Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Applications of Integration to Probability Density Functions01:27

Applications of Integration to Probability Density Functions

Continuous probability distributions are used to model random variables that can take on any real value within a specified range. These variables do not take on isolated or countable values but rather exist on a continuum. For example, the height of an individual can be measured with increasing precision—such as 163.5 or 165.25 centimeters—demonstrating that height is a continuous random variable.The behavior of such variables is described using a probability density function (PDF), which...
Real-Life Applications of Multiple Integrals01:18

Real-Life Applications of Multiple Integrals

Multiple integrals provide a powerful mathematical framework for calculating physical quantities distributed throughout two- and three-dimensional regions. One important application is the determination of volume in objects with curved geometries, such as storage tanks, pipes, and reservoirs. Cylindrical coordinates are especially useful for systems with rotational symmetry because they simplify the description of circular and paraboloid-shaped regions.Consider a paraboloid-shaped water tank...
Applications of Integration to Find Centers of Mass01:30

Applications of Integration to Find Centers of Mass

Rotational equilibrium provides a natural framework for defining the center of mass of a system. For a plank balanced on a pivot with two unequal masses, equilibrium is achieved when the net torque about the pivot is zero. Torque is defined as the product of a force and its perpendicular distance from the pivot. When the torques due to all forces cancel, the pivot coincides with the center of mass of the system.For a system composed of several discrete point masses, the center of mass lies at...
Density00:56

Density

Density is an important characteristic of substances, crucial in determining whether an object sinks or floats in a fluid. Its SI unit is kg/m3, and its cgs unit is g/cm3. The density of an object helps in identifying its composition, and also reveals information about the phase of the matter and its substructure. The densities of liquids and solids are roughly comparable, consistent with the fact that their atoms are in close contact. However, gases have much lower densities than liquids and...
Line, Surface, and Volume Integrals01:15

Line, Surface, and Volume Integrals

A line integral for a vector field is defined as the integral of the dot product of a vector function with an infinitesimal displacement vector along a prescribed path. If the prescribed path is closed, the integrals reduce to a closed-line integral. The closed-contour integral of the vector field is referred to in terms of the circulation of the vector field around the closed path. A vector with zero circulation around every closed path is called a conservative field, while one with non-zero...
Applications of Line Integrals01:26

Applications of Line Integrals

When a force acts along a curved path, work is determined by summing the contributions from each infinitesimal segment of motion. This summation is expressed as a line integral, which accounts for both the changing magnitude and direction of the force along the path. A similar mathematical structure describes electromagnetic induction, in which a changing magnetic field induces an electric field around a conducting loop.For a particle moving along a curve, the work done by a force is written...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Atmospheric Oxidation Kinetics of Monochloramine by Hydroxyl Radical, Carbonyl Oxide, and Sulfur Trioxide Catalyzed by Water.

The journal of physical chemistry. A·2026
Same author

Nonadiabatic dynamics starting from reactant and transition state in luminol chemiluminescence.

The Journal of chemical physics·2026
Same author

PpF: a density functional fine-tuned for noncovalent interactions of protein and peptide residues.

Chemical science·2026
Same author

Dynamics of Electronically Inelastic and Reactive Collisions of O(<sup>1</sup>D) with N<sub>2</sub> Based on Machine-Learned Coupled Potential Energy Surfaces.

Journal of chemical theory and computation·2026
Same author

New Framework for Multi-Electronic-State Dynamics and Its Validation for Photoisomerization of 1,3-Cyclohexadiene.

Journal of chemical theory and computation·2026
Same author

Room-Temperature Gas-Phase CO<sub>2</sub>-to-C<sub>3</sub> Coupling by a 4f-Aromatic Cluster.

Angewandte Chemie (International ed. in English)·2026
Same journal

PSFF-PTM: A Coarse-Grained Force-Field Parameter Patch for Modeling Post-Translational Modification Effects on Biomolecular Condensates.

Journal of chemical theory and computation·2026
Same journal

Low-Scaling Many-Body Green's Function Calculations for Molecular Systems via Interacting-Bath Dynamical Embedding Theory.

Journal of chemical theory and computation·2026
Same journal

Machine-Learned Leftmost Hessian Eigenvectors for Robust Transition State Finding.

Journal of chemical theory and computation·2026
Same journal

A Cautionary Tale: Failure of the Valence CASSCF to Describe the Hallmark of Hydrogen Bonding.

Journal of chemical theory and computation·2026
Same journal

GPU Accelerated Minimal Auxiliary Basis Approach TDDFT for Large Organic Molecules.

Journal of chemical theory and computation·2026
Same journal

Unveiling Electric Field-Driven Stereocontrol in Hurd-Claisen Rearrangements.

Journal of chemical theory and computation·2026
See all related articles
  1. Home
  3. Reinventing Density Functional Theory With Machine Learning On Integral Features.
  1. Home
  3. Reinventing Density Functional Theory With Machine Learning On Integral Features.

Related Experiment Videos

Reinventing Density Functional Theory with Machine Learning on Integral Features.

Dayou Zhang1, Yinan Shu1, Donald G Truhlar1

  • 1Department of Chemistry, Chemical Theory Center, and Minnesota Supercomputing Institute, University of Minnesota; Minneapolis, Minnesota 55455-0431, United States.

Journal of Chemical Theory and Computation
|June 25, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

A new machine learning strategy uses "integral features" to create highly accurate density functionals for electronic structure modeling. This approach enhances accuracy without increasing computational cost, outperforming existing methods.

Related Experiment Videos

Area of Science:

  • Computational Chemistry
  • Materials Science
  • Quantum Mechanics

Background:

  • Kohn-Sham density functional theory (KS-DFT) is crucial for electronic structure modeling.
  • Accuracy of KS-DFT relies on density functional approximations.
  • Existing methods face limitations in balancing accuracy and computational cost.

Purpose of the Study:

  • Introduce a novel strategy for developing accurate density functionals.
  • Leverage machine learning with integrated local descriptors.
  • Improve computational efficiency while enhancing functional dependence.

Main Methods:

  • Developed a multilayer perceptron learning nonlinear functional of "integral features".
  • Formulated an "integral-features" approach applying the model once per calculation.
  • Trained ML25@MN15 functional on 185 databases covering diverse chemical properties.

    • Main Results:

    • ML25@MN15 achieved a mean unsigned error of 1.05 kcal/mol on 7232 energetic data points.
    • Demonstrated superior performance over leading modern functionals across various categories.
    • Maintained computational cost comparable to standard functionals like MN15.

    Conclusions:

    • Integral features offer a computationally efficient path to high-accuracy density functionals.
    • Machine learning can determine complex density functional dependencies.
    • This strategy advances electronic structure modeling, especially for systems with transition metals.