Genetic algorithms for computational materials discovery accelerated by machine learning
Problem
Finding stable nanoparticle alloy compositions via computational search is slow because each candidate requires expensive energy calculations.
Why it matters
Nanoalloy catalysts and other advanced materials could be discovered far faster and cheaper if the search process is accelerated.
What the AI did
A machine learning model was trained on-the-fly as a cheap energy predictor and used as a surrogate inside a genetic algorithm to accelerate the search for stable nanoparticle alloys.
Results
50-fold reduction in the number of required energy calculations compared to a traditional brute-force genetic algorithm.
Impact
The abstract reports a concrete 50-fold speedup in a demonstrated nanoparticle alloy search, published in a peer-reviewed Nature Partner Journal with 240 citations.
Record
| Venue | npj Computational Materials |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Paul C. Jennings, Steen Lysgaard, Jens S. Hummelshøj, Tejs Vegge, Thomas Bligaard |
| Citations | 265 (OpenAlex, at import time) |
| References | 51 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41524-019-0181-4 |
| Open access | gold |
| Keywords | machine learning, genetic algorithms, nanoparticle alloys, materials discovery, surrogate model |
Importance rating
real but narrower advance
Accelerates search for stable nanoalloy catalysts; abstract quantifies a 50-fold reduction in required energy calculations, but scope is a single materials-discovery use case, a real but narrower advance.
More in Engineering & Materials
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Scaling deep learning for materials discovery | 2023 | 1,471 |
8
|
| 2 | Application of Machine Learning in Material Synthesis and Property Prediction | 2023 | 165 |
7
|
| 3 | Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries | 2023 | 115 |
7
|
| 4 | Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review | 2025 | 44 |
7
|
| 5 | Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology | 2023 | 42 |
7
|