{"title":"使用生成模型进行粉末衍射晶体结构测定","authors":"Qi Li, Rui Jiao, Liming Wu, Tiannian Zhu, Wenbing Huang, Shifeng Jin, Yang Liu, Hongming Weng, Xiaolong Chen","doi":"arxiv-2409.04727","DOIUrl":null,"url":null,"abstract":"Accurate crystal structure determination is critical across all scientific\ndisciplines involving crystalline materials. However, solving and refining\ninorganic crystal structures from powder X-ray diffraction (PXRD) data is\ntraditionally a labor-intensive and time-consuming process that demands\nsubstantial expertise. In this work, we introduce PXRDGen, an end-to-end neural\nnetwork that determines crystal structures by learning joint structural\ndistributions from experimentally stable crystals and their PXRD, producing\natomically accurate structures refined through PXRD data. PXRDGen integrates a\npretrained XRD encoder, a diffusion/flow-based structure generator, and a\nRietveld refinement module, enabling the solution of structures with\nunparalleled accuracy in a matter of seconds. Evaluation on MP-20 inorganic\ndataset reveals a remarkable matching rate of 82% (1 sample) and 96% (20\nsamples) for valid compounds, with Root Mean Square Error (RMSE) approaching\nthe precision limits of Rietveld refinement. PXRDGen effectively tackles key\nchallenges in XRD, such as the precise localization of light atoms,\ndifferentiation of neighboring elements, and resolution of overlapping peaks.\nOverall, PXRDGen marks a significant advancement in the automated determination\nof crystal structures from powder diffraction data.","PeriodicalId":501234,"journal":{"name":"arXiv - PHYS - Materials Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Powder Diffraction Crystal Structure Determination Using Generative Models\",\"authors\":\"Qi Li, Rui Jiao, Liming Wu, Tiannian Zhu, Wenbing Huang, Shifeng Jin, Yang Liu, Hongming Weng, Xiaolong Chen\",\"doi\":\"arxiv-2409.04727\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Accurate crystal structure determination is critical across all scientific\\ndisciplines involving crystalline materials. However, solving and refining\\ninorganic crystal structures from powder X-ray diffraction (PXRD) data is\\ntraditionally a labor-intensive and time-consuming process that demands\\nsubstantial expertise. In this work, we introduce PXRDGen, an end-to-end neural\\nnetwork that determines crystal structures by learning joint structural\\ndistributions from experimentally stable crystals and their PXRD, producing\\natomically accurate structures refined through PXRD data. PXRDGen integrates a\\npretrained XRD encoder, a diffusion/flow-based structure generator, and a\\nRietveld refinement module, enabling the solution of structures with\\nunparalleled accuracy in a matter of seconds. Evaluation on MP-20 inorganic\\ndataset reveals a remarkable matching rate of 82% (1 sample) and 96% (20\\nsamples) for valid compounds, with Root Mean Square Error (RMSE) approaching\\nthe precision limits of Rietveld refinement. PXRDGen effectively tackles key\\nchallenges in XRD, such as the precise localization of light atoms,\\ndifferentiation of neighboring elements, and resolution of overlapping peaks.\\nOverall, PXRDGen marks a significant advancement in the automated determination\\nof crystal structures from powder diffraction data.\",\"PeriodicalId\":501234,\"journal\":{\"name\":\"arXiv - PHYS - Materials Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Materials Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.04727\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Materials Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04727","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Powder Diffraction Crystal Structure Determination Using Generative Models
Accurate crystal structure determination is critical across all scientific
disciplines involving crystalline materials. However, solving and refining
inorganic crystal structures from powder X-ray diffraction (PXRD) data is
traditionally a labor-intensive and time-consuming process that demands
substantial expertise. In this work, we introduce PXRDGen, an end-to-end neural
network that determines crystal structures by learning joint structural
distributions from experimentally stable crystals and their PXRD, producing
atomically accurate structures refined through PXRD data. PXRDGen integrates a
pretrained XRD encoder, a diffusion/flow-based structure generator, and a
Rietveld refinement module, enabling the solution of structures with
unparalleled accuracy in a matter of seconds. Evaluation on MP-20 inorganic
dataset reveals a remarkable matching rate of 82% (1 sample) and 96% (20
samples) for valid compounds, with Root Mean Square Error (RMSE) approaching
the precision limits of Rietveld refinement. PXRDGen effectively tackles key
challenges in XRD, such as the precise localization of light atoms,
differentiation of neighboring elements, and resolution of overlapping peaks.
Overall, PXRDGen marks a significant advancement in the automated determination
of crystal structures from powder diffraction data.