2023
DOI: 10.1039/d2ee03499a
|View full text |Cite
|
Sign up to set email alerts
|

Identification of potential solid-state Li-ion conductors with semi-supervised learning

Abstract: A semi-supervised machine learning pipeline is reported for the discovery of new Li-ion solid-state electrolytes. The approach is experimentally validated with the synthesis and characterization of a new superionic conductor predicted by the model.

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
7
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 8 publications
(7 citation statements)
references
References 87 publications
0
7
0
Order By: Relevance
“…Amorphization of SSEs often results in an increase in ionic conductivity. , Excess water adsorption could result in the formation of amorphous domains within the material. However, NMR data show that 0.52 H 2 O/ZnPS 3 does not contain significant fractions of amorphous phases.…”
Section: Resultsmentioning
confidence: 99%
“…Amorphization of SSEs often results in an increase in ionic conductivity. , Excess water adsorption could result in the formation of amorphous domains within the material. However, NMR data show that 0.52 H 2 O/ZnPS 3 does not contain significant fractions of amorphous phases.…”
Section: Resultsmentioning
confidence: 99%
“…There have been many different attempts to apply semi-supervised learning to small sample learning, and good results have been achieved in materials science. [46][47][48] In general, semisupervised learning belongs to iterative learning. Researchers can try to build a predictive model on the training data set of small samples (although the accuracy of the model is far from the expectation), use the model to predict the unlabeled samples in test set, and select an appropriate proportion of high confidence (low uncertainty) prediction samples from the prediction results to add to the original training data set, iteratively increasing the data set.…”
Section: Semi-supervised Learningmentioning
confidence: 99%
“…For this, machine learning (ML) techniques can be exploited for uncovering latent data structures and exceptional accuracy in prediction tasks. 2,17,[26][27][28][29][18][19][20][21][22][23][24][25] However, their application in material discovery may produce unreliable outcomes, mainly due to model overfitting from insufficient data. Our comprehensive literature survey reveals that, to date, only 34 Na-ion SSEs have experimental records of ionic conductivity.…”
Section: Introductionmentioning
confidence: 99%