Analysis of the Factors Influencing PM2.5 in Korea : Focusing on Seasonal Factors

박순애,; 신현재,

doi:10.15301/jepa.2017.25.1.227

Cited by 29 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such data are not used in this study due to limitations associated with the control of external factors, including weather conditions. Several studies have found a strong relationship between the concentrations of air pollution and climatic variables, such as wind direction and speed [20,[43][44][45][46][47]. In particular, Korea is heavily affected by pollutants from Northeast Asian regions due to its geographical characteristics and westerlies.…”

Section: Data and Variablementioning

confidence: 99%

Spatial Relationships between Urban Structures and Air Pollution in Korea

Jung

Park

Kim³

2019

Sustainability

View full text Add to dashboard Cite

Urban structures facilitate human activities and interactions but are also a main source of air pollutants; hence, investigating the relationship between urban structures and air pollution is crucial. The lack of an acceptable general model poses significant challenges to investigations on the underlying mechanisms, and this gap fuels our motivation to analyze the relationships between urban structures and the emissions of four air pollutants, including nitrogen oxides, sulfur oxides, and two types of particulate matter, in Korea. We first conduct exploratory data analysis to detect the global and local spatial dependencies of air pollutants and apply Bayesian spatial regression models to examine the spatial relationship between each air pollutant and urban structure covariates. In particular, we use population, commercial area, industrial area, park area, road length, total land surface, and gross regional domestic product per person as spatial covariates of interest. Except for park area and road length, most covariates have significant positive relationships with air pollutants ranging from 0 to 1, which indicates that urbanization does not result in a one-to-one negative influence on air pollution. Findings suggest that the government should consider the degree of urban structures and air pollutants by region to achieve sustainable development.

show abstract

Section: Data and Variablementioning

confidence: 99%

Spatial Relationships between Urban Structures and Air Pollution in Korea

Jung

Park

Kim³

2019

Sustainability

View full text Add to dashboard Cite

show abstract

“…For instance, fine dust accumulated by the lower tropospheric high pressure can cause dust pollution in Seoul for several days, while an anomalous low pressure system formed in the Okhotsk Sea and East Sea, blocks the movement of upstream high pressure. Park et al [7] confirmed that the fine dust concentration on the Shandong Peninsula together with a westerly wind have a positive correlation with fine dust concentration in Korea.…”

Section: Introductionmentioning

confidence: 97%

The Effects of Spring and Winter Blocking on PM10 Concentration in Korea

Yun

Yoo

2019

Atmosphere

View full text Add to dashboard Cite

Atmospheric blocking is known to be related to locally developed abnormal climate of the Korean Peninsula, such as heat and cold waves. However, little attention has been devoted to the effects of blocking on the fine dust concentration over Korea. In this study, we analyze the connection between the monthly frequency of blocking occurrence and high particulate matter smaller than 10 μm in diameter (PM10) concentration events in Korea. Our analyses are limited to winter (DJF) and spring (MAM) when both the blocking and high PM10 events tend to take place most frequently. During winter, significant and positive correlations are found in the North Pacific, while significantly negative values are seen over Ural-Siberia. A high PM10 concentration tends to be accompanied by negative (positive) pressure anomalies over Siberia (North Pacific). However, while examining atmospheric fields associated with the high PM10 events, we find that the high PM10 events show two different types of atmospheric fields depending on the strength of wind speed over Korea. When the local wind speed over Korea is weaker than normal, the connection with the North Pacific blocking is strengthened, whereas, the connection with the Ural-Siberia blocking is enhanced when the wind speed is stronger than normal. However, to increase the occurrence of the high PM10 events, both types feature a strong meridional pressure gradient caused by a high pressure system forming over Siberia. This is accompanied by a strong upper tropospheric zonal wind from China and Mongolia to Korea.

show abstract

“…in Korea, and new deep learning models have been developed to show high performance in air quality prediction [9,10]. However, foreign factors should also be considered in predicting PM 2.5 concentration in Korea, as the concentration of PM 2.5 in the Shandong region of China is also found to affect Korea's PM 2.5 concentration [11]. However, as China's past PM 2.5 concentration data are composed of daily data, Korea's data should also be organized on a daily basis for deep learning PM 2.5 prediction.…”

Section: Introductionmentioning

confidence: 99%

Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5

Choi

Kim

2021

Sustainability

View full text Add to dashboard Cite

Fine particulate matter (PM2.5) is one of the main air pollution problems that occur in major cities around the world. A country’s PM2.5 can be affected not only by country factors but also by the neighboring country’s air quality factors. Therefore, forecasting PM2.5 requires collecting data from outside the country as well as from within which is necessary for policies and plans. The data set of many variables with a relatively small number of observations can cause a dimensionality problem and limit the performance of the deep learning model. This study used daily data for five years in predicting PM2.5 concentrations in eight Korean cities through deep learning models. PM2.5 data of China were collected and used as input variables to solve the dimensionality problem using principal components analysis (PCA). The deep learning models used were a recurrent neural network (RNN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM). The performance of the models with and without PCA was compared using root-mean-square error (RMSE) and mean absolute error (MAE). As a result, the application of PCA in LSTM and BiLSTM, excluding the RNN, showed better performance: decreases of up to 16.6% and 33.3% in RMSE and MAE values. The results indicated that applying PCA in deep learning time series prediction can contribute to practical performance improvements, even with a small number of observations. It also provides a more accurate basis for the establishment of PM2.5 reduction policy in the country.

show abstract

Analysis of the Factors Influencing PM2.5 in Korea : Focusing on Seasonal Factors

Cited by 29 publications

References 0 publications

Spatial Relationships between Urban Structures and Air Pollution in Korea

Spatial Relationships between Urban Structures and Air Pollution in Korea

The Effects of Spring and Winter Blocking on PM10 Concentration in Korea

Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5

Contact Info

Product

Resources

About