• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.4
• /
• pp.1931-1938
• /
• 2012

This study evaluated whether the installed location of air quality monitoring stations is at an optimal level in an effort to improve the health and environmental quality of the surrounding areas of the Pohang Steel Complex. As a result of analyzing the atmospheric flow field, it was found that the location of air quality monitoring stations was acceptable in case of Daesong-myeon(The 1st Division of Local Wind Sector) and Jukdo-dong(The 3rd Division of Local Wind Sector). However, the air quality monitoring stations installed at Daedo-dong and Jukdo-dong is judged to have made an overlapped measurement because the stations existed at the Division of the same Wind Sector. Accordingly, this study suggests that the further air quality monitoring stations should be additionally installed at Buk-gu areas of Pohang where more than 50% of the population of Pohang is living presently. As a result of the analysis of air contaminant concentration distribution, the Jangheung-dong area showed higher concentration distribution than other areas in case of $PM_{10}$ while the Daesong-myeon area showed a comparatively higher concentration distribution in case of $O_3$. Conclusively, this study indicates that it is high time to prepare an aggressive management of $PM_{10}$ and $O_3$ which causes a harmful impact on the life and health of the residents of the target areas.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.4
• /
• pp.109-118
• /
• 2022

The data of the missing section among the vertex surface sea temperature observation data was imputed using the Bidirectional Recurrent Neural Network(BiRNN). Among artificial intelligence techniques, Recurrent Neural Networks (RNNs), which are commonly used for time series data, only estimate in the direction of time flow or in the reverse direction to the missing estimation position, so the estimation performance is poor in the long-term missing section. On the other hand, in this study, estimation performance can be improved even for long-term missing data by estimating in both directions before and after the missing section. Also, by using all available data around the observation point (sea surface temperature, temperature, wind field, atmospheric pressure, humidity), the imputation performance was further improved by estimating the imputation data from these correlations together. For performance verification, a statistical model, Multivariate Imputation by Chained Equations (MICE), a machine learning-based Random Forest model, and an RNN model using Long Short-Term Memory (LSTM) were compared. For imputation of long-term missing for 7 days, the average accuracy of the BiRNN/statistical models is 70.8%/61.2%, respectively, and the average error is 0.28 degrees/0.44 degrees, respectively, so the BiRNN model performs better than other models. By applying a temporal decay factor representing the missing pattern, it is judged that the BiRNN technique has better imputation performance than the existing method as the missing section becomes longer.

• Journal of the Korean association of regional geographers
• /
• v.4 no.1
• /
• pp.43-56
• /
• 1998

The purpose of this study is to identify distributional characteristics of climatic elements and to analyze synoptic characteristics on the pressure fields for spring droughts in Korea. In the distributions of minimum temperature during the spring droughts, positive anomalies and negative anomalies are mixed up, but in March the negative anomaly areas are widely distributed in Korea. It implies that the droughts of March have more frequent occurrences of the west-high, east-low pressure patterns. In the maximum air temperatures, the positive anomalies appear in Korea. It indicates that the spring droughts have rain days, cloud amount and humidities less than normal. As a result, the amount of evaporation is increased in Korea. In the pressure anomaly of surface pressure fields, the positive anomalies appear in the west, negative anomalies in the east in March, but in May the positive anomalies appeared zonally around the Korean peninsula. It indicates that March droughts have more frequent occurrences of the west-high. east-low patterns, but in May the Korean Peninsula has more frequent recurrences of the migratory anticyclone patterns. The height anomaly patterns of 500hPa pressure surface in spring droughts are similarly shown to those of surface fields. In March droughts, the positive height anomalies appear in the west, the negative height anomalies in the east, but in April the negative height anomaly areas are extended to the west part. In May the positive anomalies appear zonally around the Korean Peninsula, and strong positive height anomalies appear around the Kamchatka Peninsula and the sea of Okhotsk. These are the result of circulations that inhibit the eastward movement of westerlies and that has persistent anticyclone circulation patterns around the Korean Peninsula. As a result, the zonal indices of westerlies during March and April droughts are lower than normal, but higher in May. These data indicate that early spring droughts are associated with weak zonal flow, but the late spring droughts are obviously related with strong zonal flow. In addition, during early spring droughts the abnormally deep trough over the west coast of the North Pacific Ocean that accompanied the anticyclone was associated with frequent advection of air from the dry regions in the Central Asia into the Korean Peninsula. The atmospheric circulation patterns at the height of the 500hPa pressure surface in May was quite different from March and April circulation patterns. Instead of the abnormal ridge in the west and trough in the east, the circulation pattern in May was characterized by a much stronger than normal anticyclone over the Korean Peninsula. Also, the zonal indices of westerlies in May are higher than normal. The occurrences of drought in early spring, therefore, have mechanism different from those of late spring.