Spherical Channels for Modeling Atomic Interactions

  title={Spherical Channels for Modeling Atomic Interactions},
  author={C. Lawrence Zitnick and Abhishek Das and Adeesh Kolluru and Janice Lan and Muhammed Shuaibi and Anuroop Sriram and Zachary W. Ulissi and Brandon C. Wood},
Modeling the energy and forces of atomic systems is a fundamental problem in computational chemistry with the potential to help address many of the world’s most pressing problems, including those related to energy scarcity and climate change. These calculations are traditionally performed using Density Functional Theory, which is computationally very expensive. Machine learning has the potential to dramatically improve the efficiency of these calculations from days or hours to seconds. We… 

Figures and Tables from this paper



Perspective: Machine learning potentials for atomistic simulations.

  • J. Behler
  • Materials Science
    The Journal of chemical physics
  • 2016
Recent advances in machine learning (ML) now offer an alternative approach for the representation of potential-energy surfaces by fitting large data sets from electronic structure calculations, which are reviewed along with a discussion of their current applicability and limitations.

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

This work proposes to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid, and obtains a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles.

Towards exact molecular dynamics simulations with machine-learned force fields

A flexible machine-learning force-field with high-level accuracy for molecular dynamics simulations is developed, for flexible molecules with up to a few dozen atoms and insights into the dynamical behavior of these molecules are provided.

Directional Message Passing for Molecular Graphs

This work proposes a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them, and uses spherical Bessel functions to construct a theoretically well-founded, orthogonal radial basis that achieves better performance than the currently prevalent Gaussian radial basis functions while using more than 4x fewer parameters.

The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials

A mathematical framework is constructed that generalised the Atomic Cluster Expansion so that it can be recast as one layer of a multi-layer architecture and presents BOTNet (Body-Ordered-Tensor-Network), a much-simplified version of NequIP, which has an interpretable architecture and maintains accuracy on benchmark datasets.

SchNet - A deep learning architecture for molecules and materials.

The deep learning architecture SchNet is presented that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers and employs SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules.

Machine learning of accurate energy-conserving molecular force fields

The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.

Quantum-chemical insights from deep tensor neural networks

An efficient deep learning approach is developed that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems, and unifies concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate chemical space predictions.

Neural Message Passing for Quantum Chemistry

Using MPNNs, state of the art results on an important molecular property prediction benchmark are demonstrated and it is believed future work should focus on datasets with larger molecules or more accurate ground truth labels.

Equivariant message passing for the prediction of tensorial properties and molecular spectra

This work proposes the polarizable atom interaction neural network (PAINN) and improves on common molecule benchmarks over previous networks, while reducing model size and inference time and leverage the equivariant atomwise representations obtained by PAINN for the prediction of tensorial properties.