007","url":null,"abstract":"In High-Performance Computing, new use cases are currently emerging in which classical numerical simulations are coupled with machine learning as a surrogate for complex physical models that are expensive to compute. In the context of simulating reactive thermo-fluid systems, the idea to replace current state-of-the-art tabulated chemistry with machine learning inference is an active field of research. For this purpose, a simplified OpenFOAM application is coupled with an artificial neural network. In this work, we present a case study focusing solely on the performance of the coupled OpenFOAM-ML application. Our coupling approach features a heterogeneous cluster architecture combining pure CPU nodes and nodes equipped with two Nvidia V100 GPUs. We evaluate our approach by comparing the inference performance and the communication our approach induces with various machine learning frameworks. Additionally, we also compare the GPUs with NEC Vector Engine Type 10B regarding inference performance.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121842609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00012
Lesi Wang, Dongfang Zhao
Federated learning (FL) is deemed a promising paradigm for privacy-preserving data analytics in collaborative scientific computing. However, there lacks an effective and easy-to-use FL infrastructure for scientific computing and high-performance computing (HPC) environments. The objective of this position paper is two-fold. Firstly, we identify three missing pieces of a scientific FL infrastructure: (i) a native MPI programming interface that can be seamlessly integrated into existing scientific applications, (ii) an independent data layer for the FL system such that the user can pick the persistent medium for her own choice, such as parallel file systems and multidimensional databases, and (iii) efficient encryption protocols that are optimized for scientific workflows. The second objective of this paper is to present a work-in-progress FL infrastructure, namely MPI-FL, which is implemented with PyTorch and MPI4py. We deploy MPI-FL on 1,000 CPU cores and evaluate it with four standard benchmarks: MNIST, Fashion-MNIST, CIFAR-10, and SVHN-extra. It is our hope that the scientific computing and HPC community would find MPI-FL useful for their FL-related projects.
{"title":"Practical Federated Learning Infrastructure for Privacy-Preserving Scientific Computing","authors":"Lesi Wang, Dongfang Zhao","doi":"10.1109/AI4S56813.2022.00012","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00012","url":null,"abstract":"Federated learning (FL) is deemed a promising paradigm for privacy-preserving data analytics in collaborative scientific computing. However, there lacks an effective and easy-to-use FL infrastructure for scientific computing and high-performance computing (HPC) environments. The objective of this position paper is two-fold. Firstly, we identify three missing pieces of a scientific FL infrastructure: (i) a native MPI programming interface that can be seamlessly integrated into existing scientific applications, (ii) an independent data layer for the FL system such that the user can pick the persistent medium for her own choice, such as parallel file systems and multidimensional databases, and (iii) efficient encryption protocols that are optimized for scientific workflows. The second objective of this paper is to present a work-in-progress FL infrastructure, namely MPI-FL, which is implemented with PyTorch and MPI4py. We deploy MPI-FL on 1,000 CPU cores and evaluate it with four standard benchmarks: MNIST, Fashion-MNIST, CIFAR-10, and SVHN-extra. It is our hope that the scientific computing and HPC community would find MPI-FL useful for their FL-related projects.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131113594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00006
Orcun Yildiz, Henry Chan, Krishnan Raghavan, W. Judge, M. Cherukara, Prasanna Balaprakash, S. Sankaranarayanan, T. Peterka
X-ray Bragg coherent diffraction imaging (BCDI) is widely used for materials characterization. However, obtaining X-ray diffraction data is difficult and computationally intensive. Here, we introduce a machine learning approach to identify crystalline line defects in samples from the raw coherent diffraction data. To automate this process, we compose a workflow coupling coherent diffraction data generation with training and inference of deep neural network defect classifiers. In particular, we adopt a continual learning approach, where we generate training and inference data as needed based on the accuracy of the defect classifier instead of all training data generated a priori. The results show that our approach improves the accuracy of defect classifiers while using much fewer samples of data.
{"title":"Automated Continual Learning of Defect Identification in Coherent Diffraction Imaging","authors":"Orcun Yildiz, Henry Chan, Krishnan Raghavan, W. Judge, M. Cherukara, Prasanna Balaprakash, S. Sankaranarayanan, T. Peterka","doi":"10.1109/AI4S56813.2022.00006","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00006","url":null,"abstract":"X-ray Bragg coherent diffraction imaging (BCDI) is widely used for materials characterization. However, obtaining X-ray diffraction data is difficult and computationally intensive. Here, we introduce a machine learning approach to identify crystalline line defects in samples from the raw coherent diffraction data. To automate this process, we compose a workflow coupling coherent diffraction data generation with training and inference of deep neural network defect classifiers. In particular, we adopt a continual learning approach, where we generate training and inference data as needed based on the accuracy of the defect classifier instead of all training data generated a priori. The results show that our approach improves the accuracy of defect classifiers while using much fewer samples of data.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133385875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00011
H. Ahmed, Roselyne B. Tchoua, J. Lofstead
Science is a practice of systematically studying something and offering data and evidence to reach a conclusion. With first principles simulations, basic physics are used to model some phenomena leading to consistent, repeatable results. With an incomplete physics model or models too complex or costly to run for a given task, AI or ML are being used to estimate what the missing physics would be if we could meet our goals with a first principles approach. Our work has been exploring how to ensure ML is capable of offering a science level of consistency so we can trust our science applications incorporating ML models. Our earlier work examined the impact of pseudorandom numbers on model quality. For this study, we have examined the pseudo-random number generation algorithms used to seed essentially all ML algorithms to ensure that model generation can be performed by other scientists to achieve identical results.
{"title":"Ensuring AI For Science is Science: Making Randomness Portable","authors":"H. Ahmed, Roselyne B. Tchoua, J. Lofstead","doi":"10.1109/AI4S56813.2022.00011","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00011","url":null,"abstract":"Science is a practice of systematically studying something and offering data and evidence to reach a conclusion. With first principles simulations, basic physics are used to model some phenomena leading to consistent, repeatable results. With an incomplete physics model or models too complex or costly to run for a given task, AI or ML are being used to estimate what the missing physics would be if we could meet our goals with a first principles approach. Our work has been exploring how to ensure ML is capable of offering a science level of consistency so we can trust our science applications incorporating ML models. Our earlier work examined the impact of pseudorandom numbers on model quality. For this study, we have examined the pseudo-random number generation algorithms used to seed essentially all ML algorithms to ensure that model generation can be performed by other scientists to achieve identical results.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128451997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ai4s56813.2022.00005
{"title":"AI4S 22 Workshop Organization","authors":"","doi":"10.1109/ai4s56813.2022.00005","DOIUrl":"https://doi.org/10.1109/ai4s56813.2022.00005","url":null,"abstract":"","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127119036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ai4s56813.2022.00004
{"title":"Message from the AI4S22 Workshop Chairs","authors":"","doi":"10.1109/ai4s56813.2022.00004","DOIUrl":"https://doi.org/10.1109/ai4s56813.2022.00004","url":null,"abstract":"","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131745254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00010
Akashnil Dutta, J. Alcaraz, Ali TehraniJamsaz, A. Sikora, Eduardo César, A. Jannesari
Stagnation of Moore's law has led to the increased adoption of parallel programming for enhancing performance of scientific applications. Frequently occurring code and design patterns in scientific applications are often used for transforming serial code to parallel. But, identifying these patterns is not easy. To this end, we propose using Graph Neural Networks for modeling code flow graphs to identify patterns in such parallel code. Additionally, identifying the runtime parameters for best performing parallel code is also challenging. We propose a pattern-guided deep learning based tuning approach, to help identify the best runtime parameters for OpenMP loops. Overall, we aim to identify commonly occurring patterns in parallel loops and use these patterns to guide auto-tuning efforts. We validate our hypothesis on 20 different applications from Polybench, and STREAM benchmark suites. This deep learning-based approach can identify the considered patterns with an overall accuracy of 91%. We validate the usefulness of using patterns for auto-tuning on tuning the number of threads, scheduling policies and chunk size on a single socket system, and the thread count and affinity on a multi-socket machine. Our approach achieves geometric mean speedups of $1.1times$ and $4.7times$ respectively over default OpenMP configurations, compared to brute-force speedups of $1.27times$ and $4.93times$ respectively.
{"title":"Pattern-based Autotuning of OpenMP Loops using Graph Neural Networks","authors":"Akashnil Dutta, J. Alcaraz, Ali TehraniJamsaz, A. Sikora, Eduardo César, A. Jannesari","doi":"10.1109/AI4S56813.2022.00010","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00010","url":null,"abstract":"Stagnation of Moore's law has led to the increased adoption of parallel programming for enhancing performance of scientific applications. Frequently occurring code and design patterns in scientific applications are often used for transforming serial code to parallel. But, identifying these patterns is not easy. To this end, we propose using Graph Neural Networks for modeling code flow graphs to identify patterns in such parallel code. Additionally, identifying the runtime parameters for best performing parallel code is also challenging. We propose a pattern-guided deep learning based tuning approach, to help identify the best runtime parameters for OpenMP loops. Overall, we aim to identify commonly occurring patterns in parallel loops and use these patterns to guide auto-tuning efforts. We validate our hypothesis on 20 different applications from Polybench, and STREAM benchmark suites. This deep learning-based approach can identify the considered patterns with an overall accuracy of 91%. We validate the usefulness of using patterns for auto-tuning on tuning the number of threads, scheduling policies and chunk size on a single socket system, and the thread count and affinity on a multi-socket machine. Our approach achieves geometric mean speedups of $1.1times$ and $4.7times$ respectively over default OpenMP configurations, compared to brute-force speedups of $1.27times$ and $4.93times$ respectively.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130060797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/AI4S56813.2022.00013
Mathew Boyer, W. Brewer, D. Jude, I. Dettwiller
Integration of machine learning with simulation is part of a growing trend, however, the augmentation of codes in a highly-performant, distributed manner poses a software development challenge. In this work, we explore the question of how to easily augment legacy simulation codes on high-performance computers (HPCs) with machine-learned surrogate models, in a fast, scalable manner. Initial naïve augmentation attempts required significant code modification and resulted in significant slowdown. This led us to explore inference server techniques, which allow for model calls through drop-in functions. In this work, we investigated TensorFlow Serving with $mathbf{gRPC}$ and RedisAI with SmartRedis for server-client inference implementations, where the deep learning platform runs as a persistent process on HPC compute node GPUs and the simulation makes client calls while running on the CPUs. We evaluated inference performance for several use cases on SCOUT, an IBM POWER9 supercomputer, including, real gas equations of state, machine-learned boundary conditions for rotorcraft aerodynamics, and super-resolution techniques. We will discuss key findings on performance. The lessons learned may provide useful advice for researchers to augment their simulation codes in an optimal manner.
{"title":"Scalable Integration of Computational Physics Simulations with Machine Learning","authors":"Mathew Boyer, W. Brewer, D. Jude, I. Dettwiller","doi":"10.1109/AI4S56813.2022.00013","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00013","url":null,"abstract":"Integration of machine learning with simulation is part of a growing trend, however, the augmentation of codes in a highly-performant, distributed manner poses a software development challenge. In this work, we explore the question of how to easily augment legacy simulation codes on high-performance computers (HPCs) with machine-learned surrogate models, in a fast, scalable manner. Initial naïve augmentation attempts required significant code modification and resulted in significant slowdown. This led us to explore inference server techniques, which allow for model calls through drop-in functions. In this work, we investigated TensorFlow Serving with $mathbf{gRPC}$ and RedisAI with SmartRedis for server-client inference implementations, where the deep learning platform runs as a persistent process on HPC compute node GPUs and the simulation makes client calls while running on the CPUs. We evaluated inference performance for several use cases on SCOUT, an IBM POWER9 supercomputer, including, real gas equations of state, machine-learned boundary conditions for rotorcraft aerodynamics, and super-resolution techniques. We will discuss key findings on performance. The lessons learned may provide useful advice for researchers to augment their simulation codes in an optimal manner.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122270200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-10DOI: 10.1109/AI4S56813.2022.00009
Nadav Schneider, M. Rusanovsky, R. Gvishi, G. Oren
High energy density physics (HEDP) experiments commonly involve a dynamic wave-front propagating inside a lowdensity foam. This effect affects its density and hence, its transparency. A common problem in foam production is the creation of defective foams. Accurate information on their dimension and homogeneity is required to classify the foams' quality. Therefore, those parameters are being characterized using a 3D-measuring laser confocal microscope. For each foam, five images are taken: two 2D images representing the top and bottom surface foam planes and three images of side cross-sections from 3D scannings. An expert has to do the complicated, harsh, and exhausting work of manually classifying the foam's quality through the image set and only then determine whether the foam can be used in experiments or not. Currently, quality has two binary levels of normal vs. defective. At the same time, experts are commonly required to classify a sub-class of normal-defective, i.e., defective foams but might be sufficient for the needed experiment. This sub-class is problematic due to inconclusive judgment that is primarily intuitive. In this work, we present a novel state─of─the─art multi-view deep learning classification model that mimics the physicist's perspective by automatically determining the foams' quality classification and thus aids the expert. Our model achieved 86% accuracy on upper and lower surface foam planes and 82% on the entire set, suggesting interesting heuristics to the problem. A significant added value in this work is the ability to regress the foam quality instead of binary deduction and even explain the decision visually. The source code used in this work, as well as other relevant sources, are available at: https://github.com/Scientific-Computing-Lab-NRCNIMulti-View-Foams.git.
{"title":"Determining HEDP Foams' Quality with Multi-View Deep Learning Classification","authors":"Nadav Schneider, M. Rusanovsky, R. Gvishi, G. Oren","doi":"10.1109/AI4S56813.2022.00009","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00009","url":null,"abstract":"High energy density physics (HEDP) experiments commonly involve a dynamic wave-front propagating inside a lowdensity foam. This effect affects its density and hence, its transparency. A common problem in foam production is the creation of defective foams. Accurate information on their dimension and homogeneity is required to classify the foams' quality. Therefore, those parameters are being characterized using a 3D-measuring laser confocal microscope. For each foam, five images are taken: two 2D images representing the top and bottom surface foam planes and three images of side cross-sections from 3D scannings. An expert has to do the complicated, harsh, and exhausting work of manually classifying the foam's quality through the image set and only then determine whether the foam can be used in experiments or not. Currently, quality has two binary levels of normal vs. defective. At the same time, experts are commonly required to classify a sub-class of normal-defective, i.e., defective foams but might be sufficient for the needed experiment. This sub-class is problematic due to inconclusive judgment that is primarily intuitive. In this work, we present a novel state─of─the─art multi-view deep learning classification model that mimics the physicist's perspective by automatically determining the foams' quality classification and thus aids the expert. Our model achieved 86% accuracy on upper and lower surface foam planes and 82% on the entire set, suggesting interesting heuristics to the problem. A significant added value in this work is the ability to regress the foam quality instead of binary deduction and even explain the decision visually. The source code used in this work, as well as other relevant sources, are available at: https://github.com/Scientific-Computing-Lab-NRCNIMulti-View-Foams.git.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124362398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-30DOI: 10.1109/AI4S56813.2022.00008
Rajat Arora
Traditional numerical approaches have been successfully used to model mechanical behavior of heterogeneous materials (composites, multicomponent alloys, and polycrystals) widely used in industrial applications. However, these methods require a fine mesh resulting in computationally expensive and time-consuming calculations. The physics-informed deep-learning based super-resolution framework (PhySRNet) introduced in this paper is aimed at overcoming this computational challenge. PhySRNet enables reconstruction of high-resolution solution fields from their low-resolution counterparts without requiring labeled data, thereby allowing researchers to run their numerical simulations on a coarse mesh. Through an illustrative example, we demonstrate that the super-resolved fields match the accuracy of an advanced numerical solver running at 400 times the coarse mesh resolution and satisfy the (highly nonlinear) governing laws. The approach opens the door to applying machine learning and traditional numerical approaches in tandem to reduce computational complexity and accelerate scientific discovery and engineering design.
{"title":"PhySRNet: Physics informed super-resolution network for application in computational solid mechanics","authors":"Rajat Arora","doi":"10.1109/AI4S56813.2022.00008","DOIUrl":"https://doi.org/10.1109/AI4S56813.2022.00008","url":null,"abstract":"Traditional numerical approaches have been successfully used to model mechanical behavior of heterogeneous materials (composites, multicomponent alloys, and polycrystals) widely used in industrial applications. However, these methods require a fine mesh resulting in computationally expensive and time-consuming calculations. The physics-informed deep-learning based super-resolution framework (PhySRNet) introduced in this paper is aimed at overcoming this computational challenge. PhySRNet enables reconstruction of high-resolution solution fields from their low-resolution counterparts without requiring labeled data, thereby allowing researchers to run their numerical simulations on a coarse mesh. Through an illustrative example, we demonstrate that the super-resolved fields match the accuracy of an advanced numerical solver running at 400 times the coarse mesh resolution and satisfy the (highly nonlinear) governing laws. The approach opens the door to applying machine learning and traditional numerical approaches in tandem to reduce computational complexity and accelerate scientific discovery and engineering design.","PeriodicalId":262536,"journal":{"name":"2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114325637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：