苏州工业园区绿地分布驱动因子及优化路径^*

Driving Factors and Optimization Paths to Green Space Distribution in Suzhou Industrial Park

摘要

【目的】 科学识别高密度工业园区绿地分布空间分异的动态驱动因子、 解析其非线性作用机制， 构建空间响应式优化框架， 为 《苏州国土空间总体规划 (2021—2035) 》 的绿地分布的存量优化提供分区调控依据。【方法】 基于地理空间数据分析平台与 Landsat8/9 遥感影像， 提取苏州工业园区 2020—2022 年 GSD 数据； 在人文－自然协同驱动下， 结合随机森林模型与偏依赖分析解析驱动因子的时空分异规律及优化路径。【结果】 耕地的生态支撑功能增强， 其特征重要性 (IncMSE%) 从 2020 年 104.77%增至 2022 年 162.46% ； 坡度、 降水量等自然因子重要性明显提升， 说明高密度建成区的绿地布局需重视微地形条件与水文特征的适配； 地表温度在工业带呈阈值效应； 城市化指标重要性下降反映存量规划转型。【结论】 耕地重要性随土地策略优化而增强， 地形－水文协同效应对工业型城市 GSD 影响凸显， 城市化指标随规划转型作用减弱。 因此， 高密度工业园区绿地分布优化应重点强化耕地 (CL) 的生态支撑功能、 优化地形与水文适应性绿化、 提升绿地对热环境 (LST) 的调控能力。

Abstract

【Objective】 This study constructs a space-responsive optimization framework for identifying the dynamic driving factors to the spatial differentiation of green space distribution (GSD) in high-density industrial parks and analyzing their nonlinear action mechanism, aiming to provide a basis for partitioned regulation for the optimization of green space distribution proposed in the Suzhou Territorial Spatial Master Plan (2021-2035). 【Method】 Based on the Geospatial Data Analysis Platform (Google Earth Engine, GEE) and Landsat 8/9 remote sensing images, GSD data on Suzhou Industrial Park from 2020 to 2022 are extracted. Under the synergistic humanistic and natural driving pattern, the Random Forest (RF) model combined with Partial Dependence Plot (PDP) is used to analyze the spatiotemporal differentiation patterns of the driving factors. 【Result】 Arable land has its ecological support function enhanced, and its feature importance (IncMSE%) increased from 104.77% in 2020 to 162.46% in 2022. The importance of natural factors such as slope and precipitation significantly increases, suggesting that the green space layout in high-density built-up areas should focus on the alignment of micro-topographic conditions and hydrological features. Surface temperature (LST) shows a threshold effect in the industrial belt. The decline in the importance of urbanization indicators reflects the transition to stock planning. 【Conclusion】 The importance of arable land has been enhanced with the optimization of land strategy. The synergy effect of terrain and hydrology has a more prominent influence on the GSD of industrialized cities. Urbanization indicators weaken with the transformation of planning. Therefore, the optimization of green space distribution in high-density industrial parks should focus on enhancement of the ecological support function of arable land, optimization of the greening adapted to terrain and hydrology and improvement of the regulation ability of green spaces on the thermal environment.

关键词

绿地分布 / 随机森林 / 驱动机制 / 苏州工业园

Key words

green space distribution / random forest / driving mechanism / Suzhou Industrial Park

参考文献

[1] GÓMEZ—BAGGETHUN E, BARTON D N. Classifying and valuing ecosystem services for urban planning[J]. Ecological Economics, 2013, 86: 235-245.

[2] HAALAND C, VAN DEN BOSCH C K. Challenges and strategies for urban green—space planning in cities undergoing densification: A review[J]. Urban Forestry & Urban Greening, 2015, 14(4): 760-771.

[3] LI F, ZHOU T, LAN F. Relationships between urban form and air quality at different spatial scales: a case study from northern China[J]. Ecological Indicators, 2021, 121: 107029.

[4] 徐雨涵, 林乙煌, 杨鸿辉, 等 . 海岛型城市绿地景观格局与热环境的作用机制研究[J]. 西北林学院学报, 2025, 40: 273-284.

[5] DUNLOP T, KHOJASTEH D, COHEN—SHACHAM E, et al. The evolution and future of research on Nature—based Solutions to address societal challenges[J]. Communications Earth & Environment, 2024, 5(1): 132.

[6] 刘杰, 张浪, 张青萍. 城市绿地系统进化特征及驱动机制分析: 以河南省许昌市为例[J]. 南京林业大学学报(自然科学版), 2024, 48(03): 275-284.

[7] 李志杰, 黄贵超, 马訾懿, 等 . 基于土地利用变化的城市生境质量时空分异格局及影响因素[J]. 中国城市林业, 2024, 22: 135-143.

[8] DUAN Z W, HUANG L B, ZHU Z C, et al. Transformation and inequity of urban green space in Guangzhou: drivers and policy implications under rapid urbanization[J]. Sustainability, 2025, 17(5): 2217.

[9] YAN S Y, TANG J. Optimization of green space planning to improve ecosystem services efficiency: the case of Chongqing urban areas[J]. International Journal of Environmental Research and Public Health, 2021, 18(16): 8441— 8441.

[10] ZHOU X C, ZOU X F, XIONG W. Optimization of urban green space in Wuhan based on machine learning algorithm from the perspective of healthy city[J]. Frontiers in Public Health, 2025, 13: 1490857— 1490857.

[11] 赵海霞, 王淑芬, 孟菲, 等 . 绿色空间格局变化及其驱动机理: 以南京都市区为例[J]. 生态学报, 2020, 40: 7861-7872.

[12] 中衡设计集团股份有限公司. 喜讯丨苏州工业园区合创产业园开工[EB/OL] (2024—04—22) [2026—05—12] http://www.artsgroup.cn/en/ennews/enoodNews/2024—04—22/834.html

[13] 刘阳, 欧小杨, 郑曦. 整合绿地结构与功能性连接分析的城市生物多样性保护规划[J]. 风景园林, 2022, 29(01): 26-33.

[14] 王嘉丽, 冯婧珂, 杨元征, 等 . 南宁市主城区不透水面与热环境效应的空间关系研究[J]. 生态环境学报, 2023, 32: 525-534.

[15] 俞孔坚, 段铁武, 李迪华, 等 . 景观可达性作为衡量城市绿地系统功能指标的评价方法与案例[J]. 城市规划, 1999, 23(8): 7-10, 42, 63.

[16] 奥勇, 张亦恒, 王晓峰, 等 . 基于景观指数的关中地区耕地细碎化程度的时空变迁及其驱动因素[J]. 水土保持研究, 2024, 31: 401-411.

[17] MANSOUR MOGHADDAM M, ROUSTAI I, GHAFARIAN MALAMIRI H, et al. Modeling and estimating the land surface temperature (LST) using remote sensing and machine learning (Case study: Yazd, Iran)[J]. Remote Sensing, 2024, 16(3): 454.

[18] 周业泽, 高远, 裴阳, 等 . 基于 AHP—GIS 的地表基质适宜性评价: 以吉林省双辽—东丰地区为例[J]. 地质与资源, 2024, 33: 802-812.

[19] RODGERS J L, NICEWANDER W A. Thirteen ways to look at the correlation coefficient[J]. The American Statistician, 1988, 42(1): 59-66.

[20] BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.

[21] KRZYWINSKI M, ALTMANN N. Classification and regression trees[J]. Nature Methods, 2017, 14(8): 757-758.

[22] YAN Y C, JU H R, ZHANG S R, et al. Spatiotemporal patterns and driving forces of urban expansion in coastal areas: a study on urban agglomeration in the Pearl River Delta, China[J]. Sustainability, 2020, 12(1): 191.

[23] WANG X H, PALAZZO D, CARPER M. Ecological wisdom as an emerging field of scholarly inquiry in urban planning and design[J]. Landscape and Urban Planning, 2016, 155: 100-107.

[24] BOWLER D E, BUYUNG—ALI L, KNIGHT T M, et al. Urban greening to cool towns and cities: a systematic review of the empirical evidence[J]. Landscape & Urban Planning, 2010, 97(3): 147-155.

[25] 李京涛, 周生路, 吴绍华. 道路交通网络与城市土地利用时空耦合关系: 以南京市为例[J]. 长江流域资源与环境, 2014, 23(01): 18-25.

[26] 高静, 龚健, 李靖业. “源—汇” 景观格局的热岛效应研究: 以武汉市为例[J]. 地理科学进展, 2019, 38(11): 1770-1782.

[27] SETO K C, GÜNERALP B, HUTYRA L R. Global forecasts of urban expansion to 2030 and direct impacts on biodiversity and carbon pools[J]. Proceedings of the National Academy of Sciences of the United States of America, 2012, 109(40): 16083-16088.

基金资助

*中国博士后面上基金(2023M741758)

江苏高校哲学社会科学研究重大项目(2023SJZD131)

江苏镇江市科技计划 (软科学) 基金(YJ2024008)