Related Experiment Video
Updated: May 8, 2026
12:11
Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
Published on: April 8, 2020
GMMLP: An Efficient Software for Searching the Global-Minimum of Clusters Accelerated by Using the Machine Learning
Yang-Yang Zhang1,2, Yu Cheng1,2, Shu-Wen Zhang1,2
1Fundamental Science Center of Rare Earths, Ganjiang Innovation Academy, Chinese Academy of Sciences, Ganzhou, Jiangxi, China.
Journal of Computational Chemistry
|May 7, 2026
Summary
This study introduces GMMLP, a machine learning-powered software for efficiently finding the global minimum structures of chemical clusters. It significantly speeds up the search for complex cluster configurations.
Area of Science:
- Computational Chemistry
- Materials Science
- Chemical Physics
Background:
- Finding the global-minimum (GM) structure of clusters is computationally challenging due to the vast number of local minima on the potential energy surface (PES).
- Existing methods struggle with the exponential increase in complexity as cluster size grows.
Purpose of the Study:
- To develop an efficient software package, GMMLP (Global-Minimum Search of Clusters Accelerated by Machine Learning Potentials), for identifying the GM structures of clusters.
- To leverage machine learning potentials for accelerating the global search of cluster structures.
Main Methods:
- GMMLP integrates the atom-in-molecules neural network potential (AIMNet2) with an improved genetic algorithm (GA).
- AIMNet2 was trained at the ωB97M-D3/def2-TZVPP level of theory, ensuring high accuracy.
- The optimized GA provides robust global search capabilities.
Main Results:
- Benchmark tests on nine types of clusters (n=1-10) demonstrated GMMLP's efficiency in exploring the PES.
- GMMLP searched 9869 isomers in approximately 10.8 hours, with average times per isomer ranging from 0.22s to 10.01s.
- Analysis of relative energies and optimized structures confirmed the reliability of the search process.
Conclusions:
- GMMLP offers a powerful and efficient tool for accurate GM structure identification in diverse cluster systems.
- This capability is crucial for advancing research in cluster properties and their applications.
- The software accelerates discovery in chemistry, materials science, and related fields.
Related Concept Videos
01:29Mechanistic 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...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
01:20Cluster Sampling Method
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...