• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2008.10a
• /
• pp.367-368
• /
• 2008

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.5
• /
• pp.722-727
• /
• 2018

Until now, the study of fine dust has been divided into prediction, analysis and measurement, mainly in the field of atmospheric environment. Fine dust is caused by various causes such as atmospheric quality factor, meteorological factor and emission. It was determined that it was a priority to analyze the correlation of how much each element affects fine dust, and it was experimented. This correlation analysis was done using IBM SPSS tool using air quality factor and meteorological factor data obtained from Korea Meteorological Administration and Air Korea. As a result, the influence of air quality factors and meteorological factors on the fine dust level was more clearly understood. In this paper, we present experimental results as correlation analysis and pearson coefficient for more precise analysis between PM10 values and affected factors.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.130-145
• /
• 2021

As part of the Smart Seoul policy, the importance of using big urban data is being highlighted. Furthermore interest in the impact of transportation-related urban environmental factors such as PM10 and noise on citizen's quality of life is steadily increasing. This study established the integrated DB by matching IoT big data with transportation data, including traffic volume and speed in the microscopic Spatio-temporal scope. This data analyzed the impact of a spatial unit in the road-effect zone on environmental risk level. In addition, spatial units with similar characteristics of road traffic and environmental factors were clustered. The results of this study can provide the basis for systematically establishing environmental risk management of urban spatial units such as PM10 or PM2.5 hot-spot and noise hot-spot.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1881-1890
• /
• 2021

Particulate matter (PM) affects the human, ecosystems, and weather. Motorized vehicles and combustion generate fine particulate matter (PM_2.5), which can contain toxic substances and, therefore, requires systematic management. Consequently, it is important to monitor and predict PM_2.5 concentrations, especially in large cities with dense populations and infrastructures. This study aimed to predict PM_2.5 concentrations in large cities using meteorological and chemical variables as well as satellite-based aerosol optical depth. For PM_2.5 concentrations prediction, a random forest (RF) model showing excellent performance in PM concentrations prediction among machine learning models was selected. Based on the performance indicators R², RMSE, MAE, and MAPE with training accuracies of 0.97, 3.09, 2.18, and 13.31 and testing accuracies of 0.82, 6.03, 4.36, and 25.79 for R², RMSE, MAE, and MAPE, respectively. The variables used in this study showed high correlation to PM_2.5 concentrations. Therefore, we conclude that these variables can be used in a random forest model to generate reliable PM_2.5 concentrations predictions, which can then be used to assess the vulnerability of schools to PM_2.5.

• Journal of Wetlands Research
• /
• v.22 no.1
• /
• pp.24-30
• /
• 2020

To assess the wetland systems' capability to reduce fine dust, we used an artificial wetland module of small-sized greenhouse (70cm W × 70cm L × 60cm H) which creates a closed system. Experiment was performed twice using four species in each experiment. Non-plantation, one species, or two species condition was created in each mesocosm. We measured air quality, primarily PM2.5 and PM10 at the initial open mesocosms and 1hr later since mesocosms were closed. The dry weight of vegetation was measured at the 2nd experiment. The decreased amount of PM2.5 and PM10 was 13.7±1.3 and 13.2±1.3 ㎍·m^-3hr^-1 in wetland condition and 15.0±1.4 and 13.8±1.5 ㎍·m^-3hr^-1 in dryland condition, respectively. In 2^nd experiment, the decreased amount of PM 2.5 and PM 10 in wetland condition was 13.7±1.3 and 9.2±1.5 ㎍·m^-3hr^-1, 15.0±1.4 and 8.8±1.4 ㎍·m^-3hr^-1 in dryland condition, respectively. Wetland showed higher removal effect due to its high productivity leading to more effective absorption of particulate matter. Furthermore, the aquatic characteristics of wetland system and high humidity helped purifying the air quality. This can be seen as another value of wetlands, which can be presented as one of the solutions to the problem of fine dust.

• Korean Chemical Engineering Research
• /
• v.56 no.3
• /
• pp.356-360
• /
• 2018

The negative effects on ecosystem are getting serious due to the increase of particulate matters (PM) in the air by the increase of the number of population and the industrial activities. Thus, there have been a lot of environmental policies and researches of air purification system and filter mask to relieve the environmental problem. In this research, activated carbon impregnated cellulose acetate fiber filters produced using an electrospinning technique are studied for air purification. NaCl aqueous solution was used to generate PM and the humid air with NaCl PM was dried using a dehumidifier for the filter performance test. Filtration efficiency was increased with the increase of activated carbons, and acetone adsorption capacity was enhanced.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.8-14
• /
• 2020

The human impact of particulate matter are revealed and demand for improved forecast accuracy is increasing. Recently, efforts is made to improve the accuracy of PM10 predictions by using machine learning, but prediction performance is decreasing due to the particulate matter data with a large rate of low concentration occurrence. In this paper, separation prediction model by concentration is proposed to improve the accuracy of PM10 particulate matter forecast. The low and high concentration prediction model was designed using the weather and air pollution factors in Cheonan, and the performance comparison with the prediction models was performed. As a result of experiments with RMSE, MAPE, correlation coefficient, and AQI accuracy, it was confirmed that the predictive performance was improved, and that 20.62% of the AQI high-concentration prediction performance was improved.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.329-352
• /
• 2022

It is reported that particulate matter(PM) penetrates the lungs and blood vessels and causes various heart diseases and respiratory diseases such as lung cancer. The subway is a means of transportation used by an average of 10 million people a day, and although it is important to create a clean and comfortable environment, the level of particulate matter pollution is shown to be high. It is because the subways run through an underground tunnel and the particulate matter trapped in the tunnel moves to the underground station due to the train wind. The Ministry of Environment and the Seoul Metropolitan Government are making various efforts to reduce PM concentration by establishing measures to improve air quality at underground stations. The smart air quality management system is a system that manages air quality in advance by collecting air quality data, analyzing and predicting the PM concentration. The prediction model of the PM concentration is an important component of this system. Various studies on time series data prediction are being conducted, but in relation to the PM prediction in subway stations, it is limited to statistical or recurrent neural network-based deep learning model researches. Therefore, in this study, we propose four transformer-based models including spatiotemporal transformers. As a result of performing PM concentration prediction experiments in the waiting rooms of subway stations in Seoul, it was confirmed that the performance of the transformer-based models was superior to that of the existing ARIMA, LSTM, and Seq2Seq models. Among the transformer-based models, the performance of the spatiotemporal transformers was the best. The smart air quality management system operated through data-based prediction becomes more effective and energy efficient as the accuracy of PM prediction improves. The results of this study are expected to contribute to the efficient operation of the smart air quality management system.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.4
• /
• pp.405-412
• /
• 2021

The objective of this study is to investigate the environmental impact of fine dust generated at the construction waste intermediate treatment plants, and to propose engineering data and measures to suppress the generation of fine dust to cope with the expected strengthened environmental regulations of the government. The following study conclusions are drawn. 1) T he maximum concentration of fine dust in the workplace was measured as 160㎍/m³ from the crushing operation followed by the point of waste unloading, where focused suppression plan of the fine dust generation is needed in the future. 2) Fine dust concentrations of 113㎍/m³ in wet road conditions and 50㎍/m³ in dry conditions were measured, indicating that fine dust could be reduced by 50% with watering alone. 3) The effect of distancing from the dust source was studied. PM10 during operation of the workplace was measured as about 25㎍/m³ higher than those of the neighboring areas. Whereas there was no significant difference in case of PM2.5 between workplace and neighboring areas. 4) The measurement results of the heavy metal contents showed that these metals did not affect neighboring areas.

• Korea Petroleum Association Journal
• /
• s.308
• /
• pp.48-51
• /
• 2018

국내에서 대기 중에 존재하는 미세먼지 ($PM_{10}$, $PM_{2.5}$) 농도는 법적 허용치인 대기환경기준을 현재 초과하고 있으며, 2018년 3월말 강화된 기준을 달성하기 위해서는 어쩌면 우리가 '상상'할 수 있는 모든 방안을 이끌어내고 적극적으로 시행하는 방법 외에는 다른 선택의 여지가 없을 지도 모른다. 참으로 어려운 문제이다. 환경부의 2017년 대기환경연보를 보면 2016년 서울의 $PM_{2.5}$ 농도는 $26{\mu}g/m^3$으로 새로운 기준인 $15{\mu}g/m^3$를 달성하기 위해서는 대략 $11{\mu}g/m^3$ 만큼의 미세먼지 농도 감소가 필요하다. 중국 등 국외 배출량의 영향이 감소하고는 있다지만, 아직은 그 영향이 작지 않다. 많은 국민들이 이미 인지하고 있듯이, 국외 영향이 절반을 차지한다고 가정하면, 우리는 우리가 배출하는 모든 것을 중지시켜야 목표 농도 달성이 가능할 정도다. 과연 그 누가 그러자고 선 듯 나서서 말할 수 있을까?