Identification of New Particle Formation Events Using a You Only Look Once (YOLO) Deep Learning Algorithm

Atmospheric new particle formation (NPF) events, which involve the formation and growth of molecular clusters, affect air quality, weather, climate, and human health. Traditional NPF event classification schemes in the literature, primarily through visual inspection of particle number size distributions, are subjective, time-consuming, and laborious. Here, we introduced a fast object detection deep learning algorithm, You Only Look Once (YOLO), for the first time to detect NPF events. We used more than one year of asynchronous particle number size distribution data from 20 diverse geographical locations globally. The YOLO algorithm was first trained and validated using a small subset of manually annotated 252 NPF events and 195 non-events (approximately 25 images from each measurement site). The trained YOLO algorithm was then evaluated to detect NPF events against the remaining 6462 observation days across all measurement sites. The performance metrics of the trained YOLO algorithm revealed high precision and accuracy in detecting NPF events. The model accuracy for each measurement site was calculated by taking the ratio of the total number of NPF events detected by the trained YOLO algorithm at a confidence score (CoS) > 0.1 to the total number of visually identified NPF events. Considering all measurement sites, the trained YOLO algorithm’s accuracy (in fraction) for detecting NPF events ranged from 0.74 to 0.97 at a CoS > 0.1, although the accuracy decreased with increasing threshold CoS. This work underscores the efficacy and robustness of the YOLO algorithm and demonstrates its applicability in accurately detecting NPF events in diverse environmental conditions worldwide.

Authors

Institutions

Publication Details

Journal
ACS ES&T Air
Published
2025-06-24
DOI
https://doi.org/10.1021/acsestair.5c00021
Primary Topic
Atmospheric chemistry and aerosols
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Identification of New Particle Formation Events Using a You Only Look Once (YOLO) Deep Learning Algorithm

Lauri Laakso, Chandan Sarangi, Shan‐Hu Lee, Pieter G. van Zyl et al.
ACS ES&T Air
Atmospheric chemistry and aerosols
article

Identification of New Particle Formation Events Using a You Only Look Once (YOLO) Deep Learning Algorithm

Lauri Laakso, Chandan Sarangi, Shan‐Hu Lee, Pieter G. van Zyl, N. Mihalopoulos, Michael Pikridas, Roy M. Harrison, Vijay Kumar Soni, Kerneels Jaars, Antti Hyvärinen, Tuomo Nieminen, David C. S. Beddows, Tuija Jokinen, Li‐Hao Young, Rajat Bhandari, G. Pandithurai, Imre Salma, Máté Vörösmarty, Eija Asmi, Mathew Sebastian, Vijay P. Kanawade, Ville Vakkari, Johan P. Beukes, Zachary Watson, Jean Sciare, Nikos Kalivitis, Rakesh K. Hooda, Sachchidanand Singh
article en

Abstract

Atmospheric new particle formation (NPF) events, which involve the formation and growth of molecular clusters, affect air quality, weather, climate, and human health. Traditional NPF event classification schemes in the literature, primarily through visual inspection of particle number size distributions, are subjective, time-consuming, and laborious. Here, we introduced a fast object detection deep learning algorithm, You Only Look Once (YOLO), for the first time to detect NPF events. We used more than one year of asynchronous particle number size distribution data from 20 diverse geographical locations globally. The YOLO algorithm was first trained and validated using a small subset of manually annotated 252 NPF events and 195 non-events (approximately 25 images from each measurement site). The trained YOLO algorithm was then evaluated to detect NPF events against the remaining 6462 observation days across all measurement sites. The performance metrics of the trained YOLO algorithm revealed high precision and accuracy in detecting NPF events. The model accuracy for each measurement site was calculated by taking the ratio of the total number of NPF events detected by the trained YOLO algorithm at a confidence score (CoS) > 0.1 to the total number of visually identified NPF events. Considering all measurement sites, the trained YOLO algorithm’s accuracy (in fraction) for detecting NPF events ranged from 0.74 to 0.97 at a CoS > 0.1, although the accuracy decreased with increasing threshold CoS. This work underscores the efficacy and robustness of the YOLO algorithm and demonstrates its applicability in accurately detecting NPF events in diverse environmental conditions worldwide.

ACS ES&T AirVol. 2(7)
Eötvös Loránd University (HU), Finnish Meteorological Institute (FI), Indian Institute of Tropical Meteorology (IN), University of Helsinki (FI), National Physical Laboratory (GB), University of Crete (GR), Cyprus Institute (CY), King Abdulaziz University (SA), Indian Institute of Technology Madras (IN), North-West University (ZA), India Meteorological Department (IN), University of Hyderabad (IN), College of Occupational Safety and Health (HR), National Observatory of Athens (GR), University of Birmingham (GB), University of Alabama in Huntsville (US)
European Commission, Department of Science and Technology, Ministry of Science and Technology, India, Academy of Finland, Ministry of Environment, University of Hyderabad, Nemzeti Kutatási Fejlesztési és Innovációs Hivatal, National Science and Technology Council, HORIZON EUROPE Framework Programme, Science and Engineering Research Board
Openalex Percentile: Top 81%
Atmospheric chemistry and aerosols
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.