A high-energy conversion-type cathode activated by amorpholization for Li rechargeable batteries

Lee, Yongseok; Kang, Jungmin; Ahn, Jinho; Ko, Wonseok; Park, Hyun-Young; Lee, Seokjin; Lee, Sangyeop; Yoo, Jung-Keun; Kim, Jongsoon

doi:10.1039/d2ta02167f

Cited by 5 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…S5 ) is able to acquire knowledge by reusing parameters in the hidden layers from a well-trained model and apply it to another different but related task ( 29 ). Two MOFs ( 30 , 31 ) (PFC-73-Cu and Cu-PO 3 , left column in Fig. 2 B and C ) and CO@MOF systems with 1,305 sets of spectra and catalytic property data were generated by similar sampling and calculation methods.…”

Section: Resultsmentioning

confidence: 99%

Machine learning of spectra-property relationship for imperfect and small chemistry data

Chong

Huo

Jiang

et al. 2023

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Machine learning (ML) is causing profound changes to chemical research through its powerful statistical and mathematical methodological capabilities. However, the nature of chemistry experiments often sets very high hurdles to collect high-quality data that are deficiency free, contradicting the need of ML to learn from big data. Even worse, the black-box nature of most ML methods requires more abundant data to ensure good transferability. Herein, we combine physics-based spectral descriptors with a symbolic regression method to establish interpretable spectra–property relationship. Using the machine-learned mathematical formulas, we have predicted the adsorption energy and charge transfer of the CO-adsorbed Cu-based MOF systems from their infrared and Raman spectra. The explicit prediction models are robust, allowing them to be transferrable to small and low-quality dataset containing partial errors. Surprisingly, they can be used to identify and clean error data, which are common data scenarios in real experiments. Such robust learning protocol will significantly enhance the applicability of machine-learned spectroscopy for chemical science.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine learning of spectra-property relationship for imperfect and small chemistry data

Chong

Huo

Jiang

et al. 2023

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

Tactics to optimize conversion-type metal fluoride/sulfide/oxide cathodes toward advanced lithium metal batteries

2023

View full text Add to dashboard Cite

Chiolite Na5Ti3F14: A novel sodium titanium fluoride anode for low-cost and high-performance Na-ion batteries

Kang,

Ahn,

Lee

et al. 2023

Energy Storage Materials

View full text Add to dashboard Cite

A high-energy conversion-type cathode activated by amorpholization for Li rechargeable batteries

Abstract: Although conversion-type electrodes deliver larger theoretical capacities than intercalation-type electrodes, their application as practical cathodes for Li rechargeable batteries is hindered by their intrinsically sluggish kinetics and low operating voltage....

Cited by 5 publications

References 46 publications

Machine learning of spectra-property relationship for imperfect and small chemistry data

Machine learning of spectra-property relationship for imperfect and small chemistry data

Tactics to optimize conversion-type metal fluoride/sulfide/oxide cathodes toward advanced lithium metal batteries

Chiolite Na5Ti3F14: A novel sodium titanium fluoride anode for low-cost and high-performance Na-ion batteries

Contact Info

Product

Resources

About