Related Experiment Video
Updated: Oct 7, 2025
08:04
Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids
Published on: May 27, 2020
8.6K
Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
Jigyasa Nigam1, Michael J Willatt1, Michele Ceriotti1
1Laboratory of Computational Science and Modeling, Institute of Materials, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.
The Journal of Chemical Physics
|January 9, 2022
Summary
Machine learning models for atomic structures are enhanced by new N-center descriptors. These descriptors capture multi-center interactions, enabling accurate prediction of quantum mechanical properties like the Hamiltonian matrix.
Area of Science:
- Computational chemistry
- Materials science
- Machine learning
Background:
- Symmetry is crucial for representing atomic configurations in machine learning.
- Current models often focus on atom-centered environments, limiting their scope.
- Many quantum mechanical properties, such as the Hamiltonian matrix, involve interactions between multiple atoms.
Purpose of the Study:
- To develop generalized N-center structural descriptors.
- To extend atom-centered density correlation features to multi-center scenarios.
- To enable machine learning models to predict properties not reducible to atomic contributions.
Main Methods:
- Generalizing atom-centered density correlation features to N-center descriptors.
- Constructing N-center features that are equivariant to translations, rotations, and atom permutations.
- Applying these features to learn matrix elements of the single-particle Hamiltonian.
Main Results:
- Demonstrated a family of N-center descriptors that capture multi-center atomic interactions.
- Showcased the efficient learning of Hamiltonian matrix elements using these descriptors.
- Developed fully equivariant N-center features suitable for symmetry-adapted machine learning.
Conclusions:
- N-center descriptors significantly expand the capability of machine learning in materials science.
- These descriptors facilitate the prediction of complex quantum mechanical properties.
- The developed features enable the construction of advanced, symmetry-adapted machine learning models for molecular and material properties.
Related Concept Videos
02:36Molecular Geometry and Dipole Moments
15.4K
The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:
15.4K
02:18Fischer Projections
14.3K
Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines.
14.3K
01:18Molecular Shapes
59.2K
Molecules have characteristic shapes that are crucial for their function. The arrangement of various electron groups around the central atom dictates their molecular geometry. Electron pairs in the valence shell of a central atom will adopt an arrangement that minimizes repulsions between the electron pairs by maximizing the distance between them. The valence electrons form either bonding pairs, located primarily between bonded atoms, or lone pairs.
Two regions of electron density in a diatomic...
Two regions of electron density in a diatomic...
59.2K
02:06Newman Projections
18.6K
Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
18.6K
03:51Molecular Orbital Theory II
20.3K
Molecular Orbital Energy Diagrams
20.3K
02:00Molecular Models
41.4K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
41.4K