Speaker
Description
Synchrotron radiation (SR) light sources provide precise and deep insights that have been driving cutting-edge scientific research. Facing to SR scientific big data challenge, it is urgent to develop artificial intelligence (AI) analysis methods to enhance research efficiency including novel material discovery[1]. In this talk, I will focus on the construction of “Intelligence Terminal” multimodal data analysis system including AI analysis methods for image and diffraction SR data. First, regarding image data, we implement a novel localization quantitative analysis method based on deep learning to analyze X-ray nano-computed tomography (Nano-CT). We achieve localization three-dimensional quantitative Nano-CT imaging analysis of single-cell HfO2 nanoparticles and demonstrate the notable effect of the nanoparticles in tumor treatment[2]. Our approaches show the potential to explore the localization quantitative three-dimensional distribution information of specific molecules at the nanoscale level in Nano-CT. Second, regarding diffraction data, we develop two sets of data-driven and physics-knowledge-driven machine learning (ML) methods to analyze the X-ray diffraction and extract three-dimensional orientation information of nanofibers. The data-driven ML model achieves high accuracy and fast analysis of experimental data and is available to be applied in multi light sources and beamlines[3]. The physics-knowledge-driven ML method enables high-precision, self-supervised, interpretable analysis and lays the foundation for systematic knowledge-driven online scientific big data analysis. Then, we develop the using interface named as intelligence photon source brain (IPSBrain, www.ipsbrain.com) based on the “Intelligence Terminal” system for users to utilize the novel AI driven data analysis methods. Overall, our work aims to analyze multimodal SR data accurately and quickly in real-time through AI algorithms, which support AI for SR-based Science strongly.
Reference:
[1] Qingmeng Li, Rongchang Xing, Linshan Li, Haodong Yao, Liyuan Wu, Lina Zhao. Synchrotron radiation data-driven artificial intelligence approaches in materials discovery. Artificial Intelligence Chemistry, 2(1): 2949-7477, (2024).
[2] Zuoxin Xi, Haodong Yao, Tingfeng Zhang, Zongyi Su, Bing Wang, Weiyue Feng, Qiumei Pu, Lina Zhao. Quantitative Three-Dimensional Imaging Analysis of HfO2 NPs in Single Cells Via Deep Learning aided Nano-CT. ACS Nano, revision returned, (2024).
[3] Minghui Sun, Zheng Dong, Liyuan Wu, Haodong Yao, Wenchao Niu, Deting Xu, Ping Chen, Himadri S Gupta, Yi Zhang, Yuhui Dong, Chunying Chen, Lina Zhao*. Fast extraction of three-dimensional nanofiber orientation from WAXD patterns using machine learning, IUCrJ, 10, 3 (2023).
| Abstract publication | I agree that the abstract will be published on the web site |
|---|
