Descriptors divide‐and‐conquer enables multifaceted and interpretable materials structure–activity relationship analysis

Simple item page
dc.contributor.authorLiu, Yen_AU
dc.contributor.authorWu, LHen_AU
dc.contributor.authorYang, ZWen_AU
dc.contributor.authorZou, XXen_AU
dc.contributor.authorZou, ZYen_AU
dc.contributor.authorLin, YXen_AU
dc.contributor.authorAvdeev, Men_AU
dc.contributor.authorShi, SQen_AU
dc.date.accessioned2025-10-14T23:14:23Zen_AU
dc.date.available2025-10-14T23:14:23Zen_AU
dc.date.issued2025-02-11en_AU
dc.date.statistics2025-10-14en_AU
dc.description.abstractMachine learning (ML) is increasingly adopted to explore the dependence of properties on descriptors especially for materials with the complicated structure–activity relationships. However, most current ML modeling strategies typically depend on a single combination of descriptors, which leads to inaccurate and unilateral inferences. Here, a descriptors divide‐and‐conquer method is proposed for machine learning (descriptors‐DCML) in which rough set theory (RST) is integrated with materials domain knowledge to select multiple optimal sets of descriptors combinations and thus diverse rule extraction strategies are provided to dig out mechanisms latent in materials data. Its potential utility and applications using the sodium ion energy barrier prediction of NASICION‐type solid‐state electrolyte compounds with multifaceted influencing factors as an example are demonstrated. A total of 85 NASICION‐type samples with 45 descriptors derived from 72 published literature serve as the data foundation for ML modeling. Not only does descriptors‐DCML exhibit the energy barrier prediction accuracy of 93.8% but also extract 9 relations mapping essential factors to Na ion energy barrier in which 5 ones conform to existing understanding rule and the rest are waiting for validation. This work paves the way for reducing the complexity of analyzing materials structure–activity relationships and enhancing the interpretability of ML models. © 1999-2025 John Wiley & Sons, Inc or related companies.en_AU
dc.description.sponsorshipThis work was supported in part by National Natural Science Foundation of China (Nos. 92270124, 52073169,92472207 and 52102313) and the National Key Research and Development Program of China (No. 2021YFB3802101) and Shandong Province Natural Science Foundation (No. ZR2022ZD11). The authors appreciated the High Performance Computing Center of Shanghai University and Shanghai Engineering Research Center of Intelligent Computing System for providing the computing resources and technical support.en_AU
dc.identifier.articlenumber2421621en_AU
dc.identifier.citationLiu, Y., Wu, L., Yang, Z., Zou, X., Zou, Z., Lin, Y., Avdeev, M., & Shi, S. (2025). Descriptors divide‐and‐conquer enables multifaceted and interpretable materials structure–activity relationship analysis. Advanced Functional Materials, 35(26), 2421621. doi:10.1002/adfm.202421621en_AU
dc.identifier.issn1616-301Xen_AU
dc.identifier.issn1616-3028en_AU
dc.identifier.issue26en_AU
dc.identifier.journaltitleAdvanced Functional Materialsen_AU
dc.identifier.urihttps://doi.org/10.1002/adfm.202421621en_AU
dc.identifier.urihttps://apo.ansto.gov.au/handle/10238/16602en_AU
dc.identifier.volume35en_AU
dc.languageEnglishen_AU
dc.language.isoenen_AU
dc.publisherWileyen_AU
dc.subjectMachine Learningen_AU
dc.subjectMaterialsen_AU
dc.subjectSodium ionsen_AU
dc.subjectElectrolytesen_AU
dc.subjectEnergyen_AU
dc.subjectSodiumen_AU
dc.subjectDataen_AU
dc.subjectMaterialsen_AU
dc.subjectAccuracyen_AU
dc.titleDescriptors divide‐and‐conquer enables multifaceted and interpretable materials structure–activity relationship analysisen_AU
dc.typeJournal Articleen_AU
Files
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.66 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles