纳入空间自相关的FLUS模型在土地利用变化多情景模拟中的应用

doi:10.12082/dqxxkx.2020.190359

地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (3): 531-542.doi: 10.12082/dqxxkx.2020.190359

• “土地利用模拟”专栏 • 上一篇下一篇

纳入空间自相关的FLUS模型在土地利用变化多情景模拟中的应用

张经度¹, 梅志雄^1,^2,^*(), 吕佳慧¹, 陈进钊¹

^1. 华南师范大学地理科学学院, 广州 510631
^2. 华南师范大学粤港澳村镇可持续发展研究中心, 广州 510631

收稿日期:2019-07-04 修回日期:2019-12-19 出版日期:2020-03-25 发布日期:2020-05-18
通讯作者: 梅志雄 E-mail:zhixiongmei76@126.com
作者简介:张经度（1995— ）,男,江西赣州人,硕士生,主要从事空间分析与建模、土地利用模拟等研究。E-mail:cuitzjd@163.com
基金资助:
国家自然科学基金(41001078)

Simulating Multiple Land Use Scenarios based on the FLUS Model Considering Spatial Autocorrelation

ZHANG Jingdu¹, MEI Zhixiong^1,^2,^*(), LV Jiahui¹, CHEN Jinzhao¹

^1. School of Geography, South China Normal University, Guangzhou 510631, China
^2. Center for Sustainable Development of Rural and Town in Guangdong-Hong Kong-Marco Greater Bay Area, South China Normal University, Guangzhou 510631, China

Received:2019-07-04 Revised:2019-12-19 Online:2020-03-25 Published:2020-05-18
Contact: MEI Zhixiong E-mail:zhixiongmei76@126.com
Supported by:
National Natural Science Foundation of China(41001078)

摘要/Abstract

摘要：

FLUS模型是一种新型的土地利用变化模拟模型,应用前景广阔。本文通过在FLUS模型的人工神经网络（Artificial Neural Network,ANN）训练模块中引入空间自相关因子来改进模型,以珠江三角洲地区为例,基于2009年、2015年土地利用数据和一系列驱动因子对改进的模型进行了验证,并利用该改进的FLUS模型模拟了2035年研究区在3种情景下土地利用变化格局。结果表明：① 引入空间自相关因子后各地类发生概率分布的预测精度更高,耕地、林地、建设用地、水体和未利用土地的拟合优度ROC值分别从0.819、0.928、0.885、0.855和0.861提高到0.857、0.934、0.890、0.863和0.978;② 改进的FLUS模型的模拟精度有一定的提高,Kappa系数从0.732提高到0.744,FOM系数从0.077升到0.106;③ 情景模拟表明,3种情景下珠江三角洲建设用地和林地均将增加、而耕地均呈减少趋势。但不同情景下模拟的土地利用格局也存在显著差异: 基准情景下,建设用地明显扩张且大幅侵占耕地。耕地保护情景下,耕地面积保持在合理水平,建设用地蔓延扩张趋势得到遏制,土地利用布局总体趋向合理。生态保护情景下,耕地、林地和水体得到较好保护,建设用地布局更为合理,土地利用可持续性明显提高。

关键词: FLUS模型, 人工神经网络, 系统动力学, 空间自相关, 多尺度, 土地利用变化, 多情景模拟, 珠江三角洲

Abstract:

The Future Land Use Simulation (FLUS) model is a new model for simulating multiple land-use changes, and has a broad application prospect. This paper improved the FLUS model by incorporating a spatial autocorrelation factor into the Artificial Neural Network (ANN) module of FLUS, selected thePearl River Delta region as the case study area, and validated the improved FLUS model based on the land use data of 2009 and 2015, as well as a series of driving factors. Three future land-use scenarios in 2035: the baseline scenario, cultivated protection scenario, and ecological protection scenario, were simulated using the improved model. The results showed that: (1) After incorporating the spatial autocorrelation factor, the model had better predictive powerfor the occurrence probability distribution ofeach land use. The ROC values of cultivated land, forestland, water area,construction land, and unused land increased from 0.819, 0.928, 0.885, 0.855, and 0.861 to 0.857, 0.934, 0.890, 0.863 and 0.978, respectively. (2) The simulation accuracy of the improved FLUS model was improved. The Kappa value increased from 0.732 to 0.744, and the FOM value increased from 0.077 to 0.106. (3) The scenario simulation results indicated that under all three scenarios, forestland and construction land would increase, whereas cultivated land would decrease. Apparent differences also existed in the simulated change sizes and locations of each land use type under different scenarios. Under the baseline scenario, construction land would expand rapidly at the expense of a large amount of cultivated land. Under the cultivated land protection scenario, cultivated land area would remain at a reasonable level, the expansion of construction land would alleviate, and the land use layout would tend to be reasonable. Under the ecological protection scenario, cultivated land, forestland, and water area would be well protected, the layout of construction land would be more rational, and the land use sustainability in the study area would be improved significantly.

Key words: Key Word: FLUS model, artificial neural networks, system dynamics, spatial autocorrelation, multiscale, land use change, multi-scenarios simulation, Pearl River Delta

张经度, 梅志雄, 吕佳慧, 陈进钊. 纳入空间自相关的FLUS模型在土地利用变化多情景模拟中的应用[J]. 地球信息科学学报, 2020, 22(3): 531-542.DOI:10.12082/dqxxkx.2020.190359

ZHANG Jingdu, MEI Zhixiong, LV Jiahui, CHEN Jinzhao. Simulating Multiple Land Use Scenarios based on the FLUS Model Considering Spatial Autocorrelation[J]. Journal of Geo-information Science, 2020, 22(3): 531-542.DOI:10.12082/dqxxkx.2020.190359

图/表 11

图1

表1

图2

图3

表2

图4

表3

表4

图5

表5

图6

参考文献 35

[1]	戴声佩, 张勃 . 基于CLUE-S模型的黑河中游土地利用情景模拟研究——以张掖市甘州区为例[J]. 自然资源学报, 2013,28(2):336-348.
	[ Dai S P, Zhang B . Land use change scenarios simulation in the middle reaches of the Heiheriver basinbased on CLUE-S model: A case of Ganzhou District of Zhangye city[J]. Journal of Natural Resources, 2013,28(2):336-348. ]
[2]	卞子浩, 马小雪, 龚来存 , 等. 不同非空间模拟方法下CLUE-S模型土地利用预测——以秦淮河流域为例[J]. 地理科学, 2017,37(2):252-258.
	[ Bian Z H, Ma X X, Gong L C , et al. Land use prediction based on CLUE-S model under different non-spatial simulation methods: A case study of the Qinhuai river watershed[J]. Scientia Geographical Sinica, 2017,37(2):252-258. ]
[3]	梁友嘉, 徐中民, 钟方雷 . 基于SD和CLUE-S模型的张掖市甘州区土地利用情景分析[J]. 地理研究, 2011,30(3):564-576.
	[ Liang Y J, Xu Z M, Zhong F L . Land use scenario analyses by based on system dynamic model and CLUE-S model at regional scale: A case study of Ganzhou District of Zhangye city[J]. Geographical Research, 2011,30(3):564-576. ]
[4]	王保盛, 廖江福, 祝薇 , 等. 基于历史情景的FLUS模型邻域权重设置——以闽三角城市群2030年土地利用模拟为例[J]. 生态学报, 2019,39(12):4284-4298.
	[ Wang B S, Liao J F, Zhu W , et al. The weight of neighborhood setting of the FLUS model based on a historical scenario: A case study of land use simulation of urban agglomeration of the golden triangle of southern Fujian in 2030[J]. Acta EcologicaSinica, 2019,39(12):4284-4298. ]
[5]	黎夏, 叶嘉安 . 基于神经网络的元胞自动机及模拟复杂土地利用系统[J]. 地理研究, 2005,24(1):19-27.
	[ Li X, Yeh A G . Cellular automata for simulating complex land use systems using neural networks[J]. Geographical Research, 2005,24(1):19-27. ]
[6]	曹雪, 罗平, 李满春 , 等. 基于扩展CA模型的土地利用变化时空模拟研究——以深圳市为例[J]. 资源科学, 2011,33(1):127-133.
	[ CaoX, Luo P, Li M C , et al. Spatio-temporal simulation of land use change based on a extended CA model:A case study of Shenzhen city, China[J]. Resources Science, 2011,33(1):127-133. ]
[7]	Wang H J, Kong X D, Zhang B . The simulation of LUCC based on Logistic-CA-Markov model in Qilian Mountain area, China[J]. Sciences in Cold and Arid Regions, 2016,8(4):350-358. doi: 10.1007/s11356-019-05127-9 pmid: 31104240
[8]	Clarke K C, Gaydos L J . Loose-coupling a cellular automaton model and GIS: Long-term urban growth prediction for San Francisco and Washington/Baltimore[J]. International Journal of Geographical Information Systems, 1998,12(7):699-714. doi: 10.1080/136588198241617 pmid: 12294536
[9]	Liu Y B, Dai L, Xiong H H . Simulation of urban expansion patterns by integrating auto-logistic regression, Markov chain and cellular automata models[J]. Journal of Environmental Planning and Management, 2015,58(6):1113-1136. doi: 10.1080/09640568.2014.916612
[10]	严冬, 李爱农, 南希 , 等. 基于Dyna-CLUE改进模型和SD模型耦合的山区城镇用地情景模拟研究——以岷江上游地区为例[J]. 地球信息科学学报, 2016,18(4):514-525. doi: 10.3724/SP.J.1047.2016.00514
	[ Yan D, Li A N, Nan X , et al. The Study of urban land scenario simulation in mountain areabased on modified Dyna-CLUE model and SDM: Acase study of the upper reaches of Minjiang river[J]. Journal of Geo-information Science, 2016,18(4):514-525. ] doi: 10.3724/SP.J.1047.2016.00514
[11]	Mei Z X, Wu H, Li S Y . Simulating land-use changes by incorporating spatial autocorrelation and self-organization in CLUE-S modeling: A case study in Zengcheng District, Guangzhou, China[J]. Frontiers of Earth Science, 2018,12(2):299-310.
[12]	Silva E A, Clarke K C . Calibration of the SLEUTH urban growth model for Lisbon and Porto, Portugal[J]. Computers, Environment and Urban Systems, 2002,26(6):525-552.
[13]	詹云军, 朱捷缘, 严岩 . 基于元胞自动机的城市空间动态模拟[J]. 生态学报, 2017,37(14):4864-4872.
	[ Zhan Y J, Zhu J Y, Yan Y . Dynamic simulation of urban space based on the SLEUTH model[J]. Acta EcologicaSinica, 2017,37(14):4864-4872. ]
[14]	米媛, 姜博, 陈颜 , 等. 基于SLEUTH模型的鄂尔多斯城市扩张模拟分析[J]. 中国农业大学学报, 2019,24(2):183-190.
	[ Mi Y, Jiang B, Chen Y , et al. Simulation analysis of urban expansion in Ordos based on SLEUTH model[J]. Journal of China Agricultural University, 2019,24(2):183-190. ]
[15]	王丽妍, 李飞雪, 李满春 , 等. 基本农田信息对SLEUTH模型模拟准确性的影响——以常州市中心城区为例[J]. 地理与地理信息科学, 2015,31(3):48-53,2.
	[ Wang L Y, Li F X, Li M C , et al. Influences of basic farmland on SLEUTH model simulation accuracy:case study of Changzhou downtown[J]. Geography and Geo-Information Science, 2015,31(3):48-53. ]
[16]	Le Q B, Park S J, Vlek P L G et al. , Land-Use Dynamic Simulator (LUDAS): A multi-agent system model for simulating spatio-temporal dynamics of coupled human-landscape system I. Structure and theoretical specification[J]. Ecological Informatics, 2008,3(2):135-153.
[17]	刘小平, 黎夏, 艾彬 , 等. 基于多智能体的土地利用模拟与规划模型[J]. 地理学报, 2006,61(10):1101-1112.
	[ Liu X P, Li X, Ai B , et al. Multi- agent systems for simulating and planning land use development[J]. Acta Geographica Sinica, 2006,61(10):1101-1112. ]
[18]	Luo J, Zhan J, Lin Y , et al. An equilibrium analysis of the land use structure in the Yunnan Province, China[J]. Frontiers of Earth Science, 2014,8(3):393-404.
[19]	田光进, 邬建国 . 基于智能体模型的土地利用动态模拟研究进展[J]. 生态学报, 2008,28(9):4451-4459.
	[ Tian G J, Wu J G . Simulating land use change with agent-based models: progress and prospects[J]. Acta EcologicaSinica, 2008,28(9):4451-4459. ]
[20]	VerburgP H, Overmars K P . Dynamic simulation of land-use change trajectories with the CLUE-S model.[J]. Modelling Land-Use Change: Progress and applications, 2007,90(5):321-337.
[21]	Luo G P, Yin C Y, Chen X , et al. Combining system dynamic model and CLUE-S model to improve land use scenario analyses at regional scale: A case study of Sangong watershed in Xinjiang, China[J]. Ecological Complexity, 2010,7(2):198-207. doi: 10.1016/j.ecocom.2010.02.001
[22]	Liang X, Liu X P, Li X , et al. Delineating multi-scenario urban growth boundaries with a CA-based FLUS model and morphological method[J]. Landscape and Urban Planning, 2018,177:47-63.
[23]	Liu X P, Liang X, Li X , et al. A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects[J]. Landscape and Urban Planning, 2017,168:94-116.
[24]	谢花林, 刘黎明, 李波 , 等. 土地利用变化的多尺度空间自相关分析:以内蒙古翁牛特旗为例[J]. 地理学报, 2006,61(4):389-400.
	[ Xie H L, Liu L M, Li B , et al. Spatial autocorrelation analysis of multi-scale land-use changes: A case study in Ongniud Banner, Inner Mongolia[J]. Acta GeographicaSinica, 2006,61(4):389-400. ]
[25]	Wu G P, Zeng Y N, Xiao P F , et al. Using autologistic spatial models to simulate the distribution of land-use patterns in Zhangjiajie, Hunan Province[J]. Journal of Geographical Sciences, 2010,20(2):310-320.
[26]	Jiang W G, Chen Z, Lei X , et al. Simulating urban land use change by incorporating an autologistic regression model into a CLUE-S model[J]. Journal of Geographical Sciences, 2015,25(7):836-850.
[27]	广东省统计局, 国家统计局广东调查总队. 广东省统计年鉴[M]. 北京: 中国统计出版社, 2019.
	[ Statistics Bureau of Guangdong Province, Guangdong Survey Headquarters, National Bureau of Statistics. Guangdong Statistical Yearbook[M]. Beijing: China Statistics Press, 2019. ]
[28]	朱寿红, 舒帮荣, 马晓冬 , 等. 基于“反规划”理念及FLUS模型的城镇用地增长边界划定研究:以徐州市贾汪区为例[J]. 地理与地理信息科学, 2017,33(5):80-86.
	[ Zhu S H, Shu B R, Ma X D , et al. The delimitation of urban growth boundary based on the idea of " anti-planning" and FLUS model: A case study of Jiawangdistrict, Xuzhou city[J]. Geography and Geo-information Science, 2017,33(5):80-86. ]
[29]	吴欣昕, 刘小平, 梁迅 , 等. FLUS-UGB多情景模拟的珠江三角洲城市增长边界划定[J]. 地球信息科学学报, 2018,20(4):532-542.
	[ Wu X X, Liu X P, Liang X , et al. multi-scenarios simulation of urban growth boundaries in Pearl River Delta based on FLUS-UGB[J]. Journal of Geo-information Science, 2018,20(4):532-542. ]
[30]	田贺, 梁迅, 黎夏 , 等. 基于SD模型的中国2010-2050年土地利用变化情景模拟[J]. 热带地理, 2017,37(3):547-561.
	[ Tian H, Liang X, Li X , et al. Simulating multiple land use scenarios in China during 2010-2050 based on system dynamic model[J]. Tropical Geography, 2017,37(3):547-561. ]
[31]	Koomen E, Pontius R, Boersma W , et al. Comparing the input, output, and validation maps for several models of land change[J]. The Annals of Regional Science, 2008,42:11-37.
[32]	广东省国土资源厅. 广东省土地利用总体规划(2006-2020)[M]. 广州:广东省国土资源厅, 2009.
	[ Department of Land and Resources of Guangdong Province. General land use planning of Guangdong Province(2006-2020)[M]. Guangzhou: Department of Land and Resources of Guangdong Province, 2009. ]
[33]	广东省国土资源厅. 广东省国土规划(2016-2035)[M]. 广州:广东省国土资源厅, 2016.
	[ Department of land and resources of guangdong province. land use planning of Guangdong province(2016-2035)[M]. Guangzhou: Department of Land and Resources of Guangdong Province, 2016. ]
[34]	中华人民共和国国务院. 粤港澳大湾区发展规划纲要[M]. 北京:中华人民共和国国务院, 2019.
	[ The State Council of the People's Republic of China. Outline of Guangdong-Hong Kong-Macao Greater Bay Area Development Plan[M]. Beijing: State Council of the People's Republic of China, 2019. ]
[35]	吴康, 李耀川 . 收缩情境下城市土地利用及其生态系统服务的研究进展[J]. 自然资源学报, 2019,34(5):1121-1134.
	[ Wu K, Li Y C . Research progress of urban land use and its ecosystemservices in the context of urban shrinkage[J]. Journal of Natural Resources, 2019,34(5):1121-1134. ]

数据类别	数据	数据获取年份	数据来源
土地利用数据	土地利用数据	2009、2015	GoogleEarthEngine平台(https://earthengine.google.com/)
基础地理数据	河流、公路、铁路、机场、火车站、城市位置	2018	OpenStreetMap网站(https://www.openstreetmap.org/)
自然环境数据	DEM	2009	地理空间数据云平台(http://www.gscloud.cn/)^[22]
	土壤含氧量、土壤含氮量、土壤盐碱化程度、土壤功效	2008	联合国粮农组织官网(http://www.iiasa.ac.at/)^[23]
	年均降水、年均气温、各季度平均气温	1970—2000年平均值	世界气候数据中心(http://www.worldclim.org/)^[23]
社会经济数据	人口分布情况	2010、2015	全球人口网站(https://www.worldpop.org/)^[23]
	人口出生率、人口死亡率	2009—2015	《广东省统计年鉴》^[27]
	GDP	2009—2015	《广东省统计年鉴》^[27]
	固定资产投资	2009—2015	《广东省统计年鉴》^[27]
	城镇人口占常住人口比例（城镇化率）	2009—2015	《广东省统计年鉴》^[27]
	粮食总产量	2009—2015	《广东省统计年鉴》^[27]

	步长/m
	50	100	150	200	250	300	350	400	450	500
耕地	0.826	0.819	0.765	0.756	0.694	0.670	0.675	0.672	0.633	0.731
林地	0.918	0.928	0.917	0.903	0.891	0.907	0.901	0.911	0.919	0.899
建设用地	0.886	0.885	0.867	0.829	0.805	0.824	0.857	0.763	0.759	0.785
水体	0.854	0.855	0.822	0.821	0.796	0.771	0.764	0.773	0.698	0.750
未利用土地	0.839	0.861	0.803	0.815	0.832	0.853	0.853	0.847	0.840	0.810

	Moore邻域
	3×3	5×5	7×7	9×9	11×11	13×13	15×15	17×17	19×19
Kappa值	0.735	0.731	0.744	0.740	0.741	0.743	0.742	0.736	0.732
FOM值	0.098	0.092	0.106	0.103	0.104	0.103	0.106	0.106	0.104

模型	kappa系数	FOM		耕地	林地	建设用地	水体	未利用土地
原始FLUS模型	0.732	0.077	生产者精度	0.672	0.932	0.733	0.784	0.011
原始FLUS模型	0.732	0.077	用户精度	0.670	0.929	0.732	0.789	0.048
改进后的FLUS模型	0.744	0.106	生产者精度	0.687	0.937	0.740	0.784	0.057
改进后的FLUS模型	0.744	0.106	用户精度	0.683	0.938	0.741	0.780	0.161

纳入空间自相关的FLUS模型在土地利用变化多情景模拟中的应用

Simulating Multiple Land Use Scenarios based on the FLUS Model Considering Spatial Autocorrelation

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 35

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	方云皓, 顾康康. 基于多元数据的中国地理空间疫情风险评估探索——以2020年1月1日至4月11日COVID-19疫情数据为例[J]. 地球信息科学学报, 2021, 23(2): 284-296.
[2]	张正方, 闫振军, 王增杰, 傅蓉, 罗文, 俞肇元. 基于Bayes网络的多粒度时空对象地理过程演化建模——以新安江模型为例[J]. 地球信息科学学报, 2021, 23(1): 124-133.
[3]	葛咏, 刘梦晓, 胡姗, 任周鹏. 时空统计学在贫困研究中的应用及展望[J]. 地球信息科学学报, 2021, 23(1): 58-74.
[4]	刘明杰, 徐卓揆, 郜允兵, 杨晶, 潘瑜春, 高秉博, 周艳兵, 周万鹏, 王凌. 基于机器学习的稀疏样本下的土壤有机质估算方法[J]. 地球信息科学学报, 2020, 22(9): 1799-1813.
[5]	张世伟, 魏璐瑶, 金星星, 陆玉麒. 基于FLUS-UGB的县域土地利用模拟及城镇开发边界划定研究[J]. 地球信息科学学报, 2020, 22(9): 1848-1859.
[6]	何永红, 靳鹏伟, 舒敏. 基于多尺度相关性分析的InSAR对流层延迟误差改正算法[J]. 地球信息科学学报, 2020, 22(9): 1878-1886.
[7]	姚可桢, 岳书平. 网络大数据下的中国现代食甜习惯空间分布特征及其影响因素研究[J]. 地球信息科学学报, 2020, 22(6): 1202-1215.
[8]	黄康, 戴文远, 黄万里, 欧惠. 基于FLUS模型与动能定理的城镇用地增长边界划定[J]. 地球信息科学学报, 2020, 22(3): 557-567.
[9]	杨露, 颉耀文, 宗乐丽, 邱天, 焦继宗. 基于多目标遗传算法和FLUS模型的西北农牧交错带土地利用优化配置[J]. 地球信息科学学报, 2020, 22(3): 568-579.
[10]	柯新利, 肖邦勇, 郑伟伟, 马艳春, 李红艳. 城镇-农业-生态空间划定的多情景模拟[J]. 地球信息科学学报, 2020, 22(3): 580-591.
[11]	赵林峰, 刘小平, 刘鹏华, 陈广照, 何家律. 基于地理分区与FLUS模型的城市扩张模拟与预警[J]. 地球信息科学学报, 2020, 22(3): 517-530.
[12]	张永树, 杨振凯, 訾璐, 曹一冰, 余航. 中国艾滋病空间格局和时空演化分析[J]. 地球信息科学学报, 2020, 22(2): 198-206.
[13]	田乃满, 兰恒星, 伍宇明, 李郎平. 人工神经网络和决策树模型在滑坡易发性分析中的性能对比[J]. 地球信息科学学报, 2020, 22(12): 2304-2316.
[14]	王志远, 张考, 丁志鹏, 伍随意, 黄春华. 纳入动态数据的改进FLUS模型在城市增长边界划定中的应用[J]. 地球信息科学学报, 2020, 22(12): 2326-2337.
[15]	宋海慧, 余卓渊, 丁晓彤, 谢云鹏, 吕可晶. 森林脑炎时空分布特征和环境影响因素分析[J]. 地球信息科学学报, 2020, 22(12): 2371-2382.