• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.517-530
• /
• 2023

Recent studies revealed that fine dust in ambient air may cause various health problems such as respiratory diseases and cancer. To prevent the toxic effects of fine dust, it is important to predict the concentration of fine dust in advance and to identify factors that are closely related to fine dust. In this study, we developed a Bayesian network model for predicting PM10 concentration in Seoul, Korea, and visualized the relationship between important factors. The network was trained by using air quality and meteorological data collected in Seoul between 2018 and 2021. The study results showed that current PM10 concentration, season, carbon monoxide (CO) were the top 3 effective factors in 24 hours ahead prediction of PM10 concentration in Seoul, and that there were interactive effects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• Journal of Environmental Science International
• /
• v.12 no.6
• /
• pp.677-688
• /
• 2003

The purpose of this study was to predict occurrence of earthquakes in Korea by measuring the concentration of radon radioactivity in the air and in the underground water. Two monitoring systems of radon concentration detection in the air were installed in Seoul, East Coast area, whereas of radon concentration in the underground water in Kyungju area during December, 1999 to June, 2001. The distribution of radon concentration in the air in Seoul is as follows Winter(10.10 $\pm$ 2.81 Bq/㎥), autumn(8.41 $\pm$ 1.35 Bq/㎥), summer(5.83 $\pm$ 0.05 Bq/㎥) and spring (5.34 $\pm$ 0.44 Bq/㎥), whereas the distribution of radon in the air in the East Coast area showed some difference as follows : autumn (14.08 $\pm$ 5.75 Bq/㎥), Summer (12.04 $\pm$ 0.53 Bq/㎥), Winter (12.02 $\pm$ 1.40 Bq/㎥) and spring (8.93 $\pm$ 0.91 Bq/㎥). In the meanwhile, the distribution of radon in the water is as follows : spring (123.59 $\pm$ 16.36count/10min), Winter (93.95 $\pm$ 79.69counter/10min), autumn (68.96 $\pm$ 37.53counter/10min) and spring (34.45 $\pm$ 9.69counter/10min). The daily range of the density of radon concentration in Seoul and East Coast area was between 5.51 Bq/㎥ - 9.44 Bq/㎥, 7.15 Bq/㎥ - 15.27 Bq/㎥, respectively. Correlation of the distributions of radon concentrations in the air and in underground water with earthquake showed considerable variations of radon concentration before the occurrence of the earthquake. The results suggested that radon radioactivity seemed to be helpful for the prediction of the occurrence of earthquake.

• 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.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.573-586
• /
• 2020

PM (particulate matter) is of interest to everyone because it can have adverse effects on human health by the infiltration from respiratory to internal organs. To date, many studies have made efforts for the prediction of PM10 and PM2.5 concentrations. Unlike previous studies, we conducted the prediction of tomorrow's PM10 concentration for the Air Korea stations using Chinese PM10 data in addition to the satellite AOD and weather variables. We constructed 230,639 matchups from the raw data over 3 million and built an RF (random forest) model from the matchups to cope with the complexity and nonlinearity. The validation statistics from the blind test showed excellent accuracy with the RMSE (root mean square error) of 9.905 ㎍/㎥ and the CC (correlation coefficient) of 0.918. Moreover, our prediction model showed a stable performance without the dependency on seasons or the degree of PM10 concentration. However, part of coastal areas had a relatively low accuracy, which implies that a dedicated model for coastal areas will be necessary. Additional input variables such as wind direction, precipitation, and air stability should also be incorporated into the prediction model as future work.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.576-581
• /
• 2021

Compared to a low concentration, a high concentration clearly entails limitations in terms of predictive performance owing to differences in its frequency and environment of occurrence. To resolve this problem, in this study, an artificial intelligence neural network algorithm was used to classify low and high concentrations; furthermore, two prediction models trained using the characteristics of the classified concentration types were used for prediction. To this end, we constructed training datasets using weather and air pollutant data collected over a decade in the Cheonan region. We designed a DNN-based classification model to classify low and high concentrations; further, we designed low- and high-concentration prediction models to reflect characteristics by concentration type based on the low and high concentrations classified through the classification model. According to the results of the performance assessment of the prediction model by concentration type, the low- and high-concentration prediction accuracies were 90.38% and 96.37%, respectively.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.7-13
• /
• 2021

This study develops an artificial intelligence prediction system for Fine particulate Matter(PM2.5) based on the deep learning algorithm GAN model. The experimental data are closely related to the changes in temperature, humidity, wind speed, and atmospheric pressure generated by the time series axis and the concentration of air pollutants such as SO2, CO, O3, NO2, and PM10. Due to the characteristics of the data, since the concentration at the current time is affected by the concentration at the previous time, a predictive model for recursive supervised learning was applied. For comparative analysis of the accuracy of the existing models, CNN and LSTM, the difference between observation value and prediction value was analyzed and visualized. As a result of performance analysis, it was confirmed that the proposed GAN improved to 15.8%, 10.9%, and 5.5% in the evaluation items RMSE, MAPE, and IOA compared to LSTM, respectively.

• Journal of Advanced Navigation Technology
• /
• v.28 no.1
• /
• pp.149-154
• /
• 2024

Research on particulate matter is advancing in real-time, and various methods are being studied to improve the accuracy of prediction models. Furthermore, studies that take into account various factors to understand the precise causes and impacts of particulate matter are actively being pursued. This paper trains an LSTM model using seasonal data and another LSTM model using concentration-based data. It compares and analyzes the PM_2.5 prediction performance of the two models. To train the model, weather data and air pollutant data were collected. The collected data was then used to confirm the correlation with PM_2.5. Based on the results of the correlation analysis, the data was structured for training and evaluation. The seasonal prediction model and the concentration-specific prediction model were designed using the LSTM algorithm. The performance of the prediction model was evaluated using accuracy, RMSE, and MAPE. As a result of the performance evaluation, the prediction model learned by concentration had an accuracy of 91.02% in the "bad" range of AQI. And overall, it performed better than the prediction model trained by season.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• Journal of Korean Society for Atmospheric Environment
• /
• v.33 no.6
• /
• pp.554-569
• /
• 2017

Sensitivity analysis on $PM_{10}$ forecasting simulations was carried out by using two different initial and boundary conditions of meteorological fields: NCEP/FNL (National Centers for Environmental Prediction/Final Analysis) reanlaysis data and NCEP/GFS (National Centers for Environmental Prediction/Global Forecast System) forecasting data, and the comparisons were made between two different simulations. The two results both yielded lower $PM_{10}$ concentrations than observations, with relatively lower biased results by NCEP/FNL than NCEP/GFS. We explored the detailed individual meteorological variables to associate with $PM_{10}$ prediction performance. With the results of NCEP/FNL outperforming GFS, our conclusion is that no particular significant bias was found in temperature fields between NCEP/FNL and NCEP/GFS data, while the overestimated wind speed by NCEP/GFS data influenced on the lower $PM_{10}$ concentrations simulation than NCEP/FNL, by decreasing the duration time of high-$PM_{10}$ loaded air mass over both coastal and metropolitan areas. These comparative characteristics of FNL against GFS data such as maximum 3~4 m/s weaker wind speed, $PM_{10}$ concentration control with the highest possible factor of 1.3~1.6, and one or two hour difference of peak time for each case in this study, were also reflected into the results of statistical analysis. It is implying that improving the surface wind speed fluctuation is an important controlling factor for the better prediction of $PM_{10}$ over Korean Peninsula.