The definition of urban fringe based on multi-source data and deep learning
Received date: 2018-10-08
Request revised date: 2019-02-20
Online published: 2020-05-20
Copyright
With the development of the economy, most cities will expand continuously to the surrounding areas, thus leading to the emergence of urban fringe areas with both urban and rural characteristics. The urban fringe area, located between urban and rural areas, is the most intense area of urban land use change and one of the most likely areas for urban construction land expansion in the future. How to identify urban fringe accurately and quantitatively is of great significance for urban planning and sustainable land use. However, most existing methods about the delineation of urban fringe area is just based on one or one type of indicators, and the judgment result is too fragmented to reflect the continuity of the urban spatial structure. What's more, the urban preset boundary range, the water body and the urban green space have great interference with the judgment results of urban fringe. In view of the above problems and from multi-perspective of nature, population and social economy, this paper defines urban fringe based on deep learning and multi-source data (remote sensing image, population density and POI big data). Furthermore, the proposed method has been used to detect the urban fringe area of Guangzhou city in our experiments. The results show that: (1) This method can divide the city into urban core area, urban fringe and rural area accurately without the impact of the preset boundary range. Eventually, this way can eliminate the fragmentation caused by the internal water and green space of urban areas. (2) The results of urban fringe area are well coupled with the road network. Network distribution of the urban core area is densest, followed by the urban fringe area. (3) The spatial distribution of urban core area of Guangzhou from the experiments is reasonable and consistent with the actual situation. All in all, the proposed method can consider comprehensively multi- perspective factors and detect urban fringe effectively, thus can provide better guidance for formulation of policies for urban development, such as urban planning, sustainable development, and urban statistical analysis.
Key words: definition of urban fringe area; POI big data; deep learning; Guangzhou
LIU Xingnan , WU Zhifeng , LUO Renbo , WU Yanyan . The definition of urban fringe based on multi-source data and deep learning[J]. GEOGRAPHICAL RESEARCH, 2020 , 39(2) : 243 -256 . DOI: 10.11821/dlyj020181085
表1 城市边缘区判定的影响因子Tab. 1 The import factor of urban fringe's definition |
| 特征表现 | 影响因子 | 数据类型 |
|---|---|---|
| 土地利用 | 景观紊乱度 | 遥感数据 |
| 社会经济 | 人口 | 统计数据 |
| 餐饮业 | POI | |
| 公司企业 | POI | |
| 酒店 | POI | |
| 金融服务 | POI | |
| 科研教育 | POI |
表2 广州市城市空间结构的统计结果Tab. 2 The statistical result of urban sapce structure in Guangzhou |
| 城市空间结构类型 | 城市核心区 | 城市边缘区 | 城市外缘区 | 各区总 面积 (km2) | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 面积 (km2) | 各区百 分比(%) | 总百分 比(%) | 面积 (km2) | 各区百 分比(%) | 总百分比(%) | 面积 (km2) | 各区百 分比(%) | 总百分比(%) | ||
| 白云区 | 82.694 | 12.43 | 24.11 | 444.394 | 66.79 | 16.68 | 138.261 | 20.78 | 3.26 | 665.350 |
| 从化区 | 3.256 | 0.16 | 0.95 | 262.243 | 13.20 | 9.84 | 1 720.692 | 86.63 | 40.53 | 1 986.191 |
| 番禺区 | 41.955 | 5.44 | 12.23 | 499.051 | 64.71 | 18.73 | 230.241 | 29.85 | 5.42 | 771.248 |
| 海珠区 | 49.324 | 53.53 | 14.38 | 42.563 | 46.19 | 1.60 | 0.262 | 0.28 | 0.01 | 92.148 |
| 花都区 | 20.724 | 2.14 | 6.04 | 416.250 | 43.00 | 15.62 | 531.120 | 54.86 | 12.51 | 968.094 |
| 黄埔区 | 2.606 | 0.54 | 0.76 | 223.844 | 46.54 | 8.40 | 254.471 | 52.91 | 5.99 | 480.921 |
| 荔湾区 | 27.753 | 44.11 | 8.09 | 34.864 | 55.41 | 1.31 | 0.304 | 0.48 | 0.01 | 62.921 |
| 南沙区 | 0.007 | 0.00 | 0.00 | 173.278 | 39.48 | 6.50 | 265.643 | 60.52 | 6.26 | 438.928 |
| 天河区 | 70.282 | 51.43 | 20.49 | 60.679 | 44.40 | 2.28 | 5.695 | 4.17 | 0.13 | 136.656 |
| 越秀区 | 33.821 | 99.94 | 9.86 | 0.020 | 0.06 | 0.00 | 0.000 | 0.00 | 0.00 | 33.840 |
| 增城区 | 10.517 | 0.65 | 3.07 | 507.153 | 31.37 | 19.03 | 1 099.023 | 67.98 | 25.89 | 1 616.694 |
| 总计 | 342.938 | 100.00 | 2 664.341 | 100.00 | 4 245.712 | 100.00 | 7 252.990 | |||
注:① 各区百分比指行政区划内3个城市空间结构类型的占比;② 总百分比指3个城市空间结构类型在各区域的分布比例;③ 由于所选的全广州市行政区划差异的原因,本次采用的行政区划在南沙等地区没有包括水域部分,因此本研究的广州市总面积会低于官方统计数据。 |
| [1] |
|
| [2] |
|
| [3] |
|
| [4] |
周婕, 谢波 . 中外城市边缘区相关概念辨析与学科发展趋势. 国际城市规划, 2014,29(4):14-20.
[
|
| [5] |
姚月 . 城市边缘区构成、功能及特征探讨: 以北京市海淀区为例. 北京规划建设, 2014, ( 1):103-107.
[
|
| [6] |
涂人猛 . 城市边缘区初探: 以武汉市为例. 地理学与国土研究, 1990,6(4):38-42.
[
|
| [7] |
|
| [8] |
李世峰 . 大城市边缘区的形成演变机理及发展策略研究: 以北京市为例. 北京: 中国农业大学博士学位论文, 2005.
[
|
| [9] |
顾朝林, 陈田, 丁金宏 , 等. 中国大城市边缘区特性研究. 地理学报, 1993,60(4):317-328.
[
|
| [10] |
陈佑启 . 试论城乡交错带及其特征与功能. 经济地理, 1996,16(3):27-31.
[
|
| [11] |
程连生, 赵红英 . 北京城市边缘带探讨. 北京师范大学学报: 自然科学版, 1995, ( 1):127-133.
[
|
| [12] |
章文波, 方修琦, 张兰生 . 利用遥感影像划分城乡过渡带方法的研究. 遥感学报, 1999,3(3):199-202.
[
|
| [13] |
李世峰, 白人朴 . 基于模糊综合评价的大城市边缘区地域特征属性的界定. 中国农业大学学报, 2005, ( 3):99-104.
[
|
| [14] |
王海鹰, 张新长, 赵元 . 基于逻辑回归模型的城市边缘区界定方法研究. 测绘通报, 2010, ( 10):7-10.
[
|
| [15] |
周小驰, 刘咏梅, 杨海娟 . 西安市城市边缘区空间识别与边界划分. 地球信息科学学报, 2017,19(10):1327-1335.
[
|
| [16] |
|
| [17] |
李国杰, 程学旗 . 大数据研究: 未来科技及经济社会发展的重大战略领域: 大数据的研究现状与科学思考. 中国科学院院刊, 2012,27(6):647-657.
[
|
| [18] |
吴志峰, 柴彦威, 党安荣 , 等. 地理学碰上“大数据”: 热反应与冷思考. 地理研究, 2015,34(12):2207-2221.
[
|
| [19] |
许泽宁, 高晓路 . 基于电子地图兴趣点的城市建成区边界识别方法. 地理学报, 2016,71(6):928-939.
[
|
| [20] |
李江苏, 梁燕, 王晓蕊 . 基于POI数据的郑东新区服务业空间聚类研究. 地理研究, 2018,37(1):145-157.
[
|
| [21] |
|
| [22] |
|
| [23] |
|
| [24] |
国务院发展研究中心课题组. 城乡空间边界划分的国际经验及启示. 中国发展观察, 2010, ( 7):54-57.
[ Research Group of the State Council Development Research Center. International experience and Enlightenment of dividing urban and rural spatial boundaries. China Development Observation, 2010, ( 7):54-57.]
|
| [25] |
|
| [26] |
刘晓曈 . 基于深度学习的分类预测方法研究及应用. 南京: 东南大学硕士学位论文, 2017.
[
|
| [27] |
焦朋朋, 陆化普, 王建伟 . 基于交通效率的城市道路网络优化. 清华大学学报: 自然科学版, 2005,45(3):297-300.
[
|
| [28] |
谢顺平, 冯学智, 王结臣 , 等. 基于网络加权Voronoi图分析的南京市商业中心辐射域研究. 地理学报, 2009,64(12):1467-1476.
[
|
| [29] |
杨励雅 . 城市交通与土地利用相互关系的基础理论与方法研究. 北京: 北京交通大学博士学位论文, 2007.
[
|
| [30] |
郭欢欢, 林坚, 孙芬 , 等. 桥梁-道路建设对西南山地城市扩展影响机制研究: 以重庆嘉陵江两桥为例. 长江流域资源与环境, 2017,26(1):47-54.
[
|
/
| 〈 |
|
〉 |