AI Science Tracker
EN

Predicting Van der Waals Heterostructures by a Combined Machine Learning and Density Functional Theory Approach.

Not stated in the abstract reviewed · 27 May 2022 · multidisciplinary

Discovery

Predicting Van der Waals Heterostructures by a Combined Machine Learning and Density Functional Theory Approach.

Source check: Source checked. Not independent scientific confirmation.

Finding: The full primary article combines DFT calculations on 595 electronic-property bilayers and 776 distance/binding-energy bilayers with supervised ML trained from constituent monolayer descriptors. The resulting survey of nearly 4,000 bilayers reports property predictions and a specific stacking-dependent result: most AA/AB pairs differ substantially in equilibrium spacing, implying reconstruction in twisted moiré systems. Repeated five-fold validation supports screening utility; findings are computational predictions, not experimental confirmation.

Technology: Supervised ML regressors trained on DFT-labeled vdW bilayers and monolayer descriptors predict band gap, electron affinity, ionization energy, interlayer distance and binding energy across unlabeled combinations.

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

AI contribution
Supervised ML regressors trained on DFT-labeled vdW bilayers and monolayer descriptors predict band gap, electron affinity, ionization energy, interlayer distance and binding energy across unlabeled combinations.
Test and result
Survey of nearly 4,000 bilayers from seven prototypes; reports low-error predictions and the specific AA/AB stacking difference in spacing, with implications for moiré reconstruction.
Limitation / still unknown
Models are evaluated with repeated k-fold CV and compared against DFT; training labels originate from DFT calculations. Scope remains computational; no experimental validation is claimed.
Evidence sources and annotation context

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

Evidence sources: https://par.nsf.gov/servlets/purl/10344201

Source checked · editorial details

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

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

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.

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.

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