MétaCan
Menu
Back to cohort
Record W4386866600 · doi:10.1149/ma2023-012604mtgabs

(Invited) High-Throughput Development of LiCoPO<sub>4</sub>

2023· article· en· W4386866600 on OpenAlexaff
Nooshin Zeinali Galabi, Shipeng Jia, Antranik Jonderian, Gabin Yoon, Sang Bok, Eric McCalla

Bibliographic record

VenueECS Meeting Abstracts · 2023
Typearticle
Languageen
FieldMaterials Science
TopicMachine Learning in Materials Science
Canadian institutionsMcGill University
Fundersnot available
KeywordsDopingElectrolyteCathodeMaterials scienceConductivityLeverage (statistics)Ionic conductivityIonic bondingEnergy densityCyclingIntuitionChemical engineeringIonNanotechnologyComputer scienceElectrodeEngineering physicsChemistryPhysical chemistryOptoelectronicsPhysicsMachine learning

Abstract

fetched live from OpenAlex

High voltage cathodes are attractive for high energy density Li-ion batteries, particularly with the innovation of solid electrolytes with large stability windows. However, candidates such as LiCoPO 4 have presented numerous problems due to poor electronic/ionic conductivities. Typical solutions involving nanosizing result in extremely poor cycling performance. Herein, we first apply high-throughput methods to develop near-micron sized carbon-coated LiCoPO 4 with improved energy density and capacity retention. 1 In total, 1300 materials with 46 different substituents were synthesized and characterized. A number of substituents showed greatly improved capacity (e.g. 160 mAh/g for 1% In substitution vs. 95 mAh/g for the pristine). However, co-doping was required to improve extended cycling. Li 1-3x Co 1-2x In x Mo x PO 4 was found to be particularly effective with dramatically improved cycling (as high as 100 % after 10 cycles, vs. ~50 % in unsubstituted). While In improved the electronic conductivity of the carbon-coated materials, Mo co-doping gave larger particles and DFT calculations showed that Mo impedes the formation of Li/Co antisite defects. While the above described experiments were solely guided by the researchers intuition, we also explore potential benefits of using machine-learning (ML) algorithms to guide the composition exploration. Random compositions were first prepared to supplement our existing data as part of the training set, then further synthesis was performed based on the ML outputs. The results will be presented in detail to help establish to what extent ML can be used to further leverage our group's high-throughput data. References 1. A. Jonderian, S. Jia, G. Yoon, V.T. Cozea, N. Zeinali Galabi, S.B. Ma, and E. McCalla. Accelerated Development of High Voltage Li-Ion Cathodes. Adv. Energy Mater. 2022, 12, 2201704.

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.

How this classification was reachedexpand

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)0.004
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
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 score0.054
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.002

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 head0.018
GPT teacher head0.258
Teacher spread0.240 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueECS Meeting AbstractsSame topicMachine Learning in Materials ScienceFrench-language works237,207