中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
New particle formation event detection with convolutional neural networks

文献类型：期刊论文

作者Zhang, Xun12,13; Wu, Lijie13; Liu, Xiansheng11; Wang, Tao10; Monge, Marta11; Garcia-Marles, Meritxell9,11; Savadkoohi, Marjan8,11; Salma, Imre7; Bastian, Susanne6; Merkel, Maik5
刊名ATMOSPHERIC ENVIRONMENT
出版日期2024-06-15
卷号327页码:120487
关键词Ultrafine particles nucleation ConvNeXt Deep learning Image classification
DOI10.1016/j.atmosenv.2024.120487
产权排序2
文献子类Article
英文摘要New aerosol particle formation (NPF) events play a significant role in altering aerosol concentrations and dispersion within the atmosphere, making them vital for both climate and air quality research. The primary objective of investigating NPF events is to precisely determine their occurrence dates. In this study, we introduced the ConvNeXt model for the first time to identify NPF events, and compared its performance with two other deep learning models, EfficientNet and Swin Transformer. Our main aim was to automate an objective identification and classification of NPF events accurately. All three models employed transfer learning to effectively capture critical features associated with NPF. Our results demonstrated that the ConvNeXt model significantly outperformed the other models, achieving an impressive accuracy rate of 95.3% on event days, surpassing EfficientNet (92.8%) and Swin Transformer (94.9%). Furthermore, we performed tests using different ConvNeXt variants (ConvNeXt-T/S/B/L/XL) and different pre-training weights, revealing that different configurations of ConvNeXt models exhibited improved NPF event recognition capabilities. Finally, we conducted generalizability experiments using the ConvNeXt-XL model, achieving the highest accuracy of 96.4% on event days. This study not only underscores the recognition prowess of ConvNeXt models but also highlights their practical utility in accurately detecting NPF events in real-world scenarios. This contribution aids in advancing Atmospheric our comprehension of aerosol dynamics in atmospheric environments, providing valuable insights for climate and air quality research.
WOS关键词SULFURIC-ACID ; SIZE-DISTRIBUTION ; GROWTH ; NUCLEATION ; ARCHITECTURES ; AEROSOLS
WOS研究方向Environmental Sciences & Ecology ; Meteorology & Atmospheric Sciences
WOS记录号WOS:001224901200001
源URL[http://ir.igsnrr.ac.cn/handle/311030/205148]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Liu, Xiansheng
作者单位1.Eotvos Lorand Univ, Inst Geog & Earth Sci, Dept Meteorol, Budapest, Hungary
2.Acad Sci Czech Republ, Inst Chem Proc Fundamentals, Prague, Czech Republic
3.European Commiss, Joint Res Ctr JRC, Ispra, Italy
4.German Environm Agcy UBA, Dessau Rosslau, Germany
5.Leibniz Inst Tropospher Res TROPOS, Leipzig, Germany
6.Saxon State Off Environm Agr & Geol LfULG, Dresden, Germany
7.Eotvos Lorand Univ, Inst Chem, Budapest, Hungary
8.Univ Politecn Catalunya UPC, Manresa Sch Engn EPSEM, Dept Min Ind & ICT Engn EMIT, Manresa 08242, Spain
9.Univ Barcelona, Dept Appl Phys Meteorol, Barcelona, Spain
10.Fudan Univ, Dept Environm Sci & Engn, Shanghai Key Lab Atmospher Particle Pollut & Prev, Shanghai, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Xun,Wu, Lijie,Liu, Xiansheng,et al. New particle formation event detection with convolutional neural networks[J]. ATMOSPHERIC ENVIRONMENT,2024,327:120487.
APA Zhang, Xun.,Wu, Lijie.,Liu, Xiansheng.,Wang, Tao.,Monge, Marta.,...&Querol, Xavier.(2024).New particle formation event detection with convolutional neural networks.ATMOSPHERIC ENVIRONMENT,327,120487.
MLA Zhang, Xun,et al."New particle formation event detection with convolutional neural networks".ATMOSPHERIC ENVIRONMENT 327(2024):120487.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。