MétaCan
Menu
Back to cohort
Record W4283317747 · doi:10.1021/acsaem.2c00493

Automatically Capturing Key Features for Predicting Superionic Conductivity of Solid-State Electrolytes Using a Neural Network

2022· article· en· W4283317747 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueACS Applied Energy Materials · 2022
Typearticle
Languageen
FieldMaterials Science
TopicMachine Learning in Materials Science
Canadian institutionsNational Research Council CanadaUniversity of Toronto
FundersNational Research Council CanadaNatural Sciences and Engineering Research Council of CanadaUniversity of TorontoCanada Foundation for Innovation
KeywordsComputer scienceArtificial neural networkArtificial intelligenceFeature (linguistics)Process (computing)Machine learningProperty (philosophy)IntuitionFeature selectionObstacle

Abstract

fetched live from OpenAlex

Solid-state batteries (SSBs) are one of the most promising energy storage technologies due to their low flammability and high energy density compared with currently used liquid-state batteries. The main obstacle to SSB development, however, is the large chemical design space for the solid-state electrolytes (SSEs), as it is significantly time-consuming to screen candidates experimentally or from first-principles simulations. Toward this end, machine learning (ML) offers an efficient strategy. However, current ML models use complex manually created features as inputs based on human intuition, which can introduce human bias, are potentially difficult to obtain for many materials, and can result in a cumbersome feature selection process. This work demonstrates that a neural network-based model utilizing only two simple elemental features (group and period) and one simple structural feature (coordination number) can provide excellent predictive performance comparable to previous manual feature-based studies, while automatically capturing any potential secondary features and reducing the need for human intervention in model training. Such a model is potentially more generalizable than manual feature-based models and can be even applied to other material property predictions, while greatly reducing complexity and training time.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.325
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.254
Teacher spread0.241 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it