http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
서울 도심 공지의 개발 시나리오에 따른 미기후 영향 분석 - 풍속 및 기온 비교 -
백지원 ( Jiwon Baek ),박찬 ( Chan Park ),박소민 ( Somin Park ),최재연 ( Jaeyeon Choi ),송원경 ( Wonkyong Song ),강다인 ( Dain Kang ),김수련 ( Suryeon Kim ) 한국환경영향평가학회 2021 환경영향평가 Vol.30 No.2
건물이 밀집되고 인구밀도가 높은 도시는 열섬현상이 가중되고 열쾌적성에 취약하다. 도심에서 방치되고 있는 공지는 주거환경과 도시미관을 저해하고 지역 전체의 경제적 활력이 낮아지며 도시를 쇠퇴하는 하나의 요인으로 다루어진다. 이에 본 연구에서는 서울 종로구 송현동의 공지를 대상으로 개발 시나리오에 따라 주변 미기후 영향을 비교하고자 하였다. 현 상태 유지, 녹지 중심, 건물 중심, 녹지-건물 절충시나리오를 설정하고, ENVI-met을 사용하여 개별 시나리오별로 대상지와 대상지 주변 1 km 내 변화되는 풍속, 기온, 평균복사온도를 개발 시나리오별 내·외부 영향을 비교분석하였다. 연구 결과, 대상지 내·외부는 녹지 중심의 시나리오가 현 상태 유지 시나리오와 비교했을 때 계절별 평균 기온은 낮아졌고, 풍속이 빨라진 것으로 도출되었다. 여름철 최대 -0.73 ℃가 낮아지거나 1.5 ℃까지 상승될 것으로 예상되었고, 풍속은 시나리오에 따라 최대 210 m 범위까지 영향이 있었다. 또한, 녹지는 내·외부, 건물 배치 및 크기는 녹지보다 효과는 적으나 인접한 외부 공간에 영향을 주는 것을 확인하였다. 본 연구는 송현동 개발 방향에 대한 의사결정 지원 도구로써 도움을 줄 수 있고, 향후 환경영향평가 제도에 미기후에 대한 부분을 반영하는데 활용할 수 있을 것으로 예상된다. In the city of high population density crowded with buildings, Urban Heat Island (UHI) is intensified, and the city is vulnerable to thermal comfort. The maintenance of vacant land in downtown is treated as a factor that undermines the residential environment, spoils the urban landscape, and decreases the economic vitality of the whole region. Therefore, this study compared the effects on microclimate in the surrounding area according to the development scenarios targeting the vacant land in Songhyeon-dong, Jongno-gu, Seoul. The status quo, green oriented, building oriented and green-building mediation scenarios were established and ENVI-met was used to compare and analyze the impact of changes in wind speed, air temperature and mean radiant temperature (MRT) within 1 km of the target and the target site. The result of inside and 1 km radius the targeted area showed that the seasonal average temperature decreased and the wind speed increased when the green oriented scenario was compared with the current state one. It was expected that the temperature lowered to -0.73 °C or increased to 1.5 °C in summer, and the wind speed was affected up to 210 meters depending on the scenario. And it was revealed that green area inside the site generally affects inside area, but the layout and size of the buildings affect either internal and external area. This study is expected to help as a decision-making support tool for developing Songhyeon-dong area and to be used to reflect the part related to microclimate on the future environmental effects evaluation system.
딥러닝 사물 인식 알고리즘(YOLOv3)을 이용한 미세조류 인식 연구
박정수 ( Jungsu Park ),백지원 ( Jiwon Baek ),유광태 ( Kwangtae You ),남승원 ( Seung Won Nam ),김종락 ( Jongrack Kim ) 한국물환경학회(구 한국수질보전학회) 2021 한국물환경학회지 Vol.37 No.4
Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.