Development of Land Use Regression Models for Predicting Exposure to Particulate Matters and Nitrogen Oxides in an Area with Low Air Pollutant Concentrations

Spatial analysis studies have included the application of land use regression models (LURs) for health and air quality assessments. Recent LUR studies have collected nitrogen dioxide (NO2) and volatile organic compounds (VOCs) using passive samplers at urban air monitoring networks in El Paso and Dallas, TX, Detroit, MI, and Cleveland, OH to assess spatial variability and source influences. LURs were successfully developed to estimate pollutant concentrations throughout the study areas. Comparisons of development and predictive capabilities of LURs from these four cities are presented to address this issue of uniform application of LURs across study areas. Traffic and other urban variables were important predictors in the LURs although city-specific influences (such as border crossings) were also important. In addition, transferability of variables or LURs from one city to another may be problematic due to intercity differences and data availability or comparability. Thus, developing common predictors in future LURs may be difficult.

Download Full-text

Land use regression modelling of ambient air pollutants in Hong Kong

10.5194/egusphere-egu2020-12648 ◽

2020 ◽

Author(s):

Zhiyuan Li ◽

Steve Hung Lam Yim ◽

Kin-Fai Ho

Keyword(s):

Land Use ◽

Hong Kong ◽

Air Quality ◽

Air Pollutants ◽

Ambient Air ◽

Air Pollutant ◽

High Rise ◽

Pollutant Concentrations ◽

Air Quality Measurements ◽

Air Pollutant Concentrations

<p>Land use regression (LUR) models estimate air pollutant concentrations for areas without air quality measurements, which provides valuable information for exposure assessment and epidemiological studies. In the present study, we developed LUR models for ambient air pollutants in Hong Kong, China, a typical high-density and high-rise city. Air quality measurements at sixteen air quality monitoring stations, operated by the Hong Kong Environmental Protection Department, were collected. Moreover, five categories of predictor variables, including population distribution, traffic emissions, land use variables, urban/building morphology, and meteorological parameters, were employed to establish the LUR models of various air pollutants. Then the spatial distribution of air pollutant concentrations at 1 km &#215; 1 km grid cells were plotted. Taking fine particle (PM2.5) as an example, the developed LUR model explained 89% of variability of PM2.5 concentrations, with a leave-one-out-cross-validation R2 of 0.64. LUR modelling results for other air pollutants will be presented. In addition, further improvements on the development of LUR models will be discussed. This study can help to assess long-term exposures to air pollutants for high-density and high-rise urban areas like Hong Kong.</p>

Download Full-text

Using Measurements of Nitrogen Oxides from a Fixed Site and a Mobile Platform to Develop Spatially- and Temporally-Resolved Land Use Regression Models

ISEE Conference Abstracts ◽

10.1289/isesisee.2018.o03.03.03 ◽

2018 ◽

Vol 2018 (1) ◽

Author(s):

Laura Corlin ◽

Matthew C Simon ◽

Jonathan Levy ◽

Mark Woodin ◽

David Gute ◽

...

Keyword(s):

Land Use ◽

Nitrogen Oxides ◽

Regression Models ◽

Mobile Platform ◽

Land Use Regression

Download Full-text

Improving Correlations between Land Use and Air Pollutant Concentrations Using Wavelet Analysis: Insights from a Low-cost Sensor Network

Aerosol and Air Quality Research ◽

10.4209/aaqr.2019.03.0124 ◽

2020 ◽

Vol 20 (2) ◽

pp. 314-328

Author(s):

Naomi Zimmerman ◽

Hugh Z. Li ◽

Aja Ellis ◽

Aliaksei Hauryliuk ◽

Ellis S. Robinson ◽

...

Keyword(s):

Land Use ◽

Wavelet Analysis ◽

Sensor Network ◽

Low Cost ◽

Air Pollutant ◽

Pollutant Concentrations ◽

Air Pollutant Concentrations

Download Full-text

Machine-learning models to replicate large-eddy simulations of air pollutant concentrations along boulevard-type streets

Geoscientific Model Development ◽

10.5194/gmd-14-7411-2021 ◽

2021 ◽

Vol 14 (12) ◽

pp. 7411-7424

Author(s):

Moritz Lange ◽

Henri Suominen ◽

Mona Kurppa ◽

Leena Järvi ◽

Emilia Oikarinen ◽

...

Keyword(s):

Regression Models ◽

Concept Drift ◽

Air Pollutant ◽

Point Of View ◽

Large Eddy Simulations ◽

Pollutant Concentrations ◽

Testing Dataset ◽

Large Eddy ◽

Air Pollutant Concentrations ◽

Log Linear

Abstract. Running large-eddy simulations (LESs) can be burdensome and computationally too expensive from the application point of view, for example, to support urban planning. In this study, regression models are used to replicate modelled air pollutant concentrations from LES in urban boulevards. We study the performance of regression models and discuss how to detect situations where the models are applied outside their training domain and their outputs cannot be trusted. Regression models from 10 different model families are trained and a cross-validation methodology is used to evaluate their performance and to find the best set of features needed to reproduce the LES outputs. We also test the regression models on an independent testing dataset. Our results suggest that in general, log-linear regression gives the best and most robust performance on new independent data. It clearly outperforms the dummy model which would predict constant concentrations for all locations (multiplicative minimum RMSE (mRMSE) of 0.76 vs. 1.78 of the dummy model). Furthermore, we demonstrate that it is possible to detect concept drift, i.e. situations where the model is applied outside its training domain and a new LES run may be necessary to obtain reliable results. Regression models can be used to replace LES simulations in estimating air pollutant concentrations, unless higher accuracy is needed. In order to have reliable results, it is however important to do the model and feature selection carefully to avoid overfitting and to use methods to detect the concept drift.

Download Full-text

Agreement of Land Use Regression Models with Personal Exposure Measurements of Particulate Matter and Nitrogen Oxides Air Pollution

Environmental Science & Technology ◽

10.1021/es400920a ◽

2013 ◽

pp. 130712144458004 ◽

Cited By ~ 6

Author(s):

Denise Montagne ◽

Gerard Hoek ◽

Mark Nieuwenhuijsen ◽

Timo Lanki ◽

Arto Pennanen ◽

...

Keyword(s):

Land Use ◽

Air Pollution ◽

Particulate Matter ◽

Nitrogen Oxides ◽

Regression Models ◽

Personal Exposure ◽

Land Use Regression ◽

Exposure Measurements

Download Full-text

Spatial-Temporal Analysis of Air Pollutant Concentrations in Relation to Land Use and School Environment

Alinteri Journal of Agricultural Sciences ◽

10.47059/alinteri/v36i1/ajas21080 ◽

2021 ◽

Vol 36 (1) ◽

pp. 568-582

Author(s):

Healice Julit ◽

Nafisah Khalid ◽

Abdul Rauf Abdul Rasam ◽

Mohamad Hezri Razali ◽

Maisarah Abdul Halim

Keyword(s):

Land Use ◽

Air Pollution ◽

School Environment ◽

Strong Relationship ◽

Temporal Analysis ◽

Air Pollutant ◽

Pollutant Concentration ◽

Motor Vehicles ◽

Pollutant Concentrations ◽

Air Pollutant Concentrations

Excessive exposure schoolchildren to air pollution can lead to long-lasting health problems, allergies and respiratory disease. It is well known that the major factors contributing to increase of air pollution are motor vehicles and industries. Thus, it is important to analyze the spatial temporal air pollutant concentrations and its relation with school location as the location of schools and its surrounding can increase their exposure. In this study, six schools in Johor were selected and the land use surrounding the schools were updated using ArcGIS. The Inverse Distance Weighting (IDW) interpolation technique was used to identify which schools’ area in Johor has a higher range of air pollutant concentration. There are four air pollution parameters obtained from the Department of Environment (DOE) which are PM2.5, CO, O3 and SO2. Hourly air pollutant concentration reading was obtained from the DOE in order to analyze air pollutant concentration during school period. The results obtained from the IDW technique showed that Sekolah Menengah Pasir Gudang (2) located in Pasir Gudang, Malaysia has reached a very unhealthy and hazardous level as compared to other schools in Johor. On the other hand, Sekolah Menengah Kebangsaan Tanjung Pengelih, Pengerang, Malaysia showed good to unhealthy range as compared to other schools in Johor. The spatial autocorrelation tool was used to analyze the relationship between the air pollution concentration and the school’s location in Johor. The results showed that the Moran’s Indices is positive showing a strong relationship that is clustering. It can be stated that there is a relationship between air pollutant concentrations with the school locations.

Download Full-text

Machine learning models to replicate large-eddy simulations of air pollutant concentrations along boulevard-type streets

10.5194/gmd-2020-200 ◽

2020 ◽

Author(s):

Moritz Lange ◽

Henri Suominen ◽

Mona Kurppa ◽

Leena Järvi ◽

Emilia Oikarinen ◽

...

Keyword(s):

Regression Models ◽

Concept Drift ◽

Air Pollutant ◽

Point Of View ◽

Large Eddy Simulations ◽

Pollutant Concentrations ◽

Testing Dataset ◽

Large Eddy ◽

Air Pollutant Concentrations ◽

Log Linear

Abstract. Running large-eddy simulations (LES) can be burdensome and computationally too expensive from the application point-of-view for example to support urban planning. In this study, regression models are used to replicate modelled air pollutant concentrations from LES in urban boulevards. We study the performance of regression models and discuss how to detect situations where the models are applied outside their training domain and their outputs cannot be trusted. Regression models from 10 different model families are trained and a cross-validation methodology is used to evaluate their performance and to find the best set of features needed to reproduce the LES outputs. We also test the regression models on an independent testing dataset. Our results suggest that in general, log-linear regression gives the best and most robust performance on new independent data. It clearly outperforms the dummy model which would predict constant concentrations for all locations (mRMSE of 0.76 vs 1.78 of the dummy model). Furthermore, we demonstrate that it is possible to detect concept drift, i.e., situations where the model is applied outside its training domain and a new LES run may be necessary to obtain reliable results. Regression models can be used to replace LES simulations in estimating air pollutant concentrations, unless higher accuracy is needed. In order to have reliable results, it is however important to do the model and feature selection carefully to avoid over-fitting and to use methods to detect the concept drift.

Download Full-text