New Particle Formation Events Detection with Deep Learning
Preprint
- 13 September 2021
- preprint
- Published by Copernicus GmbH in EGUsphere
- Vol. 2021, 1-21
Abstract
Atmospheric new particle formation (NPF) is an important source of climate-relevant aerosol particles which has been observed at many locations globally. To study this phenomenon, the first step is to identify whether an NPF event occurs or not on a given day. In practice, NPF event identification is performed visually by classifying the NPF event or non-event days from the particle number size distribution surface plots. Unfortunately, this day-by-day visual classification is time-consuming, labor-intensive, and the identification process renders subjective results. To detect NPF events automatically, we regard the visual signature (banana shape) which has been observed all over the world in NPF surface plots as a special kind of object, and a deep learning model called Mask R-CNN is applied to localize the spatial layouts of NPF events in their surface plots. Utilizing only 358 human-annotated masks on data from the Station for Measuring Ecosystem and Atmospheric Relations (SMEAR) II station (Hyytiälä, Finland), the Mask R-CNN model was successfully generalized for three SMEAR stations in Finland and the San Pietro Capofiume (SPC) station in Italy. In addition to the detection of NPF events (especially the strongest events), the presented method can determine the growth rates, start times, and end times for NPF events automatically. The automatically determined growth rates agree with the growth rates determined by the maximum concentration and mode fitting methods. The statistical results valid the potential of applying the proposed method on different sites, which will improve the automatic level for NPF events detection and analysis. Furthermore, the proposed automatic NPF event analysis method provides more consistent results compared with human-made analysis, especially when long-term data series are analyzed and statistically comparisons between different sites are needed for event characteristics such as the start and end times, thereby saving time and effort of scientists studying NPF events.Keywords
All Related Versions
- Published version: Atmospheric Chemistry and Physics, 22 (2), 1293.
Funding Information
- Business Finland (UIA03-240)
- Research Council of Finland (337549, 302958, 311932)
This publication has 39 references indexed in Scilit:
- The Synergistic Role of Sulfuric Acid, Bases, and Oxidized Organics Governing New‐Particle Formation in BeijingGeophysical Research Letters, 2021
- New Particle Formation in the Atmosphere: From Molecular Clusters to Global ClimateJournal of Geophysical Research: Atmospheres, 2019
- Handcrafted vs. non-handcrafted features for computer vision classificationPattern Recognition, 2017
- SSD: Single Shot MultiBox Detector2016
- Identity Mappings in Deep Residual Networks2016
- Microsoft COCO: Common Objects in Context2014
- Station for Measuring Ecosystem-Atmosphere Relations: SMEAR2012
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- Formation and growth rates of ultrafine atmospheric particles: a review of observationsJournal of Aerosol Science, 2004
- Physical characterization of aerosol particles during nucleation eventsTellus B: Chemical and Physical Meteorology, 2001