Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys

@article{Tran2020MultifidelityMW,
  title={Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys},
  author={Anh Tran and Julien Tranchida and Tim Wildey and Aidan P. Thompson},
  journal={The Journal of chemical physics},
  year={2020},
  volume={153 7},
  pages={
          074705
        }
}
We present a scale-bridging approach based on a multi-fidelity (MF) machine-learning (ML) framework leveraging Gaussian processes (GP) to fuse atomistic computational model predictions across multiple levels of fidelity. Through the posterior variance of the MFGP, our framework naturally enables uncertainty quantification, providing estimates of confidence in the predictions. We used density functional theory as high-fidelity prediction, while a ML interatomic potential is used as low-fidelity… 

Figures from this paper

In silico active learning for small molecule properties

TLDR
This research presents a novel approach called “supervised learning” that automates the very labor-intensive and therefore time-heavy and expensive process of manually cataloging and modeling the properties of materials through a probabilistic approach.

Monotonic Gaussian process for physics-constrained machine learning with materials science applications

TLDR
This paper investigates the possibility of constraining a Gaussian process formulation with monotonicity on three different material datasets, where one experimental and two computational datasets are used.

Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning

This study extends the accurate and transferable molecular-orbital-based machine learning (MOB-ML) approach to modeling the contribution of electron correlation to dipole moments at the cost of

A simple denoising approach to exploit multi-fidelity data for machine learning materials properties

TLDR
This work investigates the possibilities in the case of the prediction of the band gap relying on both limited experimental data and density-functional theory relying on exchange-correlation functionals, and introduces an approach which aims to improve the quality of the data through denoising.

PAGP: A physics-assisted Gaussian process framework with active learning for forward and inverse problems of partial differential equations

TLDR
A novel hybrid model combining the continuous and discrete time models is presented and merges the flexibility of continuous time model and the accuracy of the discrete time model.

Machine learning for impurity charge-state transition levels in semiconductors from elemental properties using multi-fidelity datasets.

TLDR
This work significantly reduces the time typically required to predict impurity transition levels using multi-fidelity datasets and a machine learning approach employing features based on elemental properties and impurity positions, and uses the model to predict a complete space of impurity charge-state transition levels in all zinc blende III-V and II-VI systems.

Multi-fidelity prediction of molecular optical peaks with deep learning

Optical properties are central to molecular design for many applications, including solar cells and biomedical imaging. A variety of ab initio and statistical methods have been developed for their

Machine‐learning‐based interatomic potentials for advanced manufacturing

This paper summarizes the progress of machine‐learning‐based interatomic potentials and their applications in advanced manufacturing. Interatomic potential is essential for classical molecular

References

SHOWING 1-10 OF 49 REFERENCES

Roadmap on multiscale materials modeling

Modeling and simulation is transforming modern materials science, becoming an important tool for the discovery of new materials and material phenomena, for gaining insight into the processes that

sMF-BO-2CoGP: A Sequential Multi-Fidelity Constrained Bayesian Optimization Framework for Design Applications

TLDR
The proposed framework, called sMF-BO-2CoGP, is built on a multi-level CoKriging method to predict the objective function, and an external binary classifier is used to distinguish between feasible and infeasible regions.

A New Multi-Objective Bayesian Optimization Formulation With the Acquisition Function for Convergence and Diversity

TLDR
A novel acquisition function is proposed to determine the next sample point, which helps improve the diversity and convergence of the Pareto solutions.

Nudged elastic band calculations accelerated with Gaussian process regression based on inverse inter-atomic distances.

TLDR
A significant improvement to the Gaussian process regression approach is obtained by basing the difference measure between two atomic configurations in the covariance function on the inverted inter-atomic distances and by adding a new early stopping criterion for the path relaxation phase.

A Performance and Cost Assessment of Machine Learning Interatomic Potentials.

TLDR
A comprehensive evaluation of ML-IAPs based on four local environment descriptors --- atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the Spectral Neighbor Analysis Potential (SNAP) bispectrum components, and moment tensors --- using a diverse data set generated using high-throughput density functional theory (DFT) calculations.

Impact of lattice relaxations on phase transitions in a high-entropy alloy studied by machine-learning potentials

Recently, high-entropy alloys (HEAs) have attracted wide attention due to their extraordinary materials properties. A main challenge in identifying new HEAs is the lack of efficient approaches for