基于景观图式特征的低等级公路美学质量评估  

Assessing the Aesthetic Quality of Low-Grade Highways Based on the Aesthetic Features of Landscape Schema

作　　者：姚思喆 陈雨人[1] 余博[1] 何丽 YAO Sizhe;CHEN Yuren;YU Bo;HE Li(The Key Laboratory of Road and Traffic Engineering,Ministry of Education,Tongji University,Shanghai 201804,China)

机构地区：[1]同济大学道路与交通工程教育部重点实验室,上海201804

出　　处：《交通与运输》2025年第2期29-35,共7页Traffic & Transportation

摘　　要：为提升低等级公路美学质量评估的客观性和高效性,通过分析语义、色彩与纹理三类景观图式特性(包括多样性、统一性及对称性),并结合XGBoost算法与SHAP算法构成可解释机器学习框架,进而实现公路美学质量的定量计算。结果表明:所提出的方法能有效评估低等级公路的整体美学质量,并生成相应美学分数;该方法具有较高可解释性,能为低等级公路的美学优化设计提供技术支持。To improve the objectivity and efficiency of the assessment method for the aesthetic quality of low-grade highways,aesthetic features(i.e.,diversity,unity,and symmetry)of semantic,color,and texture landscape schema are analyzed.Interpretable machine learning methods(XGBoost and SHAP)are adopted to achieve the quantitative calculation of lowgrade highways’aesthetic quality.The results show that the proposed method can effectively assess the overall aesthetic quality of low-grade highways and generate the corresponding overall aesthetic scores.Furthermore,this method has a high interpretability,which provides strong support for optimizing the design of low-grade highways.

关 键 词：低等级公路 美学质量 可解释机器学习 景观图式 美学特征 

分 类 号：U491[交通运输工程—交通运输规划与管理]