Recognition and spatio-temporal evolution analysis of production-living-ecological spaces based on the random forest model: A case study of Zhengzhou city, China
ZHAO Hongbo,1, WEI Jiachen,1, SUN Dongqi2, LIU Yaxin1, WANG Shuang1, TAN Juntao3, MIAO Changhong11. Key Research Institute of Yellow River Civilization and Sustainable Development & Collaborative Innovation Center on Yellow River Civilization jointly built by Henan Province and Ministry of Education, Henan University, Kaifeng 475001, Henan, China 2. Key Laboratory of Regional Sustainable Development Modeling, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China 3. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, Jiangsu, China
Abstract Based on the POI data of Zhengzhou city in 2007 and 2017, the “production-living-ecological” spaces within the city was identified by using random forest model and quadrat proportion method, and the spatial-temporal evolution of “production-living-ecological” spaces in the study area was examined by using nuclear density and other methods. The results show that: First, as a new machine learning algorithm, random forest model can identify “production-living-ecological” spaces with high accuracy. Second, the spatial distribution pattern of “production-living-ecological” spaces in Zhengzhou matched with the urban functional zoning. The production space was concentrated in the industrial agglomeration area, the living space was located in the central urban area with a plane shape, and the ecological space was distributed in a scatter pattern as a whole. Finally, with the development of urbanization and the improvement of infrastructure in Zhengzhou, the spatial distribution pattern of “production-living-ecological” spaces in the city was more reasonable in the past 10 years. The production space was concentrated in the industrial agglomeration area, the living space was gradually dispersed, and the ecological spatial distribution was more balanced. Based on POI data, the method of random forest model to identify “production-living-ecological” spaces within the city was more effective, and the recognition results were more accurate, which can provide data and method support for territorial spatial planning on a smaller scale. Keywords:production-living-ecological space;random forest model;POI data;Zhengzhou
PDF (4805KB)元数据多维度评价相关文章导出EndNote|Ris|Bibtex收藏本文 本文引用格式 赵宏波, 魏甲晨, 孙东琪, 刘雅馨, 王爽, 谭俊涛, 苗长虹. 基于随机森林模型的“生产-生活-生态”空间识别及时空演变分析——以郑州市为例. 地理研究[J], 2021, 40(4): 945-957 doi:10.11821/dlyj020200237 ZHAO Hongbo, WEI Jiachen, SUN Dongqi, LIU Yaxin, WANG Shuang, TAN Juntao, MIAO Changhong. Recognition and spatio-temporal evolution analysis of production-living-ecological spaces based on the random forest model: A case study of Zhengzhou city, China. Geographical Research[J], 2021, 40(4): 945-957 doi:10.11821/dlyj020200237
近年来,随着地理大数据的发展,POI(point of interest)数据成为精细化分析城市空间的重要数据,也广泛应用于城市功能区的识别[12],POI描述了地理实体的空间和属性信息,如实体的名称、地址和坐标等具有大量化、快速化和多样化特点[13]。如何利用POI数据识别城市“三生空间”布局成为一个重要课题[14]。随机森林模型(random forest,RF)在生态学[15,16]、土壤学[17]和地理学[18,19]等领域均有涉及,在识别方面,赵鹏军等基于该模型算法结合多源地理大数据对地铁乘客出行目的进行识别[20],蒲东川等利用该模型优化了城镇用地提取方法[21]。可见,随机森林模型对于影响因子分析和要素识别均有明显而独特的优势,当前利用大数据对城市“三生空间”进行识别鲜有研究。本文尝试结合POI数据,利用该模型算法确定不同类型POI数据的权重,对城市内部“三生空间”进行精准识别,提高城市内部“三生空间”评价的客观性和科学性。
Tab. 5 表5 表52007年与2017年郑州市各市辖区“三生空间”的变化 Tab. 5The changes of “production-living-ecological spaces” in different districts of Zhengzhou city in 2007 and 2017
[ WangFang, AnLizhe, DangAnrong, et al. Human-land coupling and sustainable human settlements in the Yellow River Basin Geographical Research, 2020,39(8):1707-1724.] DOI: 10.11821/dlyj020200217. [本文引用: 1]
[ LiXin, YinRumeng, FangBin. Research on the functional zoning and regulation of Jiangsu province's territorial space based on the “production-living-ecological” function Resources and Environment in the Yangtze Basin, 2019,28(8):1833-1846.] DOI: 10.11870/cjlyzyyhj201908008. [本文引用: 1]
[ ChenXianchun, ZhaoJunsan, ChenGuoping. Analysis of multi-scale spatial structure of land use based on ecological-production-living spaces in urban agglomeration area of central Yunnan Research of Soil and Water Conservation, 2019,26(5):258-264.] DOI: 10.13869/j.cnki.rswc.2019.05.038. [本文引用: 1]
[ MaXiaodong, LiXin, HuRui, et al. Delineation of “production-living- ecological” space for urban fringe based on rural multifunction evaluation Progress in Geography, 2019,38(9):1382-1392.] DOI: 10.18306/dlkxjz.2019.09.011. [本文引用: 1]
[ ZhaoXu, TangFeng, ZhangPengtao, et al. Dynamic simulation and characteristic analysis of county production-living-ecological spatial conflicts based on CLUE-S model Acta Ecologica Sinica, 2019,39(16):5897-590 8.] DOI: 10.5846/stxb201901070059. [本文引用: 1]
[ HuangJinchuan, LinHaoxi, QiXiaoxiao. A literature review on optimization of spatial development pattern based on ecological-production-living space Progress in Geography, 2017,36(3):378-391.] DOI: 10.18306/dlkxjz.2017.03.014. [本文引用: 1]
[ LiuDongqing, MaXuecheng, GongJie. Function identification and spatiotemporal pattern analysis of production-living-ecological space in watershed scale: A case study of Bailongjiang Watershed in Gansu Chinese Journal of Ecology, 2018,37(5):1490-1497.] DOI: 10.13292/j.1000-4890.201805.020. [本文引用: 1]
[ LiuChunfang, WangYixuan, HeRuidong. An analysis framework for identifying and optimizing ecological-production-living space based on resident behavior Journal of Natural Resources, 2019,34(10):2113-2122.] DOI: 10.31497 /zrz yxb.20191008. [本文引用: 1]
[ ChiJiao, Jiao LiminM, DongTing, et al. Quantitative identification and visualization of urban functional area based on POI data Journal of Geomatics, 2016,41(2):68-73.] DOI: 10.14188/j.2095-6045.2016.02.017. [本文引用: 1]
[ XuZening, GaoXiaolu. A novel method for identifying the boundary of urban built-up areas with POI data Acta Geographica Sinica, 2016,71(6):928-939.] DOI: 10.11821/dlxb201606003. [本文引用: 1]
[ CaoGenrong, GuChaoyin, ZhangQiaoyang. Recognition of “ecological space, living space, and production space” in the urban central area based on POI data: The caes of Shanghai Urban Planning Forum, 2019, (2):44-53.] DOI: 10.16361/j.upf.201902005. [本文引用: 3]
[ ZhangLei, WangLinlin, ZhangXudong, et al. The basic principle of random forest and its applications in ecology: A case study of Pinus yunnanensis Acta Ecologica Sinica, 2014,34(3):650-659.] DOI: 10.5846/stxb201306031292. [本文引用: 1]
[ XiangTao, DongXianghong, GuoChao, et al. The impacts of climate change on the distribution of pelteobagrus fulvidraco by random forest model Acta Hydrobiologica Sinica, 2019,43(6):1262-1270.] DOI: 10.7541/2019.150. [本文引用: 1]
[ ZhaoYanfeng, ChengDaoquan, WuZhenfu, et al. Problem diagnosis and geographic optimization for fertilization of wheat in Henan province based on spatial analysis Acta Pedologica Sinica, 2020,57(5):1206-1218.] DOI: 10.11766/trxb201906250273. [本文引用: 1]
[ WangChao, KanAike, ZengYelong. Population distribution pattern and influencing factors in Tibet based on random forest model Acta Geographica Sinica, 2019,74(4):664-680.] DOI: 10.11821/dlxb201904004. [本文引用: 1]
Ana Cláudiados Santos Luciano, Michelle Cristina AraújoPicoli, Jansle VieiraRocha, et al. A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm , 2019,80:127-136. DOI: 10.1016/j.jag.2019.04.013. [本文引用: 1]
[ ZhaoPengjun, CaoYushu. Identifying metro trip purpose using multi-source geographic big data and machine learning approach Journal of Geo-information Science, 2020,22(9):1753-1765.] DOI: 10.12082/dqxxkx.2020.200134. [本文引用: 2]
[ PuDongchuan, WangGuizhou, ZhangZhaoming, et al. Urban area extraction based on independent component analysis and random forest algorithm Journal of Geo-information Science, 2020,22(8):1597-1606.] DOI: 10.12082/dqxxkx.2020.190385. [本文引用: 2]
[ ZhaoHongbo, YuDifei, MiaoChanghong, et al. The location distribution characteristics and influencing factors of cultural facilities in Zhengzhou based on POI data Scientia Geographica Sinica, 2018,38(9):1525-1534.] DOI: 10.132 49/j.cnki.sgs.2018.09.016. [本文引用: 2]
[ Ministry of Housing and Urban-Rural Development of the People's Republic of China. Code for classification of urban land use and planning standards of development land (GB50137-2011). Beijing: China Architecture & Building Press, 2011]. [本文引用: 2]
[ JinYu, ZhouKexin, GaoJixi, et al. Identifying the priority conservation areas for key national protected terrestrial vertebrate species based on a random forest model in China Acta Ecologica Sinica, 2016,36(23):7702-7712.] DOI: 10.5846/stxb201512082454. [本文引用: 1]
[ FangKuangnan, WuJianbin, ZhuJianping, et al. A review of technologies on random forests Statistics & Information Forum, 2011,26(3):32-38.] DOI: 10.3969/j.issn.1007-3116.2011.03.006. [本文引用: 1]
ToblerW. A computer movie simulating urban growth in the Detroit region , 1970,46(2):234-240. [本文引用: 1]
Cliff AD, Ord JK. Spatial Process: Models and Applications , 1981: 35-41. [本文引用: 1]
[ KangYuhao, WangYueyao, XiaZhujun, et al. Identification and classification of Wuhan urban districts based on POI Journal of Geomatics, 2018,43(1):81-85.] DOI: 10.14188/j.2095-6045.2016352. [本文引用: 1]