城市空间形态与夏季地表温度关系及其响应阈值研究——以天津市中心城区为例  

Relationship between urban spatial morphology factors and land surface temperature in summer:A case of the central district of Tianjin

作　　者：宋鑫博 李根 梁冬坡[1] 黄鹤[1] 郭军[1] Song Xinbo;Li Gen;Liang Dongpo;Huang He;Guo Jun(Tianjin Climate Center,Tianjin 300074,China)

机构地区：[1]天津市气候中心,天津300074

出　　处：《地理科学》2023年第2期360-369,共10页Scientia Geographica Sinica

基　　金：国家重点研发计划项目(2018YFA0606300)资助。

摘　　要：以天津中心城区为研究区,利用遥感及GIS技术反演关键空间形态指标和地表温度,并基于线性回归模型和Cubist模型深入剖析了建筑密度、容积率、高度、天空开阔度等空间形态指标与地表温度的关系,明确了关键指标的响应阈值。研究发现:(1)建筑高度与地表温度间存在分段线性关系,高度响应阈值为13.5 m;天空开阔度与地表温度线性负相关;建筑密度、容积率与地表温度线性正相关。(2)Cubist模型将建筑密度阈值划定为13%,将高度阈值划定为9.9 m,并建立了3种子规则,其中规则1表明低开发强度场景下建筑密度为正贡献因素;规则2表明中等开发强度场景下容积率为正贡献因素;规则3表明高开发强度场景下建筑密度、容积率属于正向贡献因素,建筑高度、天空开阔度属于负贡献因素。(3)Cubist模型依据自变量阈值划分规则子区,并分区建立自变量与因变量的线性关系,表现出比全局回归模型更强的适用性。This study uses RS and GIS technique to invert key spatial morphology factors and land surface temperature in the central district of Tianjin.Based on linear regression model and the Cubist model,an indepth analysis of the relationship between spatial morphology factors(i.e.building density,floor area ratio,building height,and sky view factor)and land surface temperature is accomplished,and the thresholds of key morphology factors are clarified.This study finds that:1)There is a piecewise linear relationship between building height and land surface temperature,and the response threshold for the mutant change is 13.5 meters;There is a linear negative correlation between sky view factor and land surface temperature.Both building density and floor area ratio show a linear positive correlation with land surface temperature.2)The Cubist model delineates threshold of building density as 13%and sets the threshold of building height as 9.9 meters.Three sub-rules are established:Rule 1 shows that building density is a positive contributing factor for low development intensity scenarios;Rule 2 shows floor area ratio is a positive contributing factor for medium development intensity scenario;Rule 3 shows that building density and floor area ratio belong to the positive contributing factors,while building height and sky view factor are negative contributing factors for high development intensity scenarios.3)The Cubist model is more applicable than the global regression model,and it establishes a linear relationship between independent variables and dependent variables for subarea representing different rules which is partitioned by the thresholds of independent variables.

关 键 词：空间形态 地表温度 Cubist模型 热岛效应 天津市中心城区 响应阈值 

分 类 号：X16[环境科学与工程—环境科学]