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

Laskowski, Forrest A. L.; McHaffie, Daniel B.; See, Kimberly A.

doi:10.1039/d2ee03499a

Cited by 8 publications

(7 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

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%

Water Vapor Induced Superionic Conductivity in ZnPS₃

et al. 2023

Self Cite

View full text Add to dashboard Cite

Next-generation batteries based on sustainable multivalent working ions, such as Mg 2+ , Ca 2+ , or Zn 2+ , have the potential to improve the performance, safety, and capacity of current battery systems. Development of such multivalent ion batteries is hindered by a lack of understanding of multivalent ionics in solids, which is crucial for many aspects of battery operation. For instance, multivalent ionic transport was assumed to be correlated with electronic transport; however, we have previously shown that Zn 2+ can conduct in electronically insulating ZnPS 3 with a low activation energy of 350 meV, albeit with low ionic conductivity. Here, we show that exposure of ZnPS 3 to environments with water vapor at different relative humidities results in room-temperature conductivity increases of several orders of magnitude, reaching as high as 1.44 mS cm −1 without decomposition or structural changes. We utilize impedance spectroscopy with ion selective electrodes, ionic transference number measurements, and deposition and stripping of Zn metal, to confirm that both Zn 2+ and H + act as mobile ions. The contribution from Zn 2+ to the ionic conductivity in water vapor exposed ZnPS 3 is high, representing superionic Zn 2+ conduction. The present study demonstrates that it is possible to enhance multivalent ion conduction of electronically insulating solids as a result of water adsorption and highlights the importance of ensuring that increased conductivity in water vapor exposed multivalent ion systems is in fact due to mobile multivalent ions and not solely H + .

show abstract

Section: Resultsmentioning

confidence: 99%

Water Vapor Induced Superionic Conductivity in ZnPS₃

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…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%

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

Wang,

Chen,

Tao

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Combining materials science, artificial intelligence (AI), physical chemistry and other disciplines, materials informatics is continuously accelerating the vigorous development of new materials. The emergence of “GPT AI” shows that the scientific research field has entered the era of intelligent civilization with “data” as the basic factor and “algorithm + computing power” as the core productivity. The continuous innovation of AI will impact the cognitive laws and scientific methods, and reconstruct the knowledge and wisdom system. This leads us to think more about materials informatics, both in terms of opportunities and challenges. In this review, we provide a comprehensive discussion of AI models, materials infrastructures, and review the current advances in the discovery and design of new materials. With the rise of new research paradigms triggered by “AI for Science”, we propose the vane of materials informatics: “MatGPT”, and carry out the technical path planning from the aspects of data, descriptors, generative models, pre‐training models, directed design models, collaborative training, experimental robots, as well as the efforts and preparations needed to develop a new generation of materials informatics. Finally, we discuss the challenges and constraints faced by materials informatics, in order to achieve a more digital, intelligent and automated construction of materials informatics with the joint efforts of more interdisciplinary scientists. This article is protected by copyright. All rights reserved

show abstract

“…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%

Computational screening of sodium solid electrolytes through unsupervised learning

Kim,

Park,

Chung

et al. 2024

Preprint

View full text Add to dashboard Cite

All-solid-state Na-ion batteries have emerged as alternatives of all-solid-state Li-ion batteries owing to the global abundance of Na element. However, the attempts to seek a commercially viable Na-ion solid-state electrolyte (SSE) are challenging due to the relatively poor understanding of the structures which are effective for conducting Na-ion compared to Li-ion SSE. In this study, unsupervised machine learning is performed to reveal the major characteristics of possible Na-ion SSEs. The descriptor vector that consists of 180 quantitative structure-properties for 12,670 Na-ion contained SSE structures was utilized as training data for the unsupervised clustering via the hierarchical density-based spatial clustering of applications with noise. The resulted clusters identified 12 structure groups including experimentally proven Na-ion superconductor ones such as NASICONs and thiophosphates. The post hoc analysis of the clusters reveals that the structure groups with high conductivity shares the similar characteristics implying the existence of mobility ion channels and the weak interactions between Na-ions and the proximate atoms. The ab initio molecular dynamics simulation results are presented to confirm the promising Na-ion SSE group shows characteristic tendencies in Na ion diffusivity distinguishable from other groups. The Na-ion SSEs map provided in this study will serve as fundamental guidelines to develop novel Na-ion SSEs for all-solid-state Na-ion batteries

show abstract

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.

Cited by 8 publications

References 87 publications

Water Vapor Induced Superionic Conductivity in ZnPS₃

Water Vapor Induced Superionic Conductivity in ZnPS₃

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

Computational screening of sodium solid electrolytes through unsupervised learning

Contact Info

Product

Resources

About

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.

Cited by 8 publications

References 87 publications

Water Vapor Induced Superionic Conductivity in ZnPS3

Water Vapor Induced Superionic Conductivity in ZnPS3

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

Computational screening of sodium solid electrolytes through unsupervised learning

Contact Info

Product

Resources

About

Water Vapor Induced Superionic Conductivity in ZnPS₃

Water Vapor Induced Superionic Conductivity in ZnPS₃