PURPOSES : In this study, a model was developed to estimate the concentrations of particulate matter (PM2.5 and PM10) in expressway tunnel sections. METHODS : A statistical model was constructed by collecting data on particulate matter (PM2.5 and PM10), weather, environment, and traffic volume in the tunnel section. The model was developed after accurately analyzing the factors influencing the PM concentration. RESULTS : A machine learning-based PM concentration estimation model was developed. Three models, namely linear regression, convolutional neural network, and random forest models, were compared, and the random forest model was proposed as the best model. CONCLUSIONS : The evaluation revealed that the random forest model displayed the least error in the concentration estimation model for (PM2.5 and PM10) in all tunnel section cases. In addition, a practical application plan for the model developed in this study is proposed.

The Saemangeum has a dry surface characteristic with a low moisture content ratio due to the saline and silt soil, so the vegetation cover is low compared to other areas. In areas with low vegetation cover, wind erosion has a high probability of scattering dust. If the vegetation cover is increased by cultivating crops that can withstand the Saemangeum reclaimed environment, scattering dust can be reduced by reducing the flow rate at the bottom. Thus, the purpose of this study is to analyze the effect of suppressing the generation of fine dust and scattering dust by cultivating winter forage crops on the Saemangeum reclaimed land. While growing 0.5 ha of barley and 0.5 ha of triticale in Saemangeum reclaimed land, the concentration of fine dust was monitored according to agricultural work and growth stage. Changes in the concentrations of PM-10, PM-2.5, and PM-1.0 were monitored on the leeward, the windward and centering on the crop field. As a result of monitoring, PM-1.0 had little effect on crop cultivation. the concentration of PM-10 and PM-2.5 increased according to tillage and harvesting, and tillage had a higher increasing the concentration of PM-10 and PM-2.5 than that of harvesting. According to the growth stage of crops, the effect of suppressing scattering dust was shown, and the effect of suppressing scattering dust was higher in the heading stage than in the seedling stage. So, it was found that there was an effect of suppressing scattering dust other than the effect of land covering. Through this study, it was possible to know about the generation and suppression effect of scattering dust according to crop cultivation.

This study obtained the following conclusions using the measurement results of indoor and outdoor PM10 with regard to cardiovascular disease patients in Cheongju-area in November 2020. Most of the PM10 has an I/O ratio of less than 1, which is an outdoor source. Since we measured once and twice time, Without the air purifier device’s working status, there were no concentration changes of PM10 in the first and second indoor areas. As for the concentration of PM10 according to the living environment, the distribution of PM10 is higher indoors than outdoors when the residential area is 30 m2 or more, and the outdoor PM10 concentration tends to be high when the distance to the road is within 50 m. The more time spent indoors, the higher the indoor PM10 concentration. The smaller the ventilation time and frequency, the longer the cooking time was, and the higher the number of cooking times, the higher the concentration of PM10 could be. The indoor PM10 contribution ratio through multiple regression analysis showed the possibility of increasing indoor PM10 as β = 28.590 when the time spent indoors was longer than 16 hours (p<0.05). The result regarding PM10 exposure reveals that PM10 can be inhaled not only indoors but also outdoors, and the subjects of this study appear to have lived indoors for about 16 hours or longer on a daily basis, which may affect their health regardless of gender.

PURPOSES : This study analyzes the characteristics of generated fine particulate matter (PM2.5) and nitrogen oxide (NOX) at roadsides using a statistical method, namely, a generalized linear model (GLM). The study also investigates the applicability and capability of a machine learning methods such as a generalized regression neural network (GRNN) for predicting PM2.5 and NOX generations. METHODS : To analyze the characteristics of PM2.5 and NOX generations at roadsides, data acquisition was conducted in a specific segment of roads, and PM2.5 and NOX prediction models were estimated using GLM. In addition, to investigate the applicability and capability of a machine learning methods, PM2.5 and NOX prediction models were estimated using a GRNN and were compared with models employing previously estimated GLMs using r-square, mean absolute deviation (MAD), mean absolute percentage error (MAPE), and root mean square error (RMSE) as parameters. RESULTS : Results revealed that relative humidity, wind speed, and traffic volume were significant for both PM2.5 and NOX prediction models based on estimated models from a GLM. In addition, to compare the applicability and capability of the GLM and GRNN models (i.e., PM2.5 and NOX prediction models), the GRNN model of PM2.5 and NOX prediction was found to yield better statistical significance for r-square, MAD, MAPE, and RMSE as compared with the same parameters used in the GLM. CONCLUSIONS : Analytical results indicated that a higher relative humidity and traffic volume could lead to higher PM2.5 and NOX concentrations. By contrast, lower wind speed could affect higher PM2.5 and NOX concentrations at roadsides. In addition, based on a comparison of two statistical methods (i.e., GLM and GRNN models used to estimate PM2.5 and NOX), GRNN model yielded better statistical significance as compared with GLM.

The goal of this study was to measure the indoor and outdoor fine and ultrafine particulate matter concentrations (PM10, PM1.0) of some houses in Yeosu and in S university in Asan from March to September 2018. PM10 concentration in indoor air in Yeosu area was 18.25 μg/m3, while for outdoor air it was 14.53 μg/m3. PM1.0 concentration in indoor air in the Asan area was 1.70 μg/m3, while for outdoor air it was 1.76 μg/m3, showing a similar trend. Heavy metal concentrations in the Yeosu region were the highest, at Mn 2.81 μg/m3, Cr 1.30 μg/ m3, and Ni 1.11 μg/m3 indoors. Outside, similar concentrations were found, at Cr 3.44 μg/m3, Mn, 2.60 μg/m3, and Ni 1.71 μg/m3. Our analysis of indoor and outdoor PM concentrations in the Asan region, which was carried out using the MOUDI (Micro-orifice Uniform Deposit Impactor) technique, found that PM concentration is related to each particle size concentration, as the concentration of 18 μm and 18-10 μm inside tends to increase by 3.2- 1.8 μm and 0.56-0.32 μm.

The purpose of this study was to evaluate the concentration of airborne particulate matter and heavy metals in the houses of the respiratory tract disease patients and a control group of residents in the city of Gwangyang. The particulate matter was measured using a mini-volume air sampler and then weighed three times using a micro balance to calculate the weighted average value. The heavy metals in the particulate matter were extracted using a hot plate and analyzed using an inductively coupled plasma/mass spectrometer. The average concentration of particulate matter in the outdoor air (34.478 μm/m3) was higher than that in the indoor air (16.794 μm/m3), showing a statistically significant difference (p<0.001). The average concentration of copper, manganese and chromium in the indoor and outdoor air were higher in the houses of those in the study group than those of the control group. In addition, there was a generally high correlation between particulate matter in the outdoor air and heavy metals in the indoor and outdoor air concentration (p<0.05).