• 한국대기환경학회지
• /
• 제26권6호
• /
• pp.666-682
• /
• 2010

The forecasting system for Today's and Tomorrow's PM10 was developed based on the statistical model and the forecasting was performed at 9 AM to predict Today's 24 hour average PM10 concentration and at 5 PM to predict Tomorrow's 24 hour average PM10. The Today's forecasting model was operated based on measured air quality and meteorological data while Tomorrow's model was run by monitored data as well as the meteorological data calculated from the weather forecasting model such as MM5 (Mesoscale Meteorological Model version 5). The observed air quality data at ambient air quality monitoring stations as well as measured and forecasted meteorological data were reviewed to find the relationship with target PM10 concentrations by the regression analysis. The PM concentration, wind speed, precipitation rate, mixing height and dew-point deficit temperature were major variables to determine the level of PM10 and the wind direction at 500 hpa height was also a good indicator to identify the influence of long-range transport from other countries. The neural network, regression model, and decision tree method were used as the forecasting models to predict the class of a comprehensive air quality index and the final forecasting index was determined by the most frequent index among the three model's predicted indexes. The accuracy, false alarm rate, and probability of detection in Tomorrow's model were 72.4%, 0.0%, and 42.9% while those in Today's model were 80.8%, 12.5%, and 77.8%, respectively. The statistical model had the limitation to predict the rapid changing PM10 concentration by long-range transport from the outside of Korea and in this case the chemical transport model would be an alternative method.

• Asian Journal of Atmospheric Environment
• /
• 제4권2호
• /
• pp.72-79
• /
• 2010

In this study, the ionic composition of volcanogenically derived particles and their temporal and spatial distributions have been investigated to evaluate the impact of the volcanic eruption on the local ecosystem and residents. To this end, an intensive field study was conducted to measure the size-segregated particulate matters at the east part of Sakurajima in Japan. Fractionated sampling of particles into > $PM_{10}$, $PM_{10-2.5}$, and $PM_{2.5}$ was made by a multi nozzle cascade impactor (MCI). The concentration of various ions present in the size-resolved particles was determined by Ion chromatography. The time dependent 3-dimensional Volcanic Ash Forecast Transport And Dispersion (VAFTAD) model developed by the NOAA Air Resources Laboratory (ARL) indicated that the sampling site of this work was affected by the volcanic aerosol particles plume. The temporal distributions of sulfate and $PM_{2.5}$ during the field campaign were significantly variable with important contributions to particle mass concentration. The chlorine loss, suspected to be caused by acidic components of volcanic gases, occurred predominantly in fine particles smaller than $10\;{\mu}m$.

• 한국대기환경학회지
• /
• 제22권5호
• /
• pp.614-626
• /
• 2006

Using the data of three environmental monitoring sites in Pohang area(KME112, KME113, and KME114), statistical forecasting models of the daily maximum and mean values of PM10 have been developed. Since the distributions of the daily maximum and mean PM10 values are skewed, which are similar to the Weibull distribution, these values were log-transformed to increase prediction accuracy by approximating the normal distribution. Three statistical forecasting models, which are regression, neural networks(NN) and support vector regression(SVR), were built using the log-transformed response variables, i.e., log(max(PM10)) or log(mean (PM10)). Also, the forecasting models were validated by the measure of RMSE, CORR, and IOA for the model comparison and accuracy. The improvement rate of IOA before and after the log-transformation in the daily maximum PM10 prediction was 12.7% for the regression and 22.5% for NN. In particular, 42.7% was improved for SVR method. In the case of the daily mean PM10 prediction, IOA value was improved by 5.1% for regression, 6.5% for NN, and 6.3% for SVR method. As a conclusion, SVR method was found to be performed better than the other methods in the point of the model accuracy and fitness views.

• 한국지구과학회지
• /
• 제43권3호
• /
• pp.386-404
• /
• 2022

2011년 4월 29일부터 30일까지 몽골에서 발원한 황사의 영향으로 우리나라는 4일간 전국적으로 고농도의 황사가 관측되었다. 본 연구는 몽골의 황사발원지에서 황사 발생 시 기상 조건과 고농도 황사 사례의 원인 및 특성을 알아보기 위한 것으로, 황사 일기도 자료, 황사감시기상탑 자료, 위성 자료, 후방공기궤적 자료, 관측자료(PM₁₀ 및 광학입자 계수기 자료), ECMWF 재분석 자료를 이용하였다. 분석 결과, 종관 분석에서는 몽골 중부지역에 등압선의 간격이 조밀하게 분포하고 기압경도력이 강해지면서 강풍에 의해 황사가 발원하였다. 황사 발원과 기상 조건의 관계에서 황사 발원 직전에는 10℃ 이상으로 비교적 높은 기온을 나타내다 황사 발원과 동시에 급감하였으며, 상대습도는 약 40% 이하의 낮은 값을 지속적으로 나타내다 황사 발원 후에는 50% 이상으로 급격히 높아지며 황사의 발생이 줄어드는 경향을 보였다. COMS에서 관측된 황사지수는 황사발원지에서는 25 이상을 나타내면서 고농도의 황사가 탐지되었고, 실황에서 목측으로 관측된 지점과 일치하였다. 72시간 후방공기궤적에서는 모두 북서 기류가 한반도로 유입되었고, 5월 2일 흑산도에서는 PM₁₀의 시간평균농도가 1,025 ㎍ m^-3으로 최고 농도를 보였다. 특히 운동학적 연직 분석에서, 상층에서 발달한 기압골과 저기압성 소용돌이도에 의해 지상 저기압이 강화되고 동시에 상승 기류의 발달이 고농도의 황사 발생에 큰 역할을 한 것으로 판단된다.

• Asia-Pacific Journal of Atmospheric Sciences
• /
• 제54권4호
• /
• pp.623-637
• /
• 2018

This study investigates the effects of horizontal resolution, cumulus parameterization scheme (CPS), and probability forecasting on precipitation forecasts over the Korean Peninsula from 00 UTC 15 August to 12 UTC 14 September 2013, using the limited-area ensemble prediction system (LEPS) of the Korea Meteorological Administration. To investigate the effect of resolution, the control members of the LEPS with 1.5- and 3-km resolution were compared. Two 3-km experiments with and without the CPS were conducted for the control member, because a 3-km resolution lies within the gray zone. For probability forecasting, 12 ensemble members with 3-km resolution were run using the LEPS. The forecast performance was evaluated for both the whole study period and precipitation cases categorized by synoptic forcing. The performance of precipitation forecasts using the 1.5-km resolution was better than that using the 3-km resolution for both the total period and individual cases. The result of the 3-km resolution experiment with the CPS did not differ significantly from that without it. The 3-km ensemble mean and probability matching (PM) performed better than the 3-km control member, regardless of the use of the CPS. The PM complemented the defect of the ensemble mean, which better predicts precipitation regions but underestimates precipitation amount by averaging ensembles, compared to the control member. Further, both the 3-km ensemble mean and PM outperformed the 1.5-km control member, which implies that the lower performance of the 3-km control member compared to the 1.5-km control member was complemented by probability forecasting.

• 한국환경과학회지
• /
• 제32권8호
• /
• pp.595-611
• /
• 2023

The purpose of this study is to improve the daily prediction results of PM2.5 from the air quality diagnosis and evaluation system operated by the Busan Institute of Health and Environment in real time. The air quality diagnosis and evaluation system is based on the photochemical numerical model, CMAQ (Community multiscale air quality modeling system), and includes a 3-day forecast at the end of the model's calculation. The photochemical numerical model basically has limitations because of the uncertainty of input data and simplification of physical and chemical processes. To overcome these limitations, this study applied DNN (Deep Neural Network), a deep learning technique, to the results of the numerical model. As a result of applying DNN, the r of the model was significantly improved. The r value for GFS (Global forecast system) and UM (Unified model) increased from 0.77 to 0.87 and 0.70 to 0.83, respectively. The RMSE (Root mean square error), which indicates the model's error rate, was also significantly improved (GFS: 5.01 to 6.52 ug/m³ , UM: 5.76 to 7.44 ug/m³ ). The prediction results for each concentration grade performed in the field also improved significantly (GFS: 74.4 to 80.1%, UM: 70.0 to 77.9%). In particular, it was confirmed that the improvement effect at the high concentration grade was excellent.

• Asian Journal of Atmospheric Environment
• /
• 제3권1호
• /
• pp.1-8
• /
• 2009

Enhancement of aerosol optical thickness (AOT) and surface aerosol mass concentration in Korea for an active forest fire episode in Northeast Asia were estimated by Community Multi-scale Air Quality (CMAQ) model. MODIS/TERRA remote detects of fires in Northeast Asia for May 2003 gave a constraint for estimation of wildfire emissions with an NDVI distribution for recent five years. The simulated wildfire plumes and enhancement of AOT were evaluated and well resolved by comparing multiple satellite observations such as MODIS, TOMS, and others. Scatter plots of observed daily mean aerosol extinction coefficient versus $PM_{10}$ concentration in ground level in Korea showed distinctively different trends based on the ambient relative humidity.

• 정보처리학회 논문지
• /
• 제13권6호
• /
• pp.251-259
• /
• 2024

초미세먼지, 특히 지름이 2.5㎛ 이하인 PM2.5는 인체 건강과 경제에 큰 피해를 주는 오염물질이다. 본 연구는 대한민국 서울 지역을 중심으로, 2017년부터 2022년까지 자료를 수집하여 PM2.5 데이터 분석 및 데이터 경향성 변화 추이를 분석하고, PM2.5 중기 예측 모델을 개발하는 것을 목표로 한다. 수집, 생산된 대기질 및 기상 데이터, 재분석 데이터, 수치모델 예측 데이터를 바탕으로, 모델을 학습하고 이를 통합한 경향성 변화에도 대응할 수 있는 앙상블 기법을 제안한다. 본 연구에서 제안하는 앙상블 기법은 PM2.5 농도 예측 성능 면에서 기존 모델 대비 미래 D+3~D+6 예측일 F1 Score 기준 평균 2019년 약 42.16%, 2021년 약 58.92%, 2022년 약 34.79% 높은 성능을 보였다. 제안한 모델은 변화하는 환경 조건에도 성능을 유지함으로써 안정적인 예측을 가능하게 하며, 기존 딥러닝 기반 PM2.5 단기 예측보다 먼 예측을 수행하는 중기 예측 모델을 제시한다.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.203-210
• /
• 2019

Recently, a number of researchers have produced research and reports in order to forecast more exactly air quality such as particulate matter and odor. However, such research mainly focuses on the atmospheric diffusion models that have been used for the air quality prediction in environmental engineering area. Even though it has various merits, it has some limitation in that it uses very limited spatial attributes such as geographical attributes. Thus, we propose the new approach to forecast an air quality using a deep learning based ensemble model combining temporal and spatial predictor. The temporal predictor employs the RNN LSTM and the spatial predictor is based on the geographically weighted regression model. The ensemble model also uses the RNN LSTM that combines two models with stacking structure. The ensemble model is capable of inferring the air quality of the areas without air quality monitoring station, and even forecasting future air quality. We installed the IoT sensors measuring PM2.5, PM10, H2S, NH3, VOC at the 8 stations in Jeonju in order to gather air quality data. The numerical results showed that our new model has very exact prediction capability with comparison to the real measured data. It implies that the spatial attributes should be considered to more exact air quality prediction.

• Communications for Statistical Applications and Methods
• /
• 제31권1호
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).