Journal of the Korean Institute of Landscape Architecture (한국조경학회지)

The Korean Institute of Landscape Architecture (한국조경학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Urban Heat Island (UHI) Alleviating Effect of Urban Parks and Green Space in Seoul Using Deep Neural Network (DNN) Model

심층신경망 모형을 이용한 서울시 도시공원 및 녹지공간의 열섬저감효과 분석

  • Kim, Byeong-chan (Dept. of Landscape Architecture, College of Urban Science, The University of Seoul) ;
  • Kang, Jae-woo (Dept. of Landscape Architecture, College of Urban Science, The University of Seoul) ;
  • Park, Chan (Dept. of Landscape Architecture, College of Urban Science, The University of Seoul) ;
  • Kim, Hyun-jin (Dept. of Landscape Architecture, College of Urban Science, The University of Seoul)
  • 김병찬 (서울시립대학교 조경학과) ;
  • 강재우 (서울시립대학교 조경학과) ;
  • 박찬 (서울시립대학교 조경학과) ;
  • 김현진 (서울시립대학교 조경학과)
  • Received : 2020.06.30
  • Accepted : 2020.08.04
  • Published : 2020.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The Urban Heat Island (UHI) Effect has intensified due to urbanization and heat management at the urban level is treated as an important issue. Green space improvement projects and environmental policies are being implemented as a way to alleviate Urban Heat Islands. Several studies have been conducted to analyze the correlation between urban green areas and heat with linear regression models. However, linear regression models have limitations explaining the correlation between heat and the multitude of variables as heat is a result of a combination of non-linear factors. This study evaluated the Heat Island alleviating effects in Seoul during the summer by using a deep neural network model methodology, which has strengths in areas where it is difficult to analyze data with existing statistical analysis methods due to variable factors and a large amount of data. Wide-area data was acquired using Landsat 8. Seoul was divided into a grid (30m × 30m) and the heat island reduction variables were enter in each grid space to create a data structure that is needed for the construction of a deep neural network using ArcGIS 10.7 and Python3.7 with Keras. This deep neural network was used to analyze the correlation between land surface temperature and the variables. We confirmed that the deep neural network model has high explanatory accuracy. It was found that the cooling effect by NDVI was the greatest, and cooling effects due to the park size and green space proximity were also shown. Previous studies showed that the cooling effects related to park size was 2℃-3℃, and the proximity effect was found to lower the temperature 0.3℃-2.3℃. There is a possibility of overestimation of the results of previous studies. The results of this study can provide objective information for the justification and more effective formation of new urban green areas to alleviate the Urban Heat Island phenomenon in the future.

도시화로 인한 도시열섬현상(Urban Heat Island)이 심화되면서 도시차원의 열 관리가 중요한 이슈로 다뤄지고, 도시열섬현완화 방안으로 녹지사업과 환경정책이 시행되고 있고, 도시공원 및 녹지와 열의 관계를 분석하는 다수의 연구가 수행되었다. 하지만 열이라는 특성은 다수의 요인이 복합적으로 얽혀있어 선형적 상관관계를 통한 해석에 한계가 있다. 본 연구는 변수요인들이 다양하고 데이터의 양이 방대하여 기존의 통계분석방식으로는 분석하기 어려운 분야에서 강점을 갖는 심층신경망 모형 방법론을 사용하여 여름철 서울지역의 공원 및 녹지의 열섬저감효과를 평가하는 것을 목표로 연구를 진행하였다. 이를 위해서 Landsat 8 인공위성영상을 활용하여 동시간의 광역적인 데이터를 취득하였고, ArcGis 10.7을 이용하여 서울시를 30m×30m 그리드로 격자화하여, 각 격자에 열섬저감을 측정할 수 있는 환경변수를 구축하였다. Python 3.7과 Keras를 이용하여 심층신경망 모형을 생성하여 지표면 온도와 변수 간의 관계를 분석하였다. 분석 결과, 인공신경망 모형은 높은 설명력을 가지는 것을 확인하였다. 또한 일반적인 연구 결과와 마찬가지로 인접 녹지와의 거리가 가까울수록, 공원면적이 커질수록, 공원의 식생활력도가 높을수록 지표면 온도가 낮아짐을 확인하였다. 식생활력도에 의한 냉각효과가 많이 있는 것을 확인하였고, 일부 선행연구에서 녹지에 인접할수록 0.3℃ ~ 2.3℃ 저감될 수 있는 특성이 나타나고, 공원의 크기가 크면 2℃~3℃ 저감효과가 나타난다는 결과를 보이고 있는데, 본 연구결과와 비교해 보면 도출된 효과가 과대평가되었을 가능성을 확인하였다. 본 연구의 결과는 향후 도시열섬현상 완화를 위해 새로운 도시녹지를 조성시 효과적인 녹지 구성을 위한 정보로 활용될 수 있다.

Keywords

References

  1. An, M. Y. and S. H. Hong(2015) Relationship between changing vegetation type and temperature in urban forest. Korean Journal of Environment and Ecology 2015(2): 55-55.
  2. Cha, J. G., E. H. Jung, J. W. Ryu and D. W. Kim(2007) Constructing a green network and wind corridor to alleviate the urban heat-island. Journal of the Korean Association of Geographic Information Studies 10(1): 102-112.
  3. Cheng, X., B. Wei, G. Chen, J. Li and C. Song(2015) Influence of park size and its surrounding urban landscape patterns on the park cooling effect. Journal of Urban Planning and Development 141(3): A4014002. https://doi.org/10.1061/(ASCE)UP.1943-5444.0000256
  4. Feyisa, G. L., K. Dons and H. Meilby(2014) Efficiency of parks in mitigating urban heat island effect: An example from Addis Ababa. Landscape and Urban Planning 123: 87-95. https://doi.org/10.1016/j.landurbplan.2013.12.008
  5. Gallo, K., R. Hale, D. Tarpley, and Y. Yu(2011) Evaluation of the relationship between air and land surface temperature under clearand cloudy-sky conditions. J. Appl. Meteor. Climatol. 50: 767-775. https://doi.org/10.1175/2010JAMC2460.1
  6. Jo, H. G. and T. W. An(2006) Exploring relationships between urban tree plantings and microclimate amelioration. Journal of the Korean Institute of Landscape Architecture 34(5): 70-75.
  7. Joo, C. H., J. H. Kim and Y. H. Yoon(2014) A study on green space management planning considering urban thermal environment. Journal of Environmental Science International 23(7): 1349-1358. https://doi.org/10.5322/JESI.2014.23.7.1349
  8. Ki, K. S., B. H. Han and J. Y. Hur(2012) A study of factors influencing of temperature according to the land cover and planting structure in the city park - A case study of central park in Bundang gu, Seongnam -. Korean Journal of Environment and Ecology 26(5): 801-811.
  9. Kim, G. H., Y. G. Lee, J. H. Kim, H. W. Choi and B. J. Kim(2018b) Analysis of the cooling effects in urban green areas using the landsat 8 satellite data. Korean Journal of Remote Sensing 34(2): 167-178. https://doi.org/10.7780/kjrs.2018.34.2.1.1
  10. Kim, H. S. (2012) The Difference in Temperature according to the Land Coverage and Vegetation Structure of Large-Scale Green Area in Seoul. Master Thesis. University of Seoul. Korea.
  11. Kim, K. J., D. J. Kim, C. H. Lee and S. I. Lee(2018a) Analysis on influence range of reducing the surface temperature and building energy consumption by urban park size and shape. Journal of the Korean Regional Development Association 30(2): 155-176. https://doi.org/10.22885/KRDA.2018.30.2.155
  12. Kim, M. K., S. P. Kim, N. H. Kim and H. G. Sohn(2014) Urbanization and urban heat island analysis using landsat imagery: Sejong city as a case study. Journal of the Korean Society of Civil Engineers 34(3): 1033-1041. https://doi.org/10.12652/Ksce.2014.34.3.1033
  13. Kim, S. J. and S. Y. Lee(2008) A study on the determining model of office rents -Based on multiple regression and artificial neural networks-. Journal of the Korean Regional Science Association 24(2): 3-26.
  14. Kim, T. H. and H. K. Hong(2004) A study on apartment price models using regression model and neural network model. Korea Research Institute for Human Settlements 43: 183-200.
  15. Ko, Y. J., K. H. Cho and W. C. Kim(2019) Analysis of environmental equity of green space services in Seoul -The case of Jung-gu, Seongdong-gu and Dongdaemun-gu-. Journal of the Korean Institute of Landscape Architecture 47(2): 100-116. https://doi.org/10.9715/KILA.2019.47.2.100
  16. Kong, F., H. Yin, P. James, L. R. Hutyra and H. S. He(2014) Effects of spatial pattern of greenspace on urban cooling in a large metropolitan area of eastern China. Landscape and Urban Planning 128: 35-47. https://doi.org/10.1016/j.landurbplan.2014.04.018
  17. Koo, S., G. S. Jung and H. H. Yoo(2011) Analysis of correlation between urban temperature and NDVI of landsat imagery. The Korean Society for Geo-Spatial Information System 2011(5): 181-182.
  18. Lee, W. S., S. G. Jung, K. H. Park and K. T. Kim(2010). Analysis of urban thermal environment for environment-friendly spatial plan. Journal of the Korean Association of Geographic Information Studies 13(1): 142-154. https://doi.org/10.11108/kagis.2010.13.1.142
  19. Lin, W., T. Yu, X. Chang, W. Wu and Y. Zhang(2015) Calculating cooling extents of green parks using remote sensing: Method and test. Landscape and Urban Planning 134: 66-75. https://doi.org/10.1016/j.landurbplan.2014.10.012
  20. Oh, K. S. and J. J. Hong(2005) The relationship between urban spatial elements and the urban heat island effect. Journal of The Urban Design Institute of Korea 6(1): 47-63.
  21. Park, J. H. and G. H. Cho(2016a) Influence of park size on the park cooling effect - Focused on Ilsan new town in Korea -. Journal of Korea Planning Association 51(5): 247-261. https://doi.org/10.17208/jkpa.2016.10.51.5.247
  22. Park, J. H. and G. H. Cho(2016b) Examining the association between physical characteristics of green space and land surface temperature: A case study of Ulsan, Korea. Sustainability 8(8): 777. https://doi.org/10.3390/su8080777
  23. Park, S. K., S. M. Jo, C. J. Hyun, H. Y. Kong, S. H. Kim and Y. K. Shin(2017). Air temperature modification of an urban neighborhood park in summer - Hyowon Park, Suwon-si, Gyeonggi-do -. Journal of Environmental Science International 26(9): 1057-1072. https://doi.org/10.5322/JESI.2017.26.9.1057
  24. Piao, Y. (2017) Analysis of Relationship between Green Space Distribution and Temperature in Cheongju Using Landsat Data. Master Thesis. Korea National University of Education. Korea.
  25. Yoon, G. H. (2012) A Study on Apartment Housing Model Development for Mitigation of Urban Heat Island Effect. Master Thesis. ChungAng University. Korea.
  26. Yoon, M. H. and T. M. Ahn(2009). An application of satellite image analysis to visualize the effects of urban green areas on temperature. Journal of the Korean Institute of Landscape Architecture 37(3): 46-53.
  27. Yun, H. C., M. K. Kim and K. Y. Jung(2013) Analysis of temperature change by forest growth for mitigation of the urban heat island. Journal of the Korean Society of Surveying Geodesy Photogrammetry and Cartography 31(2): 143-150. https://doi.org/10.7848/ksgpc.2013.31.2.143