AI Science Tracker

Bayesian optimization and graph learning identify two synthesized ultra-incompressible hard materials

University of California San Diego · 20 Apr 2021 · materials

Discovery

Bayesian optimization and graph learning identify two synthesized ultra-incompressible hard materials

A Bayesian optimization workflow using symmetry-constrained crystal relaxation and the MEGNet graph neural network screened 399,960 transition-metal boride and carbide compositions. The study identified MoWC₂ (P6₃/mmc) and ReWB (Pca2₁), then synthesized both by in-situ reactive spark-plasma sintering; the measured hardness was reported to agree with model and DFT predictions. The result is limited to these two synthesized compounds and the authors’ tested synthesis conditions.

Technology: BOWSR (Bayesian Optimization With Symmetry Relaxation) with the MEGNet graph neural network energy model

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

Result, AI contribution and limits

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

  • Publication status: Peer-reviewed paper
  • Test type: direct test
  • Tested: A Bayesian optimization workflow using symmetry-constrained crystal relaxation and the MEGNet graph neural network screened 399,960 transition-metal boride and carbide compositions.
  • Still unknown: The arXiv abstract states that the two materials were synthesized and describes them as ultra-incompressible hard materials; the institutional project page reports experiments on eight selected candidates and confirmation of two novel hard materials. The result is from a preprint/journal study and the provided abstract does not give numeric hardness values. Do not imply commercial performance or broader synthesis robustness.
  • AI role: MEGNet supplied graph-based formation-energy predictions; BOWSR used Bayesian optimization under crystal-symmetry constraints to relax candidate structures without DFT geometry relaxation. This enabled screening of 399,960 boride/carbide compositions, narrowing candidates for experimental synthesis.

Evidence sources: https://arxiv.org/abs/2104.10242

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review scope and date are not recorded; source checked does not establish full-text review.

Citations: in the top 10% of works of the same type, year and subfield (OpenAlex work metrics, 153 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Follow-up and relationships

No follow-up recorded; this is not a claim that no follow-up exists.

Follow-up review scope and date are not recorded.

No source-supported relationships recorded.

Open in the full catalog for filters, charts and related discoveries.