新しいAIモデルは自律的材料科学への飛躍となる(New AI Model Is a Leap for Autonomous Materials Science)

ad

2024-03-21 パシフィック・ノースウェスト国立研究所(PNNL)

PNNLが開発した新しいAIモデルは、人間の介入なしに材料の電子顕微鏡画像のパターンを識別し、材料科学の正確性と一貫性を向上させます。これにより、自律型実験や材料の劣化理解が容易になり、人間の手による手作業でのデータラベリングを回避できます。

<関連情報>

電子顕微鏡における照射誘起秩序-無秩序相転移の教師なしセグメンテーション Unsupervised segmentation of irradiation‐induced order‐disorder phase transitions in electron microscopy

Arman H Ter-Petrosyan, Jenna A Bilbrey, Christina M Doty, Bethany E Matthews, Le Wang, Yingge Du, Eric Lang, Khalid Hattar, Steven R Spurgeon
arXiv  Submitted on:14 Nov 2023
DOI:https://doi.org/10.48550/arXiv.2311.08585

新しいAIモデルは自律的材料科学への飛躍となる(New AI Model Is a Leap for Autonomous Materials Science)

Abstract

We present a method for the unsupervised segmentation of electron microscopy images, which are powerful descriptors of materials and chemical systems. Images are oversegmented into overlapping chips, and similarity graphs are generated from embeddings extracted from a domain‐pretrained convolutional neural network (CNN). The Louvain method for community detection is then applied to perform segmentation. The graph representation provides an intuitive way of presenting the relationship between chips and communities. We demonstrate our method to track irradiation‐induced amorphous fronts in thin films used for catalysis and electronics. This method has potential for “on‐the‐fly” segmentation to guide emerging automated electron microscopes.

1700応用理学一般
ad
ad
Follow
ad
タイトルとURLをコピーしました