A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
New particle formation event detection with convolutional neural networks
https://orcid.org/0000-0002-0228-5551
https://orcid.org/0000-0002-3707-2601
https://orcid.org/0000-0001-8319-1647
https://orcid.org/0000-0003-1921-6496
https://orcid.org/0000-0001-9785-8561
https://orcid.org/0000-0001-8753-386X
https://orcid.org/0000-0002-5453-5495
https://orcid.org/0000-0002-6549-9899
Abstract 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 our comprehension of aerosol dynamics in atmospheric environments, providing valuable insights for climate and air quality research.
Highlights Employed ConvNeXt model, used transfer learning to identify NPF events. Comparative analysis showed ConvNeXt's outstanding 95.3% accuracy. Tests with different ConvNeXt variants demonstrated enhanced capabilities. ConvNeXt-XL excelled, achieving 96.4% accuracy in generalization experiments.
New particle formation event detection with convolutional neural networks
https://orcid.org/0000-0002-0228-5551
https://orcid.org/0000-0002-3707-2601
https://orcid.org/0000-0001-8319-1647
https://orcid.org/0000-0003-1921-6496
https://orcid.org/0000-0001-9785-8561
https://orcid.org/0000-0001-8753-386X
https://orcid.org/0000-0002-5453-5495
https://orcid.org/0000-0002-6549-9899
Abstract 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 our comprehension of aerosol dynamics in atmospheric environments, providing valuable insights for climate and air quality research.
Highlights Employed ConvNeXt model, used transfer learning to identify NPF events. Comparative analysis showed ConvNeXt's outstanding 95.3% accuracy. Tests with different ConvNeXt variants demonstrated enhanced capabilities. ConvNeXt-XL excelled, achieving 96.4% accuracy in generalization experiments.
New particle formation event detection with convolutional neural networks
https://orcid.org/0000-0002-0228-5551
https://orcid.org/0000-0002-3707-2601
https://orcid.org/0000-0001-8319-1647
https://orcid.org/0000-0003-1921-6496
https://orcid.org/0000-0001-9785-8561
https://orcid.org/0000-0001-8753-386X
https://orcid.org/0000-0002-5453-5495
https://orcid.org/0000-0002-6549-9899
Abstract 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 our comprehension of aerosol dynamics in atmospheric environments, providing valuable insights for climate and air quality research.
Highlights Employed ConvNeXt model, used transfer learning to identify NPF events. Comparative analysis showed ConvNeXt's outstanding 95.3% accuracy. Tests with different ConvNeXt variants demonstrated enhanced capabilities. ConvNeXt-XL excelled, achieving 96.4% accuracy in generalization experiments.
New particle formation event detection with convolutional neural networks
Zhang, Xun (author) / Wu, Lijie (author) / Liu, Xiansheng (author) / Wang, Tao (author) / Monge, Marta (author) / Garcia-Marlès, Meritxell (author) / Savadkoohi, Marjan (author) / Salma, Imre (author) / Bastian, Susanne (author) / Merkel, Maik (author)
Atmospheric Environment ; 327
2024-03-25
Article (Journal)
Electronic Resource
English
Biomedical event trigger detection based on convolutional neural network
| British Library Online Contents | 2016
Convolutional neural networks based droplet detection method
| Wiley | 2022
Structural crack detection using deep convolutional neural networks
| Elsevier | 2021