Download file (182KB)
Download as zip (177KB)

コレクション

引用

説明:

Motivated by the observation that screening known materials using trained property models often fails to identify candidates that outperform those in the training set, we introduce a periodic descriptor-based exploration strategy to search for new, uncharted compositions. To support structure-aware validation, we constructed classification models for space group and Pearson symbol using approximately 150,000 experimentally reported compounds from the AtomWork-Adv. (AWA) database, developed by NIMS. These models enable structure prediction from formula-only inputs, thereby facilitating downstream simulations and structure generation.

権利情報:

• In Copyright
  

キーワード: Inverse design, Structure prediction, Periodic descriptor

会議: MRM2025 (2025-12-08 - 2025-12-13)

研究助成金:

原稿種別: 論文以外のデータ

MDR DOI: https://doi.org/10.48505/nims.6034

公開URL:

関連資料:

その他の識別子:

連絡先:

更新時刻: 2025-12-19 09:52:03 +0900

MDRでの公開時刻: 2025-12-19 14:11:37 +0900