Citation: Ke Ma, Shiqiang Feng, Haihui Hu, Yimeng Cai, Dechao Chen, Lili Han. Deep learning-based workflow for atomic image denoising and chemical identification[J]. Chinese Journal of Structural Chemistry, ;2025, 44(5): 100572. doi: 10.1016/j.cjsc.2025.100572 shu

Deep learning-based workflow for atomic image denoising and chemical identification

Aberration-corrected annular dark-field scanning transmission electron microscopy (ADF-STEM) is a powerful tool for structural and chemical analysis of materials. Conventional analyses of ADF-STEM images rely on human labeling, making them labor-intensive and prone to subjective error. Here, we introduce a deep-learning-based workflow combining a pix2pix network for image denoising and either a mathematical algorithm local intensity threshold segmentation (LITS) or another deep learning network UNet for chemical identification. After denoising, the processed images exhibit a five-fold improvement in signal-to-noise ratio and a 20% increase in accuracy of atomic localization. Then, we take atomic-resolution images of Y–Ce dual-atom catalysts (DACs) and Fe-doped ReSe2 nanosheets as examples to validate the performance. Pix2pix is applied to identify atomic sites in Y–Ce DACs with a location recall of 0.88 and a location precision of 0.99. LITS is used to further differentiate Y and Ce sites by the intensity of atomic sites. Furthermore, pix2pix and UNet workflow with better automaticity is applied to identification of Fe-doped ReSe2 nanosheets. Three types of atomic sites (Re, the substitution of Fe for Re, and the adatom of Fe on Re) are distinguished with the identification recall of more than 0.90 and the precision of higher than 0.93. These results suggest that this strategy facilitates high-quality and automated chemical identification of atomic-resolution images.
- Atomic-resolution image,
- Deep learning,
- Chemical identification,
- Dual-atoms catalyst,
- Atomic dopant,
- Scanning transmission electron microscopy,
- Denoising
1. [1]
  Xi Xue , Kai Chen , Hanyu Sun , Xiangying Liu , Xue Liu , Shize Li , Jingjie Yan , Yu Peng , Mohammad S. Mubarak , Ahmed Al-Harrasi , Hai-Yu Hu , Yafeng Deng , Xiandao Pan , Xiaojian Wang . Bidirectional Chemical Intelligent Net: A unified deep learning–based framework for predicting chemical reaction. Chinese Chemical Letters, 2025, 36(11): 110968-. doi: 10.1016/j.cclet.2025.110968
2. [2]
  Na Qin , Wenxin Guo , Fangxiu Li , Houfeng Zhang , Hong Liu , Chang Zhang , Lipiao Bao , Lei Liu , Muneerah Alomar , Siqi Zhao , Jian Zhang , Xing Lu . Recent advances in machine learning-driven discovery of alloy electrocatalysts for hydrogen evolution reaction. Chinese Chemical Letters, 2026, 37(3): 112021-. doi: 10.1016/j.cclet.2025.112021
3. [3]
  Feihu Wu , Gengwen Chen , Kaitao Lai , Shiqing Zhang , Yingchao Liu , Ruijian Luo , Xiaocong Wang , Pinzhi Cao , Yi Ye , Jiarong Lian , Junle Qu , Zhigang Yang , Xiaojun Peng . Non-specific/specific SERS spectra concatenation for precise bacteria classifications with few samples using a residual neural network. Chinese Chemical Letters, 2025, 36(1): 109884-. doi: 10.1016/j.cclet.2024.109884
4. [4]
  Chang Guo , Haipeng Yang , Hui Fang , Yingguo Zhao , Yating Li . 基于深度学习的物理化学课程DOK教学实践初探——以弯曲液面附加压力和蒸气压教学为例. University Chemistry, 2025, 40(6): 28-36. doi: 10.12461/PKU.DXHX202408049
5. [5]
  Jun Jiang , Quan Lan , Yuan Zheng , Zhenggen Zha . Teaching Exploration and Practice of the Organic Chemistry Laboratory English Course Based on the “Flipped Classroom + MOOC” Teaching Model. University Chemistry, 2025, 40(9): 279-286. doi: 10.12461/PKU.DXHX202410094
6. [6]
  Haolin Zhan , Qiyuan Fang , Jiawei Liu , Xiaoqi Shi , Xinyu Chen , Yuqing Huang , Zhong Chen . Noise Reduction of Nuclear Magnetic Resonance Spectroscopy Using Lightweight Deep Neural Network. Acta Physico-Chimica Sinica, 2025, 41(2): 100017-0. doi: 10.3866/PKU.WHXB202310045
7. [7]
  Lingyue Liu , Jie Ding . Atomic design of SACs directs PMS activation through ETP. Chinese Journal of Structural Chemistry, 2025, 44(10): 100681-100681. doi: 10.1016/j.cjsc.2025.100681
8. [8]
  Xiaowen Cao , Yuheng Zhu , Siyue Fan , Feng Chen , Yongxi Zhao . Accurate counting of RNA in tissues with highly denoising amplified imaging. Chinese Chemical Letters, 2025, 36(12): 111091-. doi: 10.1016/j.cclet.2025.111091
9. [9]
  Liping Wang , Huanfeng Wang , Yuling Li , Lingchuan Li , Xiaojing Li , Huifeng Chen , Bowen Ji , Linna Wang . Exploring the Full Process of a Research-Based Teaching Model through the Deep Integration of Theory and Practice: A Case Study of the Self-Designed Scheme for “Determination of Total Acid Content in White Vinegar”. University Chemistry, 2025, 40(5): 244-251. doi: 10.12461/PKU.DXHX202406035
10. [10]
  Zhaojing Huang , Hao Li , Jiayi Luo , Shunxing Li , Ming Zhao , Fengjiao Liu , Haijiao Xie . Deep learning-based simultaneous bioavailability assessment and speciation analysis of dissolved organic copper. Chinese Chemical Letters, 2025, 36(5): 110209-. doi: 10.1016/j.cclet.2024.110209
11. [11]
  Xiangyu Chen , Aihao Xu , Dong Wei , Fang Huang , Junjie Ma , Huibing He , Jing Xu . Atomic cerium-doped CuO_x catalysts for efficient electrocatalytic CO₂ reduction to CH₄. Chinese Chemical Letters, 2025, 36(1): 110175-. doi: 10.1016/j.cclet.2024.110175
12. [12]
  Sanmei Wang , Yong Zhou , Hengxin Fang , Chunyang Nie , Chang Q Sun , Biao Wang . Constant-potential simulation of electrocatalytic N₂ reduction over atomic metal-N-graphene catalysts. Chinese Chemical Letters, 2025, 36(3): 110476-. doi: 10.1016/j.cclet.2024.110476
13. [13]
  Jinxin Li , Yifan Ren , Jianan Gao , Nadeeshani Nanayakkara , Xin Wang , Meng Liu , Yanbiao Liu . Asymmetric triple-atomic sites with modulated electronic structure toward boosted peroxymonosulfate activation. Chinese Chemical Letters, 2026, 37(2): 111355-. doi: 10.1016/j.cclet.2025.111355
14. [14]
  Wenjie Zhang , Jiong Zhou . Enhanced oxygen reduction through axial chlorine engineering of p-block antimony atomic sites. Chinese Journal of Structural Chemistry, 2026, 45(1): 100732-100732. doi: 10.1016/j.cjsc.2025.100732
15. [15]
  Li Zhou , Fengyu Li , Zhou Lu , Yingwei Wang , Jun He . Two-dimensional atomic crystals for third-order nonlinear optical modulation. Chinese Journal of Structural Chemistry, 2026, 45(2): 100772-100772. doi: 10.1016/j.cjsc.2025.100772
16. [16]
  Yutong Xiong , Ting Meng , Wendi Luo , Bin Tu , Shuai Wang , Qingdao Zeng . Molecular conformational effects on co-assembly systems of low-symmetric carboxylic acids investigated by scanning tunneling microscopy. Chinese Journal of Structural Chemistry, 2025, 44(2): 100511-100511. doi: 10.1016/j.cjsc.2025.100511
17. [17]
  Zhilin Meng , Haiying Lu , Weijie Li . A low-temperature strategy enables atomic-level control in noble metal-based high-entropy catalysts. Chinese Journal of Structural Chemistry, 2026, 45(3): 100800-100800. doi: 10.1016/j.cjsc.2025.100800
18. [18]
  Luyao Guan , Zhaoxin Wang , Shengkai Li , Phouphien Keoingthong , Zhuo Chen . CoPt graphitic nanozyme enabled naked-eye identification and colorimetric/fluorescent dual-mode detection of phenylenediamine isomers. Chinese Chemical Letters, 2026, 37(2): 111323-. doi: 10.1016/j.cclet.2025.111323
19. [19]
  Mingjiao Lu , Zhixing Wang , Gui Luo , Huajun Guo , Xinhai Li , Guochun Yan , Qihou Li , Xianglin Li , Ding Wang , Jiexi Wang . Boosting the performance of LiNi_0.90Co_0.06Mn_0.04O₂ electrode by uniform Li₃PO₄ coating via atomic layer deposition. Chinese Chemical Letters, 2024, 35(5): 108638-. doi: 10.1016/j.cclet.2023.108638
20. [20]
  Tianjun Ni , Hui Zhang , Liping Zhou , Roujie Ma , Yanyu Wang , Zhijun Yang , Dan Luo , Nithima Khaorapapong , Xingtao Xu , Yusuke Yamauchi , Dong Liu . Atomic cobalt catalysts on 3D interconnected g-C₃N₄ support for activation of peroxymonosulfate: The importance of Co-N coordination effect. Chinese Chemical Letters, 2025, 36(9): 110659-. doi: 10.1016/j.cclet.2024.110659

Get Citation

PDF

XML

Metrics

PDF Downloads(0)
Abstract views(128)
HTML views(0)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Address：Zhongguancun North First Street 2,100190 Beijing, PR China Tel: +86-010-82449177-888

DownLoad: Full-Size Img PowerPoint

Return