| 摘要: |
| 以济宁市任城区为研究对象，获取研究区域2001年、2006年和2011年三期Landsat ETM与TM影像，通过ENVI遥感影像处理软件分析了研究区影像的光谱特征以及植被归一化指数（NDVI）、建筑归一化指数（NDBI）以及水体归一化指数（NDWI），利用决策树算法确定各地类的综合阈值，建立决策树模型，得到了土地利用覆盖分类结果并取得了良好的分类精度。同时通过对研究区2001至2011年的土地利用动态度及土地利用转移矩阵的分析得出研究区在研究期内的土地利用覆盖变化特征，最终得出结论：（1）利用决策树分类能够获得较高的分类精度；（2）任城区城镇化发展迅速，城镇化在区域土地利用覆盖变化过程中起到了主导性的作用。 |
| 关键词: 遥感 决策树 土地利用分类 土地利用覆盖变化 城镇化 |
| DOI：10.7621/cjarrp.1005-9121.20140618 |
| 分类号: |
| 基金项目:江苏高校优势学科建设工程资助项目（SZBF2011-6-B35） |
|
| RESEARCH ON CLASSIFICATION OF LAND USE COVER AND ITS CHANGES BASED ON DECISION TREE ——A CASE STUDY OF RENCHENG DISTRICT, JINING |
|
Zhang Yu1, Chen Longqian1, Zhou Tianjian1, Zhang Ting1, Li Yuanyuan1, An Wei2
|
|
1.School of Environment Science and Spatial Informatics, China University of Mining and Technology, Jiangsu Xuzhou 221116;2.Nantun Coal Mine of Yanzhou Coal Mining Company Limited，Shandong Zoucheng 273515
|
| Abstract: |
| Taking Rencheng District of Jining as a study case, this paper analyzed the spectral characteristics of the images and their value of NDVI, NDBI and NDWI with the support of ENVI software, based on the Landsat ETM and TM Images of study area in 2001, 2006 and 2011. Decision Tree Algorithm was used to calculate the threshold value for different lands and built Decision Trees. Then the classification results were obtained with high accuracy results. Meanwhile, land Use Dynamics and land Use Transition Matrix of the study area from 2001 to 2011 were analyzed, and the characteristics of land Use Cover Change in the study area during the study period were obtained. The Conclusions were as follows: 1) a higher classification accuracy through using decision tree can be achieved; 2)The urbanization development of Rencheng was obvious which had played a leading role in the process of land use cover change in the study case． |
| Key words: remote sensing decision tree land use classification land use cover change urbanization |
