A framework to evaluate machine learning crystal stability predictions
Lawrence Berkeley National Laboratory · University of Cambridge · +2 more institutions
Abstract
Abstract The rapid adoption of machine learning in various scientific domains calls for the development of best practices and community agreed-upon benchmarking tasks and metrics. We present Matbench Discovery as an example evaluation framework for machine learning energy models, here applied as pre-filters to first-principles computed data in a high-throughput search for stable inorganic crystals. We address the disconnect between (1) thermodynamic stability and formation energy and (2) retrospective and prospective benchmarking for materials discovery. Alongside this paper, we publish a Python package to aid with future model submissions and a growing online leaderboard with adaptive user-defined weighting…
Citation impact
- FWCI
- 38.60
- Percentile
- 100%
- References
- 71
Authors
10- JRJanosh RiebesellCorresponding
Lawrence Berkeley National Laboratory, University of Cambridge
- RERhys E. A. Goodall
University of Cambridge
- PBPhilipp Benner
Federal Institute For Materials Research and Testing
- YCYuan Chiang
Lawrence Berkeley National Laboratory, University of California, Berkeley
- BDBowen Deng
Lawrence Berkeley National Laboratory, University of California, Berkeley
Topics & keywords
- Stability (learning theory)
- Computer science
- Machine learning
Funding
- UDU.S. Department of EnergyAwards: KC23MP, -AC02-05-CH11231, DE-AC02, AC02-05-CH11231, DE-AC02-05-CH11231, DE-AC02-
- NENational Energy Research Scientific Computing Center
- SDStudienstiftung des Deutschen Volkes
- OOOffice of ScienceAwards: DE-AC02, DE-AC02-05-CH11231
- BEBasic Energy SciencesAwards: DE-AC02, AC02-05-CH11231, KC23MP, DE-AC02-05-CH11231