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

Multicompartment Models: Overview01:14

Multicompartment Models: Overview

76
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
76
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

93
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
93
Energy Diagrams, Transition States, and Intermediates02:13

Energy Diagrams, Transition States, and Intermediates

16.0K
Free-energy diagrams, or reaction coordinate diagrams, are graphs showing the energy changes that occur during a chemical reaction. The reaction coordinate represented on the horizontal axis shows how far the reaction has progressed structurally. Positions along the x-axis close to the reactants have structures resembling the reactants, while positions close to the products resemble the products.  Peaks on the energy diagram represent stable structures with measurable lifetimes, while...
16.0K
Inductive Effects on Chemical Shift: Overview01:27

Inductive Effects on Chemical Shift: Overview

1.0K
The protons in unsubstituted alkanes are strongly shielded with chemical shifts below 1.8 ppm. Methine, methylene, and methyl protons appear at approximately 1.7, 1.2 and 0.7 ppm, while the proton signal from methane appears at 0.23 ppm. An electronegative substituent, such as chlorine, withdraws the electron density from the protons, increasing their chemical shift. Progressive substitution of the hydrogens in methane by chlorine shifts the proton signals increasingly downfield, to 3.05 ppm in...
1.0K
Energy Diagrams - II01:10

Energy Diagrams - II

4.6K
Energy diagrams are important to understand the dynamics of a system. The topology of an energy diagram helps illustrate the equilibrium points of the system.
The point in the energy diagram at which the system’s potential energy is the lowest is known as the local minima. The system tends to stay in this position indefinitely unless acted upon by a net force. The slope of the potential energy diagram at the local minima is zero, indicating that zero net force is acting on the system. The...
4.6K
Woodward–Hoffmann Selection Rules and Microscopic Reversibility01:34

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

3.0K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
3.0K

You might also read

Related Articles

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

Sort by
Same author

LFaB: Low Fidelity as Bias for Active Learning in the Chemical Configuration Space.

Journal of chemical theory and computation·2026
Same author

Benchmarking data efficiency in Δ-ML and multifidelity models for quantum chemistry.

The Journal of chemical physics·2025
Same author

Predicting Molecular Energies of Small Organic Molecules With Multi-Fidelity Methods.

Journal of computational chemistry·2025
Same author

QeMFi: A Multifidelity Dataset of Quantum Chemical Properties of Diverse Molecules.

Scientific data·2025
Same author

Multifidelity Machine Learning for Molecular Excitation Energies.

Journal of chemical theory and computation·2023

Related Experiment Video

Updated: May 22, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.4K

Investigating Data Hierarchies in Multifidelity Machine Learning for Excitation Energies.

Vivin Vinod1, Peter Zaspel1

  • 1School of Mathematics and Natural Sciences, University of Wuppertal, Wuppertal 42119 Germany.

Journal of Chemical Theory and Computation
|March 13, 2025
PubMed
Summary

Multifidelity machine learning (MFML) improves quantum chemistry (QC) predictions by optimizing data scaling. This study introduces compute time-informed factors, achieving high accuracy with minimal training data costs.

More Related Videos

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids
08:04

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Published on: May 27, 2020

8.3K
Using Three-color Single-molecule FRET to Study the Correlation of Protein Interactions
11:22

Using Three-color Single-molecule FRET to Study the Correlation of Protein Interactions

Published on: January 30, 2018

10.0K

Related Experiment Videos

Last Updated: May 22, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.4K
Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids
08:04

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Published on: May 27, 2020

8.3K
Using Three-color Single-molecule FRET to Study the Correlation of Protein Interactions
11:22

Using Three-color Single-molecule FRET to Study the Correlation of Protein Interactions

Published on: January 30, 2018

10.0K

Area of Science:

  • Quantum chemistry
  • Computational chemistry
  • Machine learning applications

Background:

  • Machine learning (ML) advances enhance the accessibility of high-accuracy quantum chemistry (QC) calculations.
  • Multifidelity machine learning (MFML) methods leverage training data from varying accuracy levels.
  • Current MFML methods often use a fixed scaling factor (γ) for inter-fidelity data, reflecting cost and sparsity assumptions.

Purpose of the Study:

  • Investigate the effect of modifying the scaling factor (γ) on MFML model efficiency and accuracy for predicting vertical excitation energies.
  • Introduce QC compute time-informed scaling factors (θ) that dynamically adjust based on computational costs at different fidelities.
  • Propose a novel error metric, 'error contours of MFML,' for a detailed analysis of error contributions from each fidelity level.

Main Methods:

  • Utilized the QeMFi benchmark dataset for evaluating vertical excitation energy predictions.
  • Modified the traditional fixed scaling factor (γ) and introduced new QC compute time-informed scaling factors (θ).
  • Developed and applied 'error contours of MFML' to visualize fidelity-specific error contributions.
  • Introduced the Γ-curve to compare model error against the computational cost of training data generation.

Main Results:

  • Achieved high model accuracy using only 2 training samples at the target fidelity when supplemented by a larger number of lower-fidelity samples.
  • Demonstrated that MFML models can attain high accuracy while significantly reducing training data costs.
  • The proposed QC compute time-informed scaling factors (θ) offer improved model efficiency.
  • Error contours provide a comprehensive understanding of error sources across different data fidelities.

Conclusions:

  • Optimizing scaling factors in MFML is crucial for balancing model accuracy and computational cost.
  • MFML, particularly with compute time-informed scaling, offers a cost-effective approach to high-accuracy QC predictions.
  • The developed error metrics and visualization tools (error contours, Γ-curve) enhance the interpretability and efficiency of MFML.
  • This research paves the way for more efficient and accessible high-accuracy computational chemistry through advanced ML techniques.