Rhys E. A. Goodall
YOU?
Author Swipe
View article: TorchSim: An efficient atomistic simulation engine in PyTorch
TorchSim: An efficient atomistic simulation engine in PyTorch Open
We introduce TorchSim, an open-source atomistic simulation engine tailored for the Machine Learned Interatomic Potential (MLIP) era. By rewriting core atomistic simulation primitives in PyTorch, TorchSim can achieve orders of magnitude acc…
View article: A framework to evaluate machine learning crystal stability predictions
A framework to evaluate machine learning crystal stability predictions Open
The rapid adoption of machine learning in various scientific domains calls for the development of best practices and community agreed-upon benchmarking tasks and metrics. We present Matbench Discovery as an example evaluation framework for…
View article: Atomate2: Modular workflows for materials science
Atomate2: Modular workflows for materials science Open
High-throughput density functional theory (DFT) calculations have become a vital element of computational materials science, enabling materials screening, property database generation, and training of “universal” machine learning models. W…
View article: Atomate2: modular workflows for materials science
Atomate2: modular workflows for materials science Open
We present atomate2, a composable and interoperable workflow engine that extends its predecessor by leveraging the jobflow library and supporting a wide range of calculators (DFT and MLIPs) for dynamic, high-throughput workflow orchestrati…
View article: Correction: Atomate2: modular workflows for materials science
Correction: Atomate2: modular workflows for materials science Open
Correction for “Atomate2: modular workflows for materials science” by Alex M. Ganose et al. , Digital Discovery , 2025, 4 , 1944–1973, https://doi.org/10.1039/D5DD00019J.
View article: Identifying crystal structures beyond known prototypes from x-ray powder diffraction spectra
Identifying crystal structures beyond known prototypes from x-ray powder diffraction spectra Open
The large amount of powder diffraction data for which the corresponding crystal structures have not yet been identified suggests the existence of numerous undiscovered, physically relevant crystal structure prototypes. In this paper, we pr…
View article: Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials
Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials Open
Materials with high-dielectric constant easily polarize under external electric fields, allowing them to perform essential functions in many modern electronic devices. Their practical utility is determined by two conflicting properties: hi…
View article: A foundation model for atomistic materials chemistry
A foundation model for atomistic materials chemistry Open
Atomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much of our understanding of chemistry and materials science. O…
View article: Identifying Crystal Structures Beyond Known Prototypes from X-ray Powder Diffraction Spectra
Identifying Crystal Structures Beyond Known Prototypes from X-ray Powder Diffraction Spectra Open
The large amount of powder diffraction data for which the corresponding crystal structures have not yet been identified suggests the existence of numerous undiscovered, physically relevant crystal structure prototypes. In this paper, we pr…
View article: Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions
Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions Open
The rapid adoption of machine learning (ML) in domain sciences necessitates best practices and standardized benchmarking for performance evaluation. We present Matbench Discovery, an evaluation framework for ML energy models, applied as pr…
View article: DeePMD-kit v2: A software package for deep potential models
DeePMD-kit v2: A software package for deep potential models Open
DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in …
View article: Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra
Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra Open
Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various r…
View article: DeePMD-kit v2: A software package for Deep Potential models
DeePMD-kit v2: A software package for Deep Potential models Open
DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as Deep Potential (DP) models. This package, which was released in 2017, has been widely us…
View article: Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra
Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra Open
Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various r…
View article: Rapid discovery of stable materials by coordinate-free coarse graining
Rapid discovery of stable materials by coordinate-free coarse graining Open
A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allo…
View article: Rapid discovery of novel materials by coordinate-free coarse graining
Rapid discovery of novel materials by coordinate-free coarse graining Open
Prospective density function theory (DFT) calculations carried out on novel material structures predicted to be stable by the Wren model. In total 5,675 materials were selected for validation. Of these converged results were obtained for 4…
View article: Rapid discovery of stable materials by coordinate-free coarse graining
Rapid discovery of stable materials by coordinate-free coarse graining Open
Prospective density function theory (DFT) calculations carried out on novel material structures predicted to be stable by the Wren model. In total 5,675 materials were selected for validation. Of these converged results were obtained for 4…
View article: Rapid discovery of stable materials by coordinate-free coarse graining
Rapid discovery of stable materials by coordinate-free coarse graining Open
Prospective density function theory (DFT) calculations carried out on novel material structures predicted to be stable by the Wren model. In total 5,675 materials were selected for validation. Of these converged results were obtained for 4…
View article: Materials Informatics Reveals Unexplored Structure Space in Cuprate Superconductors
Materials Informatics Reveals Unexplored Structure Space in Cuprate Superconductors Open
High‐temperature superconducting cuprates have the potential to be transformative in a wide range of energy applications. In this work, the corpus of historical data about cuprates is analyzed using materials informatics, re‐examining how …
View article: Rapid Discovery of Stable Materials by Coordinate-free Coarse Graining
Rapid Discovery of Stable Materials by Coordinate-free Coarse Graining Open
A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allo…
View article: Predicting the Outcomes of Material Syntheses with Deep Learning
Predicting the Outcomes of Material Syntheses with Deep Learning Open
A common bottleneck for materials discovery is synthesis. While recent\nmethodological advances have resulted in major improvements in the ability to\npredicatively design novel materials, researchers often still rely on\ntrial-and-error a…
View article: Data-driven approximations to the bridge function yield improved closures for the Ornstein–Zernike equation
Data-driven approximations to the bridge function yield improved closures for the Ornstein–Zernike equation Open
A central challenge for soft matter is determining interaction potentials that give rise to observed condensed phase structures. Here we tackle this problem by combining the power of Deep Learning with the physics of the Ornstein–Zernike e…
View article: ROOST - Representation Learning from Stoichiometry
ROOST - Representation Learning from Stoichiometry Open
A python implementation of the Roost framework reference model. The Roost approach imagines that materials can be represented as dense stoichiometry graphs and then uses a message passing framework to learn mappings between the stoichiomet…
View article: Coarse-graining and designing liquids with the Ornstein-Zernike equation and machine learnt closures
Coarse-graining and designing liquids with the Ornstein-Zernike equation and machine learnt closures Open
A key challenge for soft materials design and coarse-graining simulations is determining interaction potentials between components that would create the desired condensed phase structure. In theory, the Ornstein-Zernike framework provides …
View article: Machine learnt approximations to the bridge function yield improved\n closures for the Ornstein-Zernike equation
Machine learnt approximations to the bridge function yield improved\n closures for the Ornstein-Zernike equation Open
A key challenge for soft materials design and coarse-graining simulations is\ndetermining interaction potentials between components that give rise to desired\ncondensed-phase structures. In theory, the Ornstein-Zernike equation provides\na…
View article: Machine learnt approximations to the bridge function yield improved closures for the Ornstein-Zernike equation
Machine learnt approximations to the bridge function yield improved closures for the Ornstein-Zernike equation Open
A key challenge for soft materials design and coarse-graining simulations is determining interaction potentials between components that give rise to desired condensed-phase structures. In theory, the Ornstein-Zernike equation provides an e…
View article: Revisiting Tc-Structure Trends in Cuprate Superconductors using Materials Informatics
Revisiting Tc-Structure Trends in Cuprate Superconductors using Materials Informatics Open
High-temperature superconducting cuprates have the potential to be transformative in a wide range of energy applications. However, increasing the critical temperature, particularly of single-layer cuprates, remains an important goal. In th…