Effects of Time-Duration on the Performance of the Spatial-Markov Model for Land use Change Forecasting

CORC > 烟台海岸带研究所 > 中国科学院烟台海岸带研究所 > 中科院海岸带环境过程与生态修复重点实验室 > 海岸带信息集成与综合管理实验室

	Effects of Time-Duration on the Performance of the Spatial-Markov Model for Land use Change Forecasting
	Hou, Xi-Yong; Wu, Li; Lu, Xiao; Di, Xiang-Hong
刊名	JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING
	2015-06-01
卷号	43 期号:2 页码:287-295
关键词	Land use change Markov chain Spatial-Markov Time duration Ratio scale Nominal scale
ISSN号	0255-660X
通讯作者	Hou, XY (reprint author), Chinese Acad Sci, Yantai Inst Coastal Zone Res YIC, 17 ChunHui Rd, Laishan Dist 264003, Yantai, Peoples R China. xyhou@yic.ac.cn
产权排序	[Hou, Xi-Yong; Lu, Xiao] Chinese Acad Sci, Yantai Inst Coastal Zone Res YIC, Laishan Dist 264003, Yantai, Peoples R China; [Wu, Li] Henan Inst Engn, Coll Civil Engn, Zhengzhou 451191, Henan, Peoples R China; [Di, Xiang-Hong] Dezhou Univ, Coll Resources Environm & Planning, Dezhou 253023, Shandong, Peoples R China
中文摘要	Markov chain is one of the most widely used methods for land use change forecasting, however, it's a non-spatial model and few papers have discussed the effects of time-duration on its performance. In this paper, we first present the primary methodologies of the Spatial-Markov model, which endows the ordinary Markov chain with spatial dimension using spatial analysis techniques, and then explore the effects of forecasting time-duration on the model's performance. By taking Shandong province, China as a case study area, land use maps in 1990, 1995, 2000, 2005 and 2010 were created using on Landsat images and then the Spatial-Markov model was developed at 1 km spatial scale. In detail, we repeatedly run the model by choosing different initial time points and the same time step (five year interval) to simulate the spatial-temporal dynamics of land use change from 1990 to 2010. The forecasting results of a single run included a stack of ratio scale images and a derived nominal scale image, chi(2) test and Kappa coefficient were adopted to evaluate their accuracy respectively. It turned out that the Spatial-Markov model could achieve very good performance for short period forecasting. For the case study, it was quite qualified for the prediction of three time steps (up to 15 years) or more within which the results had much high reliability, however, time-duration of forecasting had much significant impact on the model's performance, the longer the forecasting duration, the lower the model's accuracy.
英文摘要	Markov chain is one of the most widely used methods for land use change forecasting, however, it's a non-spatial model and few papers have discussed the effects of time-duration on its performance. In this paper, we first present the primary methodologies of the Spatial-Markov model, which endows the ordinary Markov chain with spatial dimension using spatial analysis techniques, and then explore the effects of forecasting time-duration on the model's performance. By taking Shandong province, China as a case study area, land use maps in 1990, 1995, 2000, 2005 and 2010 were created using on Landsat images and then the Spatial-Markov model was developed at 1 km spatial scale. In detail, we repeatedly run the model by choosing different initial time points and the same time step (five year interval) to simulate the spatial-temporal dynamics of land use change from 1990 to 2010. The forecasting results of a single run included a stack of ratio scale images and a derived nominal scale image, chi(2) test and Kappa coefficient were adopted to evaluate their accuracy respectively. It turned out that the Spatial-Markov model could achieve very good performance for short period forecasting. For the case study, it was quite qualified for the prediction of three time steps (up to 15 years) or more within which the results had much high reliability, however, time-duration of forecasting had much significant impact on the model's performance, the longer the forecasting duration, the lower the model's accuracy.
学科主题	Environmental Sciences; Remote Sensing
研究领域[WOS]	Environmental Sciences & Ecology ; Remote Sensing
关键词[WOS]	USE/LAND COVER CHANGE ; REMOTE-SENSING DATA ; URBAN EXPANSION ; CHINA ; DYNAMICS ; GROWTH ; REGION ; AREA ; GIS
收录类别	SCI
语种	英语
WOS记录号	WOS:000354894500008
内容类型	期刊论文
源URL	[http://ir.yic.ac.cn/handle/133337/8586]
专题	烟台海岸带研究所_海岸带信息集成与综合管理实验室烟台海岸带研究所_中科院海岸带环境过程与生态修复重点实验室
推荐引用方式 GB/T 7714	Hou, Xi-Yong,Wu, Li,Lu, Xiao,et al. Effects of Time-Duration on the Performance of the Spatial-Markov Model for Land use Change Forecasting[J]. JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING,2015,43(2):287-295.
APA	Hou, Xi-Yong,Wu, Li,Lu, Xiao,&Di, Xiang-Hong.(2015).Effects of Time-Duration on the Performance of the Spatial-Markov Model for Land use Change Forecasting.JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING,43(2),287-295.
MLA	Hou, Xi-Yong,et al."Effects of Time-Duration on the Performance of the Spatial-Markov Model for Land use Change Forecasting".JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING 43.2(2015):287-295.