城市扩展元胞自动机多结构卷积神经网络模型

doi:10.11947/j.AGCS.2020.20190147

摘要/Abstract

摘要： 传统的城市扩展元胞自动机（CA）模型是基于单个元胞的变量信息挖掘来构建转换规则的。针对这一问题，本文基于多结构卷积神经网络提出从区域特征出发且顾及区域多尺度特征挖掘转换规则的城市扩展元胞自动机模型（MSCNN-CA），并以武汉主城区和上海浦东新区为例，模拟了两个试验区2005-2015年期间城市扩展过程。模型验证表明：与逻辑回归和神经网络相比，本文构建的3个单一结构的卷积神经网络元胞自动机（CNN-CA）模型在4个指标（Kappa系数、FoM（figure of merit）值、命中率（h）和错误率（m））上都有不同程度的提高。特别是FoM指数，在武汉主城区提高了23.3%~29.4%，在上海浦东新区提高了20.3%~28.5%。此外，MSCNN-CA模型与3个单一结构的CNN-CA模型相比，在各个指标上也有所改善，FoM指数在武汉主城区提高了0.8%~4.8%，上海浦东新区提高了2.8%~7.8%。两个试验区的模拟结果表明：相比传统CA模型，基于多结构卷积神经网络的城市扩展元胞自动机模型（MSCNN-CA）能够有效提高城市扩展模拟的精度，更真实地反映城市扩展空间演变过程。相比单结构的卷积神经网络CA模型，多结构卷积神经网络CA模型的稳定性和模拟结果准确性有所提升。

关键词: 城市扩展, 元胞自动机, 多结构卷积神经网络, 地理模拟

Abstract: Based on multi-structures convolutional neural networks, this paper proposes an urban expansion cellular automata model (MSCNN-CA) considering the multi-scale neighborhood information to explore the problem of traditional cellular automata (CA) models merely accounting for a single pixel's factors while mining the urban development suitability. This paper took the main urban zone of Wuhan and Pudong New District of Shanghai as examples to simulate the urban expansion process of the two study areas from 2005 to 2015. The experimental results show that, compared with two traditional CA models (LR, ANN), the three single-structure CNN-CA models constructed in this paper have different degrees of improvement in Kappa coefficient, FoM coefficient, hit rate (h) and miss rate (m). In particular, the FoM coefficient is increased by 23.3%~29.4% in the main urban zone of Wuhan and 20.3%~28.5% in Pudong New District of Shanghai. In addition, compared with the three single-structure CNN-CA models, the MSCNN-CA model is also improved in various indicators. Such as, the FoM coefficient is increased by 0.8%~4.8% in the main urban zone of Wuhan and 2.8%~7.8% in Pudong New District of Shanghai. The two study areas' simulation results show that, compared with the traditional CA models, the urban expansion cellular automata model based on multi-structures convolutional neural network (MSCNN-CA) can effectively improve the accuracy of urban expansion simulation and more realistically reflect the evolution process of urban expansion. Besides, both the stability and the accuracy of the MSCNN-CA model are improved comparing with the single-structure convolutional neural network CA model.

Key words: urban expansion, cellular automata, multi-structures convolutional neural networks, geographic simulation

中图分类号:

P208

谢志文, 王海军, 张彬, 黄鑫鑫. 城市扩展元胞自动机多结构卷积神经网络模型[J]. 测绘学报, 2020, 49(3): 375-385.

XIE Zhiwen, WANG Haijun, ZHANG Bin, HUANG Xinxin. Urban expansion cellular automata model based on multi-structures convolutional neural networks[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(3): 375-385.

参考文献

[1] 王海军, 邓羽, 张文婷, 等. 利用元胞自动机和遗传算法的Voronoi图生成[J]. 武汉大学学报(信息科学版), 2010, 35(7):778-781. WANG Haijun, DENG Yu, ZHANG Wenting, et al. Generation of Voronoi diagram based on genetic algorithms and cellular automata[J]. Geomatics and Information Science of Wuhan University, 2010, 35(7):778-781.
[2] 王海军, 张文婷, 贺三维, 等. 利用元胞自动机和模糊C均值进行图像分割[J]. 武汉大学学报(信息科学版), 2010, 35(11):1288-1291. WANG Haijun, ZHANG Wenting, HE Sanwei, et al. An image segmentation method based on cellular automata and fuzzy C-means[J]. Geomatics and Information Science of Wuhan University, 2010, 35(11):1288-1291.
[3] 王海军, 张文婷, 陈莹莹, 等. 利用元胞自动机作用域构建林火蔓延模型[J]. 武汉大学学报(信息科学版), 2011, 36(5):575-578. WANG Haijun, ZHANG Wenting, CHEN Yingying, et al. Fire spreading model based on CA scope[J]. Geomatics and Information Science of Wuhan University, 2011, 36(5):575-578.
[4] 张利, 周亚鹏, 门明新, 等. 基于不同种类生态安全的土地利用情景模拟[J]. 农业工程学报, 2015, 31(5):308-316. ZHANG Li, ZHOU Yapeng, MEN Mingxin, et al. Land use scenario simulation with different types of ecological security[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(5):308-316.
[5] COUCLELIS H. Cellular worlds:a framework for modeling micro-macro dynamics[J]. Environment and Planning A:Economy and Space, 1985, 17(5):585-596.
[6] COUCLELIS H. From cellular automata to urban models:new principles for model development and implementation[J]. Environment and Planning B:Planning and Design, 1997, 24(2):165-174.
[7] 王海军, 夏畅, 刘小平, 等. 大尺度和精细化城市扩展CA的理论与方法探讨[J]. 地理与地理信息科学, 2016, 32(5):1-8. WANG Haijun, XIA Chang, LIU Xiaoping, et al. Theoretical and methodological perspectives of fine-scale urban expansion cellular automata for the large regions[J]. Geography and Geo-information Science, 2016, 32(5):1-8.
[8] WHITE R, ENGELEN G. Cellular automata as the basis of integrated dynamic regional modelling[J]. Environment and Planning B:Planning and Design, 1997, 24(2):235-246.
[9] WHITE R, ENGELEN G. Cellular automata and fractal urban form:a cellular modelling approach to the evolution of urban land-use patterns[J]. Environment and Planning A:Economy and Space, 1993, 25(8):1175-1199.
[10] BATTY M, XIE Y. From cells to cities[J]. Environment and Planning B:Planning and Design, 1994, 21(7):531-538.
[11] WU Fulong. SimLand:a prototype to simulate land conversion through the integrated GIS and CA with AHP-derived transition rules[J]. International Journal of Geographical Information Science, 1998, 12(1):63-82.
[12] LI Xia, YEH A G O. Modelling sustainable urban development by the integration of constrained cellular automata and GIS[J]. International Journal of Geographical Information Science, 2000, 14(2):131-152.
[13] 王鹤, 曾永年. 城市扩展极限学习机模型[J]. 测绘学报, 2018, 47(12):1680-1690. DOI:10.11947/j.AGCS.2018.20170586. WANG He, ZENG Yongnian. Urban expansion model based on extreme learning machine[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(12):1680-1690. DOI:10.11947/j.AGCS.2018.20170586.
[14] WU Fulong. Calibration of Stochastic cellular automata:the application to rural-urban land conversions[J]. International Journal of Geographical Information Science, 2002, 16(8):795-818.
[15] CAO Kai, HUANG Bo, LI Manchun, et al. Calibrating a cellular automata model for understanding rural-urban land conversion:a Pareto front-based multi-objective optimization approach[J]. International Journal of Geographical Information Science, 2014, 28(5):1028-1046.
[16] LIU Yan, FENG Yongjiu, PONTIUS JR R G. Spatially-explicit simulation of urban growth through self-adaptive genetic algorithm and cellular automata modelling[J]. Land, 2014, 3(3):719-738.
[17] FENG Yongjiu, LIU Yan, TONG Xiaohua, et al. Modeling dynamic urban growth using cellular automata and particle swarm optimization rules[J]. Landscape and Urban Planning, 2011, 102(3):188-196.
[18] BIAU G. Analysis of a random forests model[J]. Journal of Machine Learning Research, 2012, 13(4):1063-1095.
[19] 王海军, 夏畅, 张安琪, 等. 利用生物地理学优化算法获取城市扩展元胞自动机模型参数[J]. 武汉大学学报(信息科学版), 2017, 42(9):1323-1329. WANG Haijun, XIA Chang, ZHANG Anqi, et al. Calibrating urban expansion cellular automata using biogeography-based optimization[J]. Geomatics and Information Science of Wuhan University, 2017, 42(9):1323-1329.
[20] LI Xia, CHEN Guangzhao, LIU Xiaoping, et al. A new global land-use and land-cover change product at a 1-km resolution for 2010 to 2100 based on human-environment interactions[J]. Annals of the American Association of Geographers, 2017, 107(5):1040-1059.
[21] 刘小平, 黎夏. 从高维特征空间中获取元胞自动机的非线性转换规则[J]. 地理学报, 2006, 61(6):663-672. LIU Xiaoping, LI Xia. Retrieving CA nonlinear transition rule from high-dimensional feature space[J]. Acta Geographica Sinica, 2006, 61(6):663-672.
[22] 杨青生, 黎夏. 基于支持向量机的元胞自动机及土地利用变化模拟[J]. 遥感学报, 2006, 10(6):836-846. YANG Qingsheng, LI Xia. Cellular automata for simulating land use changes based on support vector machine[J]. Journal of Remote Sensing, 2006, 10(6):836-846.
[23] HE Jialv, LI Xia, YAO Yao, et al. Mining transition rules of cellular automata for simulating urban expansion by using the deep learning techniques[J]. International Journal of Geographical Information Science, 2018, 32(10):2076-2097.
[24] 姚相坤, 万里红, 霍宏, 等. 基于多结构卷积神经网络的高分遥感影像飞机目标检测[J]. 计算机工程, 2017, 43(1):259-267. YAO Xiangkun, WAN Lihong, HUO Hong, et al. Airplane object detection in high resolution remote sensing imagery based on multi-structure convolutional neural network[J]. Computer Engineering, 2017, 43(1):259-267.
[25] 陈超, 齐峰. 卷积神经网络的发展及其在计算机视觉领域中的应用综述[J]. 计算机科学, 2019, 46(3):63-73. CHEN Chao, QI Feng. Review on development of convolutional neural network and its application in computer vision[J]. Computer Science, 2019, 46(3):63-73.
[26] 余东行, 郭海涛, 张保明, 等. 级联卷积神经网络的遥感影像飞机目标检测[J]. 测绘学报, 2019, 48(8):1046-1058. DOI:10.11947/j.AGCS.2019.20180471. YU Donghang, GUO Haitao, ZHANG Baoming, et al. Aircraft detection in remote sensing images using cascade convolutional neural networks[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(8):1046-1058. DOI:10.11947/j.AGCS.2019.20180471.
[27] 崔卫红, 熊宝玉, 张丽瑶. 多尺度全卷积神经网络建筑物提取[J]. 测绘学报, 2019, 48(5):597-608. DOI:10.11947/j.AGCS.2019.20180062. CUI Weihong, XIONG Baoyu, ZHANG Liyao. Multi-scale fully convolutional neural network for building extraction[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(5):597-608. DOI:10.11947/j.AGCS.2019.20180062.
[28] WANG Haijun, HE Sanwei, LIU Xingjian, et al. Simulating urban expansion using a cloud-based cellular automata model:a case study of Jiangxia, Wuhan, China[J]. Landscape and Urban Planning, 2013, 110(1):99-112.
[29] XIA Chang, WANG Haijun, ZHANG Anqi, et al. A high-performance cellular automata model for urban simulation based on vectorization and parallel computing technology[J]. International Journal of Geographical Information Science, 2018, 32(2):399-424.
[30] XIA Chang, ZHANG Anqi, WANG Haijun, et al. Modeling urban growth in a metropolitan area based on bidirectional flows, an improved gravitational field model, and partitioned cellular Automata[J]. International Journal of Geographical Information Science, 2019, 33(5):877-899.
[31] FENG Yongjiu, LIU Yan, BATTY M. Modeling urban growth with GIS based cellular automata and least squares SVM rules:a case study in Qingpu-Songjiang area of Shanghai, China[J]. Stochastic Environmental Research and Risk Assessment, 2016, 30(5):1387-1400.
[32] 门计林, 刘越岩, 张斌, 等. 多结构卷积神经网络特征级联的高分影像土地利用分类[J]. 武汉大学学报(信息科学版), 2019, 44(12):1841-1848. MEN Jilin, LIU Yueyan, ZHANG Bin, et al. Land use classification based on multi-structure convolution neural network features cascading[J]. Geomatics and Information Science of Wuhan University, 2019, 44(12):1841-1848.