Ziwen Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ziwen Guo has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Xu Hou
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, China
2 shared publications - Bo Yang
Engineering Research Center of Environment-Friendly Functional Materials, Ministry of Education, College of Materials Science and Engineering, Huaqiao University, Xiamen, China
1 shared publication Chenxin Ye
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, China
1 shared publication- Jia-Ping Tong
State Key Laboratory of Physical Chemistry of Solid Surfaces and Department of Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, People's Republic of China
1 shared publication - Jian Zhang
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, China
1 shared publication Jing Liu
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, China
1 shared publication
Latest Publications
- 5 October 2026
- Published by Springer Nature in Nature Sustainability
- p. 1-11
Highly efficient air purification by a charge-induced liquid-lined filter
- 5 October 2026
- Published by Springer Nature in Nature Sustainability
- p. 1-11
Highly efficient air purification by a charge-induced liquid-lined filter
- 18 May 2026
- Published by American Chemical Society (ACS) in Nano Letters
- Vol. 26 (21) , 6735-6747
Artificial Intelligence for Bioinspired Nanofluidic Iontronics
Bioinspired nanofluidic iontronics is emerging as a pivotal technology for next-generation biosensing and neuromorphic computing. Although constrained by nanoscale perturbations and fabrication heterogeneity, artificial intelligence (AI) effectively mitigates inherent signal and manufacturing bottlenecks, driving a paradigm shift toward bidirectional empowerment. In this Mini-Review, we summarize recent advances in the convergence of AI and iontronics, focusing on the core scientific conflict between algorithmic robustness and nanoscale physical stochasticity. We analyze how this interaction reshapes three key dimensions of the research workflow: (1) AI-enabled characterization for feature extraction and mechanistic analysis amidst noise; (2) AI-driven fabrication via surrogate models and inverse structural design to bridge the design-to-fabrication gap; and (3) AI-expanded applications in intelligent biosensing and physical neuromorphic computing. Finally, we propose a synergistic roadmap: managing physical imperfections via manufacturing-aware models while shifting AI from merely circumventing errors to architectures that actively exploit intrinsic stochasticity.
- 18 May 2026
- Published by American Chemical Society (ACS) in Nano Letters
- Vol. 26 (21) , 6735-6747
Artificial Intelligence for Bioinspired Nanofluidic Iontronics
Bioinspired nanofluidic iontronics is emerging as a pivotal technology for next-generation biosensing and neuromorphic computing. Although constrained by nanoscale perturbations and fabrication heterogeneity, artificial intelligence (AI) effectively mitigates inherent signal and manufacturing bottlenecks, driving a paradigm shift toward bidirectional empowerment. In this Mini-Review, we summarize recent advances in the convergence of AI and iontronics, focusing on the core scientific conflict between algorithmic robustness and nanoscale physical stochasticity. We analyze how this interaction reshapes three key dimensions of the research workflow: (1) AI-enabled characterization for feature extraction and mechanistic analysis amidst noise; (2) AI-driven fabrication via surrogate models and inverse structural design to bridge the design-to-fabrication gap; and (3) AI-expanded applications in intelligent biosensing and physical neuromorphic computing. Finally, we propose a synergistic roadmap: managing physical imperfections via manufacturing-aware models while shifting AI from merely circumventing errors to architectures that actively exploit intrinsic stochasticity.