Estimating the Near-Ground PM2.5 Concentration over China Based on the CapsNet Model during 2018–2020

Fine particulate matter (PM2.5) threatens human health and the natural environment. Estimating the near-ground PM2.5 concentrations accurately is of great significance in air quality research. Statistical and deep-learning models are widely used for estimating PM2.5 concentration based on remotely s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Remote sensing (Basel, Switzerland) Jg. 14; H. 3; S. 623
Hauptverfasser: Zeng, Qiaolin, Xie, Tianshou, Zhu, Songyan, Fan, Meng, Chen, Liangfu, Tian, Yu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.02.2022
Schlagworte:
Accuracy
aerosol optical depth
Aerosols
air pollutants
Air pollution
Air quality
Algorithms
Artificial neural networks
Atmospheric models
CapsNet
China
Coastal zone
Cognition & reasoning
Cold season
Contaminants
data collection
Deep learning
Depth indicators
DNN
dynamic routing algorithm
Estimation
human health
Latitude
Longitude
Machine learning
Mathematical models
Meteorological parameters
Model accuracy
Natural environment
Neural networks
Neurons
Normalized difference vegetative index
Optical analysis
Optical thickness
Particulate matter
particulates
PM2.5 concentration
Remote sensing
Root-mean-square errors
Seasons
Statistical analysis
China
ISSN:2072-4292, 2072-4292
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fine particulate matter (PM2.5) threatens human health and the natural environment. Estimating the near-ground PM2.5 concentrations accurately is of great significance in air quality research. Statistical and deep-learning models are widely used for estimating PM2.5 concentration based on remotely sensed aerosol optical depth (AOD) products. Deep-learning models can effectively express the nonlinear relationship between AOD, parameters, and PM2.5. This study proposed a capsule network model (CapsNet) to address the spatial differences in PM2.5 concentration distribution by introducing a capsule structure and dynamic routing algorithm for the first time, which integrates AOD, surface PM2.5 measurements, and auxiliary variables (e.g., normalized difference vegetation index (NDVI) and meteorological parameters). Moreover, we examined the longitude and latitude of pixels as input parameters to reflect spatial location information, and the results showed that the introduction of longitude (LON) and latitude (LAT) parameters improved the model fitting accuracy. The coefficient of determination (R2) increased by 0.05 ± 0.01, and the root mean square error (RMSE), mean relative error (MRE), and mean absolute error (MAE) decreased by 3.30 ± 1.0 μg/m3, 8 ± 3%, and 1.40 ± 0.2 μg/m3, respectively. To verify the accuracy of our proposed CapsNet, the deep neural network (DNN) model was executed. The results indicated that the R2 values of the validation dataset using CapsNet improved by 4 ± 2%, and RMSE, MRE, and MAE decreased by 1.50 ± 0.4 μg/m3, ~5%, and 0.60 ± 0.2 μg/m3, respectively. Finally, the effects of seasons and spatial region on the fitting accuracy were examined separately from 2018 to 2020. With respect to seasons, the model performed more robustly in the cold season. In terms of spatial region, the R2 values exceeded 0.9 in the central-eastern region, while the accuracy was lower in the western and coastal regions. This study proposed the CapsNet model to estimate PM2.5 concentrations for the first time and achieved good accuracy, which could be used for the estimation of other air contaminants.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14030623