Related Experiment Video
Updated: Jan 17, 2026
15:04
Picometer-Precision Atomic Position Tracking through Electron Microscopy
Published on: July 3, 2021
8.3K
Uncertainty in the era of machine learning for atomistic modeling
Federico Grasselli1,2, Sanggyu Chong3, Venkat Kapil4,5,6
1Dipartimento di Scienze Fisiche, Informatiche e Matematiche, Università degli Studi di Modena e Reggio Emilia 41125 Modena Italy federico.grasselli@unimore.it.
Digital Discovery
|September 15, 2025
Summary
Machine learning surrogate models enhance atomistic modeling but introduce uncertainties. This perspective reviews uncertainty quantification methods and their impact on model reliability, accuracy, and robustness in scientific research.
Area of Science:
- Computational materials science
- Data-driven modeling
Background:
- Machine learning surrogate models are increasingly used in atomistic modeling to enhance efficiency and explore complex systems.
- The data-driven nature of these models necessitates robust methods for quantifying and managing prediction uncertainties.
Purpose of the Study:
- To provide an overview of state-of-the-art uncertainty estimation techniques applicable to atomistic modeling.
- To examine the critical relationships between model accuracy, uncertainty, and data characteristics.
Main Methods:
- Review of Bayesian frameworks and ensembling techniques for uncertainty quantification.
- Analysis of the interplay between model performance, training data, and model robustness.
Main Results:
- Uncertainty quantification is crucial for reliable machine learning predictions in atomistic simulations.
- Dataset composition and acquisition strategies significantly influence model accuracy and transferability.
Conclusions:
- Effective management of uncertainties is essential for the trustworthy application of machine learning in atomistic modeling.
- Further research is needed to address ongoing debates in model transferability and robustness.
Related Concept Videos
04:08The Uncertainty Principle
31.3K
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...
31.3K
01:10Propagation of Uncertainty from Systematic Error
1.4K
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...
1.4K
00:59Uncertainty: Overview
1.6K
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.
1.6K
02:45The Quantum-Mechanical Model of an Atom
56.6K
Shortly after de Broglie published his ideas that the electron in a hydrogen atom could be better thought of as being a circular standing wave instead of a particle moving in quantized circular orbits, Erwin Schrödinger extended de Broglie’s work by deriving what is now known as the Schrödinger equation. When Schrödinger applied his equation to hydrogen-like atoms, he was able to reproduce Bohr’s expression for the energy and, thus, the Rydberg formula governing hydrogen spectra.
56.6K
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
292
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...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
292
00:59Propagation of Uncertainty from Random Error
1.8K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
1.8K