Integrating Machine Learning with HPC-driven Simulations for Enhanced Student Learning

Jadhao, Vikram; Kadupitiya, J. C. S.

doi:10.1109/eduhpc51895.2020.00009

Cited by 4 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples include DNNs that predict adsorption equilibria for different thermodynamic conditions, 11 DNNbased denoising autoencoders that predict the temporally averaged radial distribution function of Lennard-Jones fluids from a single snapshot of fluid particles generated in MD simulations, 9 Bayesian neural networks that predict the dissociation time scale of compounds bypassing the explicit time evolution of the particle trajectories in ab initio MD simulations, 10 and autoencoders that generate new protein-like structures and act as a proxy for MD simulations to mine the protein conformational space. 17 In our previous work, 15,16,18 we introduced ML surrogates for the MD simulations of soft materials. Our goal was to demonstrate that artificial neural network (ANN) based regression models can accurately predict the relationships between the input parameters characterizing the soft-matter system and the simulation outcomes describing the system's equilibrium properties.…”

Section: Introductionmentioning

confidence: 99%

“…In our previous work, ,, we introduced ML surrogates for the MD simulations of soft materials. Our goal was to demonstrate that artificial neural network (ANN) based regression models can accurately predict the relationships between the input parameters characterizing the soft-matter system and the simulation outcomes describing the system’s equilibrium properties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probing Accuracy-Speedup Tradeoff in Machine Learning Surrogates for Molecular Dynamics Simulations

Sun

Kadupitiya

Jadhao

2023

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

The performance promise of machine learning surrogates of molecular dynamics simulations of soft materials is significant but generally comes at the cost of acquiring large training datasets to learn the complex relationships between input soft material attributes and output properties. Under the constraint of limited high-performance computing resources, optimizing the size of the training datasets becomes paramount. Using an artificial neural network based surrogate for molecular dynamics simulations of confined electrolytes, we explore the tradeoff between surrogate accuracy and computational gains. Accuracy is assessed by computing the root-mean-square errors between the surrogate predictions and the ground truth results obtained via molecular dynamics simulations. The computational performance is judged by evaluating the speedup which incorporates the training dataset creation time. Improvement in accuracy occurs with a loss of speedup, which scales as the inverse of the training dataset size. The link between surrogate generalizability and the accuracy-speedup tradeoff is assessed by examining the errors incurred in surrogate predictions on unseen, interpolated input variables and developing a net speedup metric to capture the associated gains.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Probing Accuracy-Speedup Tradeoff in Machine Learning Surrogates for Molecular Dynamics Simulations

Sun

Kadupitiya

Jadhao

2023

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

Probing the Rheological Properties of Liquids Under Conditions of Elastohydrodynamic Lubrication Using Simulations and Machine Learning

Kadupitiya

Jadhao

2021

Tribol Lett

Self Cite

View full text Add to dashboard Cite

In elastohydrodynamic lubrication (EHL), the lubricant experiences pressures in excess of 500 MPa and strain rates larger than $$10^5$$ 10 5 $$\text{s}^{-1}$$ s - 1 . The high pressures lead to a dramatic rise in the Newtonian viscosity and the high rates lead to large shear stresses and pronounced shear thinning. The extraction of accurate rheological properties using non-equilibrium molecular dynamics simulations (NEMD) has played a key role in improving our understanding of lubricant flow in EHL conditions. However, the high dimensionality of the output data generated by NEMD simulations often makes a deeper interrogation of the link between molecular-scale features and rheological properties challenging. In this paper, we explore the use of machine learning to analyze and visualize the high-dimensional output data generated in typical NEMD simulations. We show that dimension reduction of NEMD simulation data describing the shear flow of squalane enables a clear visualization of the transition from Newtonian to non-Newtonian shear thinning with increasing shear rate and provides a reliable assessment of the correlation between shear thinning and the evolution in molecular alignment. The end-to-end atom pairs dominate the largest variations in pair orientation tensor components for low-pressure systems (0.1, 100 MPa) and provide the clearest separation of the orientation tensors with rate. On the other hand, the side atom pairs dominate the largest variation in the tensor components for the high-pressure systems ($$P\ge 400$$ P ≥ 400 MPa) which exhibit an overall limited evolution in orientation tensors as a function of rate. Dimension reduction using all the six components of the orientation tensors of all 435 pairs associated with a squalane molecule shows that the decrease in viscosity with rate for low pressures is strongly correlated with changes in molecular alignment. However, for high pressures, shear thinning occurs at saturated orientational order.

show abstract

Hybrid workflow of Simulation and Deep Learning on HPC: A Case Study for Material Behavior Determination

Zhong¹,

Hoppe²,

Zhou³

et al. 2021

2021 IEEE International Conference on Cluster Computing (CLUSTER)

View full text Add to dashboard Cite

Integrating Machine Learning with HPC-driven Simulations for Enhanced Student Learning

Cited by 4 publications

References 27 publications

Probing Accuracy-Speedup Tradeoff in Machine Learning Surrogates for Molecular Dynamics Simulations

Probing Accuracy-Speedup Tradeoff in Machine Learning Surrogates for Molecular Dynamics Simulations

Probing the Rheological Properties of Liquids Under Conditions of Elastohydrodynamic Lubrication Using Simulations and Machine Learning

Hybrid workflow of Simulation and Deep Learning on HPC: A Case Study for Material Behavior Determination

Contact Info

Product

Resources

About