基于PLUS-CatBoost-SHAP模型的喀斯特地区城市不透水面扩张多情景模拟及其影响因素

Multi-Scenario simulation of urban impervious surface expansion and its driving factors in karst regions based on PLUS-CatBoost-SHAP model

摘要

城市不透水面扩张是影响喀斯特地区可持续发展的关键因素,厘清其时空演变特征与驱动因素对协调城市发展与生态保护具有重要意义。本研究以典型喀斯特城市贵阳市为例,构建基于PLUS-CatBoost-SHAP的多模型集成框架,系统分析1990—2020年不透水面时空演变规律,模拟SSP-RCP多情景下(SSP1-2.6、SSP2-4.5、SSP5-8.5)至2035年的扩张趋势,并定量解析其非线性关系及阈值效应的驱动机制。结果表明:1)1990—2020年间,不透水面面积由66.91 km²增至264.87 km²,扩张近4倍,空间重心持续向东北迁移,扩张趋势由单核转向多核心模式转变。2)未来情景模拟显示,SSP5-8.5情景到2035年不透水面达424.43 km²,较SSP1-2.6情景扩张幅度高出25.7%,存在突破生态保护红线的风险。3)驱动因素分析显示,主要驱动因素贡献度表现为人口密度(29.40%)>基岩深度(11.28%)>GDP(8.68%)>NDVI(8.43%),呈现显著非线性与阈值效应。其中,人口密度＞20 000人/km²后扩张速率趋缓,基岩深度＞18 m时扩张趋势显著提升,NDVI＞0.6对扩张趋势起到明显空间约束作用。本研究利用创新性耦合多模型方法,揭示了喀斯特城市不透水面扩张的时空演变及其复杂驱动因素,研究结果可为喀斯特城市国土空间优化、生态安全管控及应对气候变化提供科学依据。

Abstract

Urban impervious surface expansion is a critical factor affecting sustainable development in karst regions.Understanding its spatiotemporal evolution and driving mechanisms is essential for balancing urban growth with ecological conservation.This study employs an integrated PLUS-CatBoost-SHAP modeling framework to systematically analyze the spatiotemporal patterns of impervious surface expansion in Guiyang,a typical karst city,from 1990 to 2020,simulate its future trends under multiple SSP-RCP scenarios (SSP1-2.6,SSP2-4.5,SSP5-8.5) in 2035,and quantitatively identify the driving factors.The results indicate that:1) The impervious surface area expanded nearly fourfold from 66.91 km² to 264.87 km² during 1990—2020,with the spatial centroid consistently shifting northeastward and the expansion pattern transitioning from monocentric to polycentric.2) Scenario projections reveal that under the SSP5-8.5 scenario,the impervious surface area will have reached 424.43 km² by 2035,which is 25.7% higher than that under the SSP1-2.6 scenario,posing a risk of breaching ecological conservation redlines.3) The driving factors,in descending order of contribution,are population density (29.40%),bedrock depth (11.28%),GDP (8.68%),and NDVI (8.43%),all exhibiting significant nonlinear and threshold effects.Specifically,the expansion rate slows when population density exceeds 20 000 persons/km²,bedrock depth greater than 18 m significantly promotes expansion,and NDVI higher than 0.6 imposes substantial spatial constraints on expansion.This study innovatively integrates multiple models to unravel the complex driving mechanisms behind impervious surface expansion in karst cities,providing a scientific basis for spatial optimization,ecological security management,and climate change adaptation in karst urban areas.

关键词

不透水面 / 时空演变 / 影响因素 / CatBoost-SHAP模型 / 多情景模拟 / 喀斯特城市

Key words

impervious surfaces / spatiotemporal evolution / driving factors / CatBoost-SHAP model / multi-scenario simulation / karst city

[1] 王美雅,徐涵秋,付伟,等.城市地表水体时空演变及其对热环境的影响[J].地理科学,2016,36(7):1099-1105.
[2] 徐涵秋,王美雅.地表不透水面信息遥感的主要方法分析[J].遥感学报,2016,20(5):1270-1289.
[3] Ren Qiang,He Chunyang,Huang Qingxu,et al.Impacts of urban expansion on natural habitats in global drylands[J].Nature Sustainability,2022,5(10):869-878.
[4] 庞萬隆,冀鹏浩,庞立东,等.内蒙古大兴安岭土地利用格局和生态系统服务功能的时空演变特征[J].水土保持通报,2024,44(4):340-351.
[5] Peng Jian,Tian Lu,Zhang Zimo,et al.Distinguishing the impacts of land use and climate change on ecosystem services in a karst landscape in China[J].Ecosystem Services,2020,46:101199.
[6] 李志,李鹏,刘强.长江中游大城市不透水面增长模式及其驱动因素[J].生态学报,2018,38(11):3766-3774.
[7] 牟凤云,朱诗柔,左丽君.基于不透水面与夜间灯光的城市建成区时空演变分析[J].自然资源遥感,2025,37(4):108-117.
[8] Sun Zhongchang,Du Wenjie,Jiang Huiping,et al.Global 10 m impervious surface area mapping:a big earth data based extraction and updating approach[J].International Journal of Applied Earth Observation and Geoinformation,2022,109:102800.
[9] 马玉林,吴华,高丽萍,等.1988—2021年拉萨市城关区不透水面时空变化遥感监测[J].高原科学研究,2022,6(1):48-55.
[10] Cui Yuyang,Zhao Yaxue,Li Xuecao.Long-term time series estimation of impervious surface coverage rate in Beijing-Tianjin-Hebei urbanization and vulnerability assessment of ecological environment response[J].Land,2025,14(8):1599.
[11] Wang Shanshan,Pu Yingxia,Li Shengfeng,et al.Spatio-temporal analysis of impervious surface expansion in the Qinhuai River Basin,China,1988—2017.[J].Remote Sensing,2021,13(22):4494.
[12] Huang Xin,Li Jiayi,Yang Jie,et al.30 m global impervious surface area dynamics and urban expansion pattern observed by Landsat satellites:from 1972 to 2019[J].Science China Earth Sciences,2021,64(11):1922-1933.
[13] Gong Peng,Li Xuecao,Wang Jie,et al.Annual maps of global artificial impervious area (GAIA) between 1985 and 2018[J].Remote Sensing of Environment,2020,236:111510.
[14] Liang Xun,Guan Qingfeng,Clarke K C,et al.Understanding the drivers of sustainable land expansion using a patch-generating land use simulation (PLUS) model:a case study in Wuhan,China[J].Computers,Environment and Urban Systems,2021,85:101569.
[15] Zhang Shengqing,Yang Peng,Xia Jun,et al.Land use/land cover prediction and analysis of the middle reaches of the Yangtze River under different scenarios[J].Science of The Total Environment,2022,833:155238.
[16] 郭桓超,何湜,闫戈丁,等.基于PLUS的太行山地区土地覆盖时空变化及预测[J].天津师范大学学报(自然科学版),2025,45(4):60-67.
[17] 王克晓,周蕊.近25年重庆主城区不透水面变化与驱动力分析[J].山地学报,2023,41(4):521-531.
[18] 周鹏,谢元礼,高志远,等.西安市不透水面的变化及其驱动力[J].水土保持通报,2020,40(3):274-281.
[19] 李益敏,杨舒婷,吴博闻,等.昆明市呈贡区不透水面时空变化及驱动力分析[J].自然资源遥感,2022,34(2):136-143.
[20] Atkinson P M,German S E,Sear D A,et al.Exploring the relations between riverbank erosion and geomorphological controls using geographically weighted logistic regression[J].Geographical Analysis,2003,35(1):58-82.
[21] Brunsdon C,Fotheringham A S,Charlton M E.Geographically weighted regression:a method for exploring spatial nonstationarity[J].Geographical Analysis,2010,28(4):281-298.
[22] Wang Jinfeng,Li Xinhu,Christakos G,et al.Geographical detectors-based health risk assessment and its application in the neural tube defects study of the Heshun region,China[J].International Journal of Geographical Information Science,2010,24(1/2):107-127.
[23] Cheng Yue,Luo Peng,Yang Hao,et al.Land use and cover change accelerated China's land carbon sinks limits soil carbon[J].NPJ Climate and Atmospheric Science,2024,7(1):199.
[24] Su Rui,Duan Cuncun,Chen Bin.The shift in the spatiotemporal relationship between supply and demand of ecosystem services and its drivers in China[J].Journal of Environmental Management,2024,365:121698.
[25] Lundberg S M,Lee S I.A unified approach to interpreting model predictions[J].Advances in neural information processing systems,2017,30:21889700.
[26] Huang Junda,Wang Yuncai.Ventilation potential simulation based on multiple scenarios of land-use changes catering for urban planning goals in the metropolitan area[J].Journal of Cleaner Production,2024,483:144301.
[27] Fan Liyao,Cai Tianyi,Wen Qian,et al.Scenario simulation of land use change and carbon storage response in Henan Province,China:1990—2050[J].Ecological Indicators,2023,154:110660.
[28] Ma Xiaoni,Li Zhanbin,Ren Zongping,et al.Predicting future impacts of climate and land use change on streamflow in the middle reaches of China's Yellow River[J].Journal of Environmental Management,2024,370:123000.
[29] Zhang Jinting,Yang Kui,Wu Jingdong,et al.Scenario simulation of carbon balance in carbon peak pilot cities under the background of the "dual carbon" goals[J].Sustainable Cities and Society,2024,116:105910.
[30] Fu Qi,Hou Ying,Wang Bo,et al.Scenario analysis of ecosystem service changes and interactions in a mountain-oasis-desert system:a case study in Altay Prefecture,China[J].Scientific Reports,2018,8(1):12939.
[31] 赵克飞,邵铮,姚晓华,等.共享社会经济路径(SSPs)下广东省城镇化情景演化及其对陆地碳储量的影响评估[J].环境科学,2025,46(10):6512-6521.
[32] 刘宝涛.京津冀城市群建设用地转型的时空演化与驱动因素[J].世界地理研究,2025,34(7):98-111.
[33] Chen Tianqi,Guestrin G.Xgboost:a scalable tree boosting system[C]//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.2016:785-794.
[34] Zhao Chunhong,Zhang Huabo,Wang Haiying,et al.Analysis of changes in the spatiotemporal characteristics of impervious surfaces and their influencing factors in the Central Plains Urban Agglomeration of China from 2000 to 2018[J].Heliyon,2023,9(8):e18849.
[35] 周正龙,沙晋明,范跃新,等.厦门市不透水面景观格局时空变化及驱动力分析[J].应用生态学报,2020,31(1):230-238.
[36] 卢罡,栗雪,石予童,等.城市复杂系统中居住空间与人口分布的时空耦合演化研究[J].系统科学学报,2026,34(2):1-8
[37] 张晓波,刘凯,蒋鹏,等.基于约束条件的深圳市南山区地下空间开发地质适宜性评价[J].水文地质工程地质,2023,50(4):213-224.
[38] 刘志佳,黄河清.珠三角地区建设用地扩张与经济、人口变化之间相互作用的时空演变特征分析[J].资源科学,2015,37(7):1394-1402.
[39] 黄万状,石培基,尹君锋.河湟地区城市体系空间网络结构的演变特征[J].干旱区资源与环境,2024,38(10):80-90.
[40] 冯贵苗,席广亮,王进.要素协同视角的都市圈空间范围划定及圈层分析:以南京都市圈为例[J].新疆师范大学学报(自然科学版),2026,45(1):1-10.
[41] Ju Xinhui,Li Weifeng,He Liang,et al.Ecological redline policy may significantly alter urban expansion and affect surface runoff in the Beijing-Tianjin-Hebei megaregion of China[J].Environmental Research Letters,2020,15(10):1040b1.
[42] Luan Chaoxu,Liu Renzhi,Sun Jing,et al.An improved future land:use simulation model with dynamically nested ecological spatial constraints[J].Remote Sensing,2023,15(11):2921.
[43] Zhang Jincai,Li Ling,Li Qingsong,et al.Multiscenario land use change simulation and its impact on ecosystem service function in Henan Province based on FLUS-InVEST model[J].Ecology and Evolution,2025,15(3):e71111.
[44] He Yating,Liang Youjia,Liu Lijun,et al.Loss of green landscapes due to urban expansion in China[J].Resources,Conservation and Recycling,2023,199:107228.
[45] Xu Feng,Wang Zhanqi,Chi Guangqing,et al.The impacts of population and agglomeration development on land use intensity:new evidence behind urbanization in China[J].Land Use Policy,2020,95:104639.
[46] Liu Shuangshuang,Liao Qipeng,Liang Yuan,et al.Spatio-temporal heterogeneity of urban expansion and population growth in China[J].International Journal of Environmental Research and Public Health,2021,18(24):13031.
[47] Vierrether C B.Urban development in karst and collapse-prone geologic environments[J].Carbonates and Evaporites,2013,28(1):23-29.

基金资助

贵州省科技支撑计划项目(黔科合支撑[2023]一般226);国家自然科学基金(U24A20579);贵州省高等学校遥感卫星人工智能应用工程研究中心(黔教技[2023]039号)