Single Particle Mass Spectral Signatures from On-Road and Non-Road Vehicle Exhaust Particles and Their Application in Refined Source Apportionment Using Deep Learning DOI
Yongjiang Xu, Zaihua Wang, Shiping Li

и другие.

Опубликована: Янв. 1, 2023

With advances in vehicle emission control technology, updating source profiles to meet the current requirement of apportionment has become increasingly crucial. In this study, on-road and non-road particles were collected, then chemical composition individual particle was analyzed using single aerosol mass spectrometry. The data grouped an adaptive resonance theory neural network, identify signatures establish a spectral database mobile sources. addition, deep learning-based model (DeepAerosolClassifier) for classifying established. objective accomplish apportionment. During training process, achieved accuracy 98.49% on validation set 93.36% test set. Regarding interpretation, ideal spectra generated verify its accurate recognition characteristic patterns spectra. practical application, used perform hourly at three specific field monitoring sites. effectiveness measurement validated by combining traffic flow spatial information with results. Compared other machine learning methods, our highly automated while eliminating need feature selection enables end-to-end operation. Thus, future, it can be applied refined online particulate matter.

Язык: Английский

High-resolution Spatiotemporal Prediction of PM2.5 Concentration based on Mobile Monitoring and Deep Learning DOI
Yizhou Wang, Hong-di He, Haichao Huang

и другие.

Environmental Pollution, Год журнала: 2024, Номер unknown, С. 125342 - 125342

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

6
Effect of local measures on the update of the circulating vehicle fleet and the reduction of associated emissions: 10 years of experience in the city of Madrid DOI Creative Commons
Javier Pérez,

H. Diez

Cities, Год журнала: 2024, Номер 152, С. 105214 - 105214

Опубликована: Июнь 19, 2024

Язык: Английский

Процитировано

3
Advancements in machine learning for spatiotemporal urban on-road traffic-air quality study: a review DOI

Zhanxia Du,

Hanbing Li, Sha Chen

и другие.

Atmospheric Environment, Год журнала: 2025, Номер unknown, С. 121054 - 121054

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Quantifying vehicle restriction related PM2.5 reduction using field observations in an isolated urban basin DOI Creative Commons
Yumin Guo, Pengfei Tian, Mengqi Li

и другие.

Environmental Research Letters, Год журнала: 2024, Номер 19(2), С. 024053 - 024053

Опубликована: Фев. 1, 2024

Abstract Vehicle (related particulate matter) emissions, including primary vehicle secondary nitrate, and road dust, have become an important source of fine matter (PM 2.5 ) in many cities across the world. The relationship between emissions PM during restrictions has not yet been revealed using field observational data. To address this issue, a three-month campaign on physical chemical characteristics at hourly resolution was conducted Lanzhou, urban basin with semi-arid climate. Lanzhou municipal government implemented more strict restriction measure latter part period. concentration nitrogen oxides (NO x decreased by 15.6% 10.6%, respectively daily traffic fluxes 11.8% due to measure. emission reduction led decrease 2.43 μ g·m −3 , dust. contribution 9.0% based results derived from positive matrix factorization model. sources other than increased 0.2 . Combining all evidence observations, is almost equal observed A further extrapolation that (2.32 μg·m ). This study clearly quantifies related observations. provide scientific support for implementation effective measures.

Язык: Английский

Процитировано

2
Single particle mass spectral signatures from on-road and non-road vehicle exhaust particles and their application in refined source apportionment using deep learning DOI
Yongjiang Xu, Zaihua Wang,

Chenglei Pei

и другие.

The Science of The Total Environment, Год журнала: 2024, Номер 930, С. 172822 - 172822

Опубликована: Апрель 28, 2024

Язык: Английский

Процитировано

1
Machine learning exploring the chemical compositions characteristics and sources of PM2.5 from reduced on-road activity DOI

Dan Liao,

Youwei Hong,

Huabin Huang

и другие.

Atmospheric Pollution Research, Год журнала: 2024, Номер 15(11), С. 102265 - 102265

Опубликована: Июль 24, 2024

Язык: Английский

Процитировано

1
Natural gas-fueled HCCI engine performance and emission analysis and comparison with SI and spark-assisted operations DOI
Erdal Tunçer, Tarkan Sandalcı, Özgün Balcı

и другие.

Australian Journal of Mechanical Engineering, Год журнала: 2024, Номер unknown, С. 1 - 12

Опубликована: Сен. 18, 2024

Язык: Английский

Процитировано

1
Review of Urban Access Regulations from the Sustainability Viewpoint DOI Creative Commons
Yunpeng Ma, Ferenc Mészáros

Urban Science, Год журнала: 2024, Номер 8(2), С. 29 - 29

Опубликована: Апрель 2, 2024

This article reviewed the urban vehicle access control policies derived from disparate spatiotemporal dimensions that aim to eliminate negative externalities of traffic caused by urbanization. Urban regulations are important tools often required achieve sustainable mobility vision cities. Employing a systematic literature review methodology, this summarized and analyzed various enlighten policymakers future scientific research. The results indicate combinations multiple-dimensional restriction (including inter-policy intra-policy) have more significant effects than implementing single policy. Classified according their objectives, were discussed in terms benefits limitations. authors inspired propose describe five paradoxes policies.

Язык: Английский

Процитировано

0
Research on Emission and Traffic Efficiency of Twice Startup at Left-Turn Waiting Area DOI
Yang Shao, Tianyue Hou,

Yuzhu CHENG

и другие.

Опубликована: Янв. 1, 2023

Urban intersections are the key nodes in whole city transportation system, and left-turn vehicle (LV) is core at intersections. The traffic light one of main control measures for through vehicles separately. In meantime, waiting area (LWA) a common optimization to improve capacity single timing cycle. LV will enter LWA when turns green switch. From stop bar end LWA, would startup twice reality, which cause more emissions reduce efficiency. Optimize phase light, be permitted into nearly traffic. reach conflict point opposite direction (TV) TV just passes point. once accelerate continuously during process, eliminate second LV. Our study proposes formulas calculate duration signal adjustment, models simulates plan before after improvement by using VISSIM software. results show that optimized method can fuel consumption significantly efficiency slightly. Which has considerable significance air quality management sustainable development.

Язык: Английский

Процитировано

0
Single Particle Mass Spectral Signatures from On-Road and Non-Road Vehicle Exhaust Particles and Their Application in Refined Source Apportionment Using Deep Learning DOI
Yongjiang Xu, Zaihua Wang, Shiping Li

и другие.

Опубликована: Янв. 1, 2023

With advances in vehicle emission control technology, updating source profiles to meet the current requirement of apportionment has become increasingly crucial. In this study, on-road and non-road particles were collected, then chemical composition individual particle was analyzed using single aerosol mass spectrometry. The data grouped an adaptive resonance theory neural network, identify signatures establish a spectral database mobile sources. addition, deep learning-based model (DeepAerosolClassifier) for classifying established. objective accomplish apportionment. During training process, achieved accuracy 98.49% on validation set 93.36% test set. Regarding interpretation, ideal spectra generated verify its accurate recognition characteristic patterns spectra. practical application, used perform hourly at three specific field monitoring sites. effectiveness measurement validated by combining traffic flow spatial information with results. Compared other machine learning methods, our highly automated while eliminating need feature selection enables end-to-end operation. Thus, future, it can be applied refined online particulate matter.

Язык: Английский

Процитировано

0