Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Propagation of Uncertainty from Systematic Error

Propagation of Uncertainty from Systematic Error

The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...

Uncertainty: Overview

Uncertainty: Overview

In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

The Uncertainty Principle

The Uncertainty Principle

Werner Heisenberg considered the limits of how accurately one can measure properties of an electron or other microscopic particles. He determined that there is a fundamental limit to how accurately one can measure both a particle’s position and its momentum simultaneously. The more accurate the measurement of the momentum of a particle is known, the less accurate the position at that time is known and vice versa. This is what is now called the Heisenberg uncertainty principle. He...

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

Molecular Models

Molecular Models

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.

You might also read

Related Articles

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

Sort by

Same author

More Converged, Less Accurate? Reassessing Standard Choices for Ab Initio Water Using Machine Learning Potentials.

The journal of physical chemistry. B·2026

Same author

How reactive is water at the nanoscale and how to control it?

Science advances·2026

Same author

When is nanoconfined water different from interfacial water?

Faraday discussions·2026

Same author

Nanoconfined superionic water is a molecular superionic.

Science advances·2026

Same author

Breaking the Air-Water Paradigm: Ion Behavior at Hydrophobic Solid-Water Interfaces.

Journal of the American Chemical Society·2026

Same author

A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data.

Journal of chemical information and modeling·2026

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

Multi-head committees enable direct uncertainty prediction for atomistic foundation models.

Hubert Beck¹, Pavol Simko¹, Lars L Schaaf^2,3

¹Charles University, Faculty of Mathematics and Physics, Ke Karlovu 3, 121 16 Prague 2, Czech Republic.

The Journal of Chemical Physics

|December 15, 2025

Summary

This summary is machine-generated.

This study introduces a committee neural network potential using MACE for efficient uncertainty predictions in materials modeling. This method accurately estimates model uncertainty and enables significant training data reduction for foundation models.

More Related Videos

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Published on: April 12, 2019

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

Related Experiment Videos

Last Updated: Jan 8, 2026

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Published on: April 12, 2019

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

Area of Science:

Materials Science
Computational Chemistry
Machine Learning

Background:

Machine learning potentials are crucial for atomistic materials modeling.
Efficient uncertainty prediction remains a challenge for active learning and error analysis.

Purpose of the Study:

To implement a committee neural network potential for message-passing architectures using MACE.
To evaluate the uncertainty estimation capabilities of this committee model.
To apply the method to foundation models for active learning and data set condensation.

Main Methods:

Utilized MACE and its multi-head mechanism to create a committee neural network.
Trained multiple output modules on the same atomic environment descriptors.
Applied the committee approach to the MACE-MP-0 foundation model, training only new output heads.

Main Results:

Demonstrated that the standard deviation of predictions serves as a reliable uncertainty estimate.
Showed strong correlation between predicted uncertainty and true errors in force predictions.
Successfully condensed the training set for a foundation model to 5% of its original size using active learning.

Conclusions:

The multi-head committee approach provides robust uncertainty estimation for machine learning potentials.
This method allows for significant reduction in training data size for foundation models without compromising accuracy.
Enables more efficient and reliable active learning workflows in materials modeling.