人为管护因素哑变量对行道树国槐胸径-树高模型精度的影响——以北京市中心城区为例  

Influence of Dummy Variables of Artificial Management Measures on Accuracy of DBH-Height Model of Styphnolobium japonicum Street Tree:A Case Study of the City Core of Beijing

作　　者：王欣冉 孙妍 徐程扬[1] Wang Xinran;Sun Yan;Xu Chengyang(Key Laboratory of Ministry of Education for Forest Cutivation and Conservation,Institute of Urban Forestry,College of Forestry,Beijing Forestry University,Beijing 100083,China)

机构地区：[1]北京林业大学林学院城市林业研究所森林培育和保护教育部重点实验室,北京100083

出　　处：《中国城市林业》2024年第3期16-25,共10页Journal of Chinese Urban Forestry

基　　金：北京市自然科学基金项目(8222067);国家自然科学基金项目(41801058);北京林业大学“5·5工程”科研创新团队项目(BLRC2023B06)。

摘　　要：为明晰特大城市都市区城市树木人为管护因素对行道树国槐的胸径-树高关系的影响,拟构建以人为管护因素为哑变量的行道树国槐胸径-树高关系模型,根据2022年北京市中心城区行道树的抽样调查,取得685株行道树国槐的实测数据,结合文献中的12个模型,通过决定系数(R2)、平均预估误差(MPE)、赤池信息准则(AIC)、均方根误差(RMSE)4个评价指标,筛选出最优基础模型,分析7种典型城市环境中的人为管护因素对行道树国槐胸径、树高的影响。结果表明:1)模型M2(R2=0.647,MPE=-2.241%,AIC=600.726,RMSE=1.683)综合拟合程度最优。2)地面防踩踏护网设置、建筑遮光和树池边长显著影响国槐胸径(P<0.05);涂白保护、地面防踩踏护网设置和建筑遮光情况、垂直结构以及树池边长显著影响国槐树高(P<0.05);株距和邻近树种的差异对国槐的胸径、树高生长影响不显著(P>0.05)。3)在模型中引入代表地面防踩踏保护、树木涂白、建筑遮光和树池边长的哑变量后,模型精度明显提升,R2提升15.8%,MPE缩小29.5%,AIC值降低29.0%,RMSE值降低15.0%。因此,将人为管护因素作为哑变量引入国槐胸径-树高模型可以有效提高模型的拟合精度与适用性,可为未来行道树的科学栽植、管护以及碳储量评估等提供理论基础。In order to clarify the influence of the factors to artificial urban tree management on the DBH(diameter at breast height)-H(tree height)relationship of Styphnolobium japonicum street tree in mega-cities,a DBH-H relationship model for Styphnolobium japonicum street tree is proposed to be constructed with the artificial management factors as dummy variables.According to the sampling survey of street trees in the city core of Beijing in 2022,the measured data of 685 Styphnolobium japonicum street trees are obtained.Combined with 12 models drawn from in literature,the optimal basic model is selected based on four evaluation indexes including determination coefficient(R^(2)),mean prediction error(MPE),Akaike information criterion(AIC),and root mean square error(RMSE).The effects of seven factors to artificial management in a typical urban environment on the DBH and the tree height of S.japonicum are analyzed.The results show that:1)Model M2(R^(2)=0.647,MPE=-2.241%,AIC=600.720,RMSE=1.683)has the best comprehensive fitting degree;2)The installation of anti-trampling ground nets,the shading of buildings and the side length of tree grates significantly affect the DBH growth of Styphnolobium japonicum(P<0.05).Whitewashing protection,the installation of anti-trampling ground nets,buildings'shading,vertical structure,and the side length of tree grates significantly affect the height of Styphnolobium japonicum(P<0.05).The differences in plant spacing and adjacent tree species have no significant effect on DBH and tree height(P>0.05);and 3)After introducing the dummy variables of anti-trampling ground protection,whitewashing,buildings'shading,and tree grates'side length into the model,its accuracy is significantly improved,while R^(2) increases by 15.8%,MPE decreases by 29.5%,AIC value decreases by 29.0%,and RMSE value decreases by 15.0%.Therefore,the introduction of artificial management factors as dummy variables into the DBH-H model of Styphnolobium japonicum can effectively improve the fitting accuracy and applicability o

关 键 词：国槐 行道树 生长模型 哑变量 树干涂白保护 地面防踩踏保护 

分 类 号：S687.1[农业科学—观赏园艺]