Skip navigation

DSpace JSPUI

DSpace preserves and enables easy and open access to all types of digital content including text, images, moving images, mpegs and data sets

Learn More
DSpace logo
English
中文
  • Browse
    • Communities
      & Collections
    • Publication Year
    • Author
    • Title
    • Subject
    • Advisor
  • Search TDR
  • Rights Q&A
    • My Page
    • Receive email
      updates
    • Edit Profile
  1. NTU Theses and Dissertations Repository
  2. 工學院
  3. 土木工程學系
Please use this identifier to cite or link to this item: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96741
Title: 地表都市熱島效應的關鍵因子之量化分析 —以桃園市為例
Quantitative Analysis of Key Impact Factors Influencing Surface Urban Heat Islands: A case study of Taoyuan
Authors: 黃瀞儀
Jing-Yi Huang
Advisor: 韓仁毓
Jen-Yu Han
Keyword: 地表都市熱島,地表溫度,遙感探測,隨機森林,都市規劃,
Surface Urban Heat Island,Remote Sensing,Random Forest,Urban Planning,Environmental Management,
Publication Year : 2024
Degree: 碩士
Abstract: 本研究結合遙測技術、地理資訊系統與機器學習模型,探討地表都市熱島的形成機制與關鍵驅動因子,並提出針對性緩解建議。以桃園市為研究區域,採用2019年至2023年夏季的多源遙測資料,結合多維環境因子(如建築密度、道路密度、植被覆蓋、空氣品質等)並配合進行地表溫度反演和都市熱場變異指數的計算,分析地表都市熱島的空間分佈特性與強度。

地表使用與覆蓋、地表高程、歸一化水體指數和空氣品質是影響地表都市熱島效應的主要驅動因子,其中不同發展密度區域的影響因子權重與作用機制存在顯著差異。高發展密度區域主要受建築密度、地表高程和空氣品質影響,而中發展密度區域則由植被與水體覆蓋主導,低發展密度區域受粗糙長度與建物密度對熱島效應的作用更為顯著。透過隨機森林模型,量化了各影響因子的重要性,並應用SHAP值進一步解釋模型預測的內在機制,為影響因子與熱島效應之間的因果關係提供了詳細解析。

本研究建立了一套整合地表都市熱島影響因子與機器學習的地表都市熱島效應分析方法,針對不同發展密度區域提出差異化的緩解建議,包括提升植被覆蓋率、優化建築布局與改善空氣品質等。本研究的成果可為都市規劃和環境管理提供實證支持,助力推動都市的永續發展。
This study integrates remote sensing, GIS, and machine learning to explore the formation mechanisms and key drivers of surface urban heat islands, proposing targeted mitigation measures. Using multi-source remote sensing data from Taoyuan City (2019–2023 summers), it examines how building density, road density, vegetation cover, and air quality affect land surface temperature and urban thermal variation.

Results show that land use/cover, surface elevation, normalized difference water index, and air quality are major drivers. High-density areas are shaped mainly by building density, elevation, and air quality, while vegetation and water coverage dominate medium-density areas. In low-density areas, roughness length and building density have stronger impacts. A random forest model quantifies factor importance and uses SHAP values for deeper insights. These findings inform different mitigation strategies—such as boosting vegetation, optimizing building layouts, and improving air quality—that can guide sustainable urban development.
URI: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96741
DOI: 10.6342/NTU202404786
Fulltext Rights: 未授權
metadata.dc.date.embargo-lift: N/A
Appears in Collections:土木工程學系

Files in This Item:
File SizeFormat 
ntu-113-1.pdf
  Restricted Access
11.28 MBAdobe PDF
Show full item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved