PuSH - Publication Server of Helmholtz Zentrum München: High-precision microscale particulate matter prediction in diverse environments using a long short-term memory neural network and street view imagery.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Liu, X.* ; Zhang, X.* ; Wang, R.* ; Liu, Y.* ; Hadiatullah, H.* ; Xu, Y.* ; Wang, T.* ; Bendl, J.* ; Adam, T. ; Schnelle-Kreis, J. ; Querol, X.*

High-precision microscale particulate matter prediction in diverse environments using a long short-term memory neural network and street view imagery.

Environ. Sci. Technol. 58, 3869-3882 (2024)

Publ. Version/Full Text

DOI

PMC

	Open Access Gold (Paid Option)

Abstract
Metrics
Extra information

In this study, we propose a novel long short-term memory (LSTM) neural network model that leverages color features (HSV: hue, saturation, value) extracted from street images to estimate air quality with particulate matter (PM) in four typical European environments: urban, suburban, villages, and the harbor. To evaluate its performance, we utilize concentration data for eight parameters of ambient PM (PM_1.0, PM_2.5, and PM₁₀, particle number concentration, lung-deposited surface area, equivalent mass concentrations of ultraviolet PM, black carbon, and brown carbon) collected from a mobile monitoring platform during the nonheating season in downtown Augsburg, Germany, along with synchronized street view images. Experimental comparisons were conducted between the LSTM model and other deep learning models (recurrent neural network and gated recurrent unit). The results clearly demonstrate a better performance of the LSTM model compared with other statistically based models. The LSTM-HSV model achieved impressive interpretability rates above 80%, for the eight PM metrics mentioned above, indicating the expected performance of the proposed model. Moreover, the successful application of the LSTM-HSV model in other seasons of Augsburg city and various environments (suburbs, villages, and harbor cities) demonstrates its satisfactory generalization capabilities in both temporal and spatial dimensions. The successful application of the LSTM-HSV model underscores its potential as a versatile tool for the estimation of air pollution after presampling of the studied area, with broad implications for urban planning and public health initiatives.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Lstm ; Pm Metrics ; Air Quality ; Deep Learning ; Exposure Assessment Models; Black Carbon; Land-use; Dispersion Model; Air; Pollution; Pollutants; Augsburg; Nexus

ISSN (print) / ISBN 0013-936X

e-ISSN 1520-5851

Journal Environmental Science & Technology

Quellenangaben Volume: 58, Issue: 8, Pages: 3869-3882

Publisher ACS

Publishing Place Washington, DC

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Cooperation Group Comprehensive Molecular Analytics (CMA)

Grants Germany Federal Ministry of Transport and Digital Infrastructure (BMVI)
European Union-NextGenerationEU
Dtec.b-Digitalization and Technology Research Center of the Bundeswehr
RI-URBANS project (Research Infrastructures Services Reinforcing Air Quality Monitoring Capacities in European Urban & Industrial Areas, European Union's Horizon 2020 research and innovation program, Green Deal, European Commission)
Project of Natural Science Foundation of Xinjiang Uygur Autonomous Region
Chunhui Project Foundation of the Education Department of China
State Key Laboratory of Resources and Environmental Information System
National Natural Science Foundation of China