Simon Batzner
YOU?
Author Swipe
View article: The design space of E(3)-equivariant atom-centred interatomic potentials
The design space of E(3)-equivariant atom-centred interatomic potentials Open
Molecular dynamics simulation is an important tool in computational materials science and chemistry, and in the past decade it has been revolutionized by machine learning. This rapid progress in machine learning interatomic potentials has …
View article: Efficient Exploratory Synthesis of Quaternary Cesium Chlorides Guided by In Silico Predictions
Efficient Exploratory Synthesis of Quaternary Cesium Chlorides Guided by In Silico Predictions Open
Exploratory synthesis of solids is essential for the advancement of materials science but is also highly time- and resource-intensive. Here, we demonstrate an efficient strategy to explore solid-state synthesis of quaternary cesium chlorid…
View article: Generative Hierarchical Materials Search
Generative Hierarchical Materials Search Open
Generative models trained at scale can now produce text, video, and more recently, scientific data such as crystal structures. In applications of generative approaches to materials science, and in particular to crystal structures, the guid…
View article: Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set
Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set Open
This work examines challenges associated with the accuracy of machine-learned force fields (MLFFs) for bulk solid and liquid phases of d -block elements. In exhaustive detail, we contrast the performance of force, energy, and stress predic…
View article: Transferability and Accuracy of Ionic Liquid Simulations with Equivariant Machine Learning Interatomic Potentials
Transferability and Accuracy of Ionic Liquid Simulations with Equivariant Machine Learning Interatomic Potentials Open
Ionic liquids (ILs) are an exciting class of electrolytes finding applications in many areas from energy storage to solvents, where they have been touted as ``designer solvents'' as they can be mixed to precisely tailor the physiochemical …
View article: Accurate Surface and Finite-Temperature Bulk Properties of Lithium Metal at Large Scales Using Machine Learning Interaction Potentials
Accurate Surface and Finite-Temperature Bulk Properties of Lithium Metal at Large Scales Using Machine Learning Interaction Potentials Open
The properties of lithium metal are key parameters in the design of lithium-ion and lithium-metal batteries. They are difficult to probe experimentally due to the high reactivity and low melting point of lithium as well as the microscopic …
View article: Scaling the Leading Accuracy of Deep Equivariant Models to Biomolecular Simulations of Realistic Size
Scaling the Leading Accuracy of Deep Equivariant Models to Biomolecular Simulations of Realistic Size Open
This work brings the leading accuracy, sample efficiency, and robustness of deep equivariant neural networks to the extreme computational scale. This is achieved through a combination of innovative model architecture, massive parallelizati…
View article: Predicting emergence of crystals from amorphous matter with deep learning
Predicting emergence of crystals from amorphous matter with deep learning Open
Crystallization of the amorphous phases into metastable crystals plays a fundamental role in the formation of new matter, from geological to biological processes in nature to synthesis and development of new materials in the laboratory. Pr…
View article: Fast uncertainty estimates in deep learning interatomic potentials
Fast uncertainty estimates in deep learning interatomic potentials Open
Deep learning has emerged as a promising paradigm to give access to highly accurate predictions of molecular and material properties. A common short-coming shared by current approaches, however, is that neural networks only give point esti…
View article: Accurate Surface and Finite Temperature Bulk Properties of Lithium Metal at Large Scales using Machine Learning Interaction Potentials
Accurate Surface and Finite Temperature Bulk Properties of Lithium Metal at Large Scales using Machine Learning Interaction Potentials Open
The properties of lithium metal are key parameters in the design of lithium ion and lithium metal batteries. They are difficult to probe experimentally due to the high reactivity and low melting point of lithium as well as the microscopic …
View article: Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size
Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size Open
This work brings the leading accuracy, sample efficiency, and robustness of deep equivariant neural networks to the extreme computational scale. This is achieved through a combination of innovative model architecture, massive parallelizati…
View article: Complexity of Many-Body Interactions in Transition Metals via Machine-Learned Force Fields from the TM23 Data Set
Complexity of Many-Body Interactions in Transition Metals via Machine-Learned Force Fields from the TM23 Data Set Open
This work examines challenges associated with the accuracy of machine-learned force fields (MLFFs) for bulk solid and liquid phases of d-block elements. In exhaustive detail, we contrast the performance of force, energy, and stress predict…
View article: Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
Fast Uncertainty Estimates in Deep Learning Interatomic Potentials Open
Deep learning has emerged as a promising paradigm to give access to highly accurate predictions of molecular and materials properties. A common short-coming shared by current approaches, however, is that neural networks only give point est…
View article: Replication Data for: Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events
Replication Data for: Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events Open
The data underlying this published work have been made publicly available in this repository as part of the IMASC Data Management Plan. This work was supported as part of the Integrated Mesoscale Architectures for Sustainable Catalysis (IM…
View article: The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials Open
The rapid progress of machine learning interatomic potentials over the past couple of years produced a number of new architectures. Particularly notable among these are the Atomic Cluster Expansion (ACE), which unified many of the earlier …
View article: Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics Open
A simultaneously accurate and computationally efficient parametrization of the energy and atomic forces of molecules and materials is a long-standing goal in the natural sciences. In pursuit of this goal, neural message passing has lead to…
View article: Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events
Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events Open
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is …
View article: e3nn/e3nn: 2021-11-18
e3nn/e3nn: 2021-11-18 Open
[0.4.3] - 2021-11-18 Fixed ReducedTensorProduct: replace QR decomposition by orthonormalize the projector X.T @ X. This keeps ReducedTensorProduct deterministic because the projectors and orthonormalize are both deterministic. The output o…
View article: e3nn/e3nn: 2021-06-21
e3nn/e3nn: 2021-06-21 Open
[0.3.3] - 2021-06-21 Changed FullyConnectedNet is now a torch.nn.Sequential Fixed BatchNorm was not equivariant for pseudo-scalars Added biases argument to o3.Linear nn.models.v2106: MessagePassing takes a sequence of irreps nn.models.v210…
View article: SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials Open
This work presents Neural Equivariant Interatomic Potentials (NequIP), a SE(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While most contemporary …
View article: Multitask machine learning of collective variables for enhanced sampling of rare events
Multitask machine learning of collective variables for enhanced sampling of rare events Open
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is …
View article: On-the-Fly Bayesian Active Learning of Interpretable Force-Fields for Atomistic Rare Events
On-the-Fly Bayesian Active Learning of Interpretable Force-Fields for Atomistic Rare Events Open
Machine learning based interatomic potentials currently require manual construction of training sets consisting of thousands of first principles calculations and are often restricted to single-component and nonreactive systems. This severe…
View article: On-the-Fly Active Learning of Interpretable Bayesian Force Fields for\n Atomistic Rare Events
On-the-Fly Active Learning of Interpretable Bayesian Force Fields for\n Atomistic Rare Events Open
Machine learned force fields typically require manual construction of\ntraining sets consisting of thousands of first principles calculations, which\ncan result in low training efficiency and unpredictable errors when applied to\nstructure…
View article: Learning symmetry-preserving interatomic force fields for atomistic simulations
Learning symmetry-preserving interatomic force fields for atomistic simulations Open
Thesis: S.M., Massachusetts Institute of Technology, Computation for Design and Optimization Program, 2019