Multicriteria decision approach for land use land cover change using Markov chain analysis and a cellular automata approach
Multicriteria decision approach for land use land cover change using Markov chain analysis and a cellular automata approach
复制标题
DOI：
10.5589/m06-032
复制
发表时间：
2006-12-01
影响因子：
2.6
通讯作者：
Wang, Le
中科院分区：
文献类型：
--
作者：
Myint, Soe W.;Wang, Le
本研究采用后分类变化检测方法，以确定土地利用土地覆盖变化在诺曼，俄克拉荷马州，1979年9月和1989年7月之间使用Landsat多光谱扫描仪和专题成像仪（TM）图像。结合马尔可夫链分析和元胞自动机方法，采用多准则决策和模糊参数标准化方法预测诺曼2000年的土地利用土地覆盖。采用分层随机抽样技术进行准确度评估。确定的随机采样点显示在Landsat增强专题成像仪（ETM）的图像数据采集于2000年5月22日，与当地的知识，地面信息收集，现有的土地利用图诺曼识别类的帮助。我们还直接比较了预测结果对同一Landsat TM图像的分类输出。这项研究表明马尔可夫和细胞模型的城市景观变化的有用性。还报告了在应用这一方法方面的限制或不确定性来源的清单。
This study used the postclassification change detection approach to identify land use land cover changes in Norman, Oklahoma, between September 1979 and July 1989 using Landsat multispectral scanner and thematic mapper (TM) images. An integration of Markov chain analysis and a cellular automata approach was employed to predict land use land cover of Norman in 2000 using multicriteria decision-making and fuzzy parameter standardization approaches. Accuracy assessment was carried out using a stratified random sampling technique. The identified random sample points were displayed on Landsat enhanced thematic mapper (ETM) image data acquired on 22 May 2000, with the help of local area knowledge, ground information collection, and existing land use maps of Norman to identify the classes. We also directly compared projected results against the classified output of the same Landsat TM image. This study demonstrates the usefulness of Markov and cellular modeling for urban landscape changes. A checklist of the sources of limitation or uncertainty in the application of this approach is also reported.