Personal exposure to various size fractions of ambient particulate matter during the heating and non-heating periods using mobile monitoring approach: A case study in Augsburg, Germany

Liu, Xiansheng; Hadiatullah, Hadiatullah; Khedr, Mohamed; Zhang, Xun; Schnelle-Kreis, Jürgen; Zimmermann, Ralf; Adam, Thomas

doi:10.1016/j.apr.2022.101483

Cited by 8 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mobile monitoring aerosol data used in this study are supplied by our previous studies in the urban of Augsburg, , German-Czech border villages, and campaigns in Neubiberg (performed during 04-12/2022) and Warnemünde (performed during 13-16/09/2022). The average concentrations of PM metrics from the selected walks in downtown Augsburg, Neubiberg, Warnemünde and villages (Bayerisch Eisenstein and Zelezna Ruda) are shown in Table .…”

Section: Resultsmentioning

confidence: 99%

“…It was discovered that the concentrations of PM 2.5 and PM 10 in all areas were meeting the 24 h average of the World Health Organization (WHO) air quality guidelines (AQG) of 15 and 45 μg/m 3 , respectively . Furthermore, a detailed analysis of spatiotemporal variability of aerosol in urban and village has been provided in our previous studies. ,, …”

Section: Resultsmentioning

confidence: 99%

“…The instruments were placed in waterproof aluminum boxes mounted on the trolleys, and omnidirectional sample inlets were positioned at a height of approximately 1.5 m, corresponding to the breathing zone of adults. Additional detailed information about the instrumentation has been provided in the literature. , …”

Section: Methodsmentioning

confidence: 99%

“…In Augsburg (48.37N, 10.90E), the study was conducted within the city center, covering a fixed walking path of approximately 15 km in length, passing through various types of land use to ensure the representation of different microenvironments (e.g., park, central business district, and traffic) (Figure S1a). , The average walking time of one route was about 4 h. Neubiberg (48.06N, 11.66E), located about 12 km south of the city center on the outskirts of Munich, was covered by a 5 km long monitoring route passing through densely populated areas such as transport stops, residential areas, parks, metro stations, shops, and restaurants (Figure S1b). Warnemünde (54.18N, 12.08E), harbor area of Rostock, was covered by a mobile measurement route (5 km) passing through the town’s densely populated areas such as churches, train stations, stores, and restaurants (Figure S1c).…”

Section: Methodsmentioning

confidence: 99%

“…Additional detailed information about the instrumentation has been provided in the literature. 30,31 Prior to each measurement campaign, instrument preparation was conducted in the laboratory, including zero calibration checks, replacement of the MA200 filter strip, battery and memory checks, and time synchronization of all instruments. Flow measurements were performed by using a factory calibrated flow meter (4043 H, TSI, USA).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery

Liu,

Zhang,

Wang

et al. 2024

Environ. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

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 PM 10 , 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.

show abstract

Section: Resultsmentioning

confidence: 99%