Exploring catalytic reaction networks with machine learning
Chemical reaction networks form the heart of microkinetic models, which are one of the key
tools available for gaining detailed mechanistic insight into heterogeneous catalytic …
tools available for gaining detailed mechanistic insight into heterogeneous catalytic …
[HTML][HTML] Representations of materials for machine learning
J Damewood, J Karaguesian, JR Lunger… - Annual Review of …, 2023 - annualreviews.org
High-throughput data generation methods and machine learning (ML) algorithms have
given rise to a new era of computational materials science by learning the relations between …
given rise to a new era of computational materials science by learning the relations between …
Forces are not enough: Benchmark and critical evaluation for machine learning force fields with molecular simulations
Molecular dynamics (MD) simulation techniques are widely used for various natural science
applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab …
applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab …
Reducing SO (3) convolutions to SO (2) for efficient equivariant GNNs
S Passaro, CL Zitnick - International Conference on Machine …, 2023 - proceedings.mlr.press
Graph neural networks that model 3D data, such as point clouds or atoms, are typically
desired to be $ SO (3) $ equivariant, ie, equivariant to 3D rotations. Unfortunately …
desired to be $ SO (3) $ equivariant, ie, equivariant to 3D rotations. Unfortunately …
Equiformerv2: Improved equivariant transformer for scaling to higher-degree representations
Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying
Transformers to the domain of 3D atomistic systems. However, they are still limited to small …
Transformers to the domain of 3D atomistic systems. However, they are still limited to small …
[HTML][HTML] Exploiting redundancy in large materials datasets for efficient machine learning with less data
Extensive efforts to gather materials data have largely overlooked potential data
redundancy. In this study, we present evidence of a significant degree of redundancy across …
redundancy. In this study, we present evidence of a significant degree of redundancy across …
Crystal structure prediction by joint equivariant diffusion
Abstract Crystal Structure Prediction (CSP) is crucial in various scientific disciplines. While
CSP can be addressed by employing currently-prevailing generative models (eg diffusion …
CSP can be addressed by employing currently-prevailing generative models (eg diffusion …
Big data in a nano world: a review on computational, data-driven design of nanomaterials structures, properties, and synthesis
The recent rise of computational, data-driven research has significant potential to accelerate
materials discovery. Automated workflows and materials databases are being rapidly …
materials discovery. Automated workflows and materials databases are being rapidly …
[HTML][HTML] A reactive neural network framework for water-loaded acidic zeolites
A Erlebach, M Šípka, I Saha, P Nachtigall… - Nature …, 2024 - nature.com
Under operating conditions, the dynamics of water and ions confined within protonic
aluminosilicate zeolite micropores are responsible for many of their properties, including …
aluminosilicate zeolite micropores are responsible for many of their properties, including …
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
Recent advances in computational modelling of atomic systems, spanning molecules,
proteins, and materials, represent them as geometric graphs with atoms embedded as …
proteins, and materials, represent them as geometric graphs with atoms embedded as …