Classification and Mapping of Land Use Land Cover change in Kanyakumari district with Remote Sensing and GIS techniques
Classification and Mapping of Land Use Land Cover change in Kanyakumari district with Remote Sensing and GIS techniques
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
L. Lekha
中科院分区：
文献类型：
--
作者：
L. Lekha
Kanyakumari地区的LULC特征与农业扩张、地下水枯竭和城市化特别相关。为了了解人口和生活质量的总体动态，监测土地利用/土地利用变化是必要的。本研究的主要目的是分析kanyakumari区的土地利用率，人口和气候变化的增加对植被，森林，地下水污染造成最大的环境影响，以及更多的建筑物和垃圾倾倒的裸露土地的恶化。本研究主要针对ENVI 5.1中的三种不同的分类器，即马氏距离分类器、神经网络分类器和自适应相干估计分类器，对Landsat影像的LULC分类进行比较，以选择最适合不同特征的分类器方法。土地利用变化特征分为建成区、水体、农业用地、丘陵区、森林和裸地。通过google earth和照片判读建立误差矩阵，分析了测量精度，得到了准确的测量精度。总体分析表明，自适应相干估计优于其他分类器在这项工作中研究。利用QGIS 2.14.4生成的Landsat影像变化分析图显示了总体变化。
The LULC features in Kanyakumari district are particularly associated with agriculture expansion, ground water depletion and urbanization. Monitoring LULC is necessary in order to understand the overall dynamics of population and quality of life. The primary objective of this study is to analyze the LULC of kanyakumari district, where the increase of population and climatic variability causes the greatest environmental impact on vegetation, forest, ground water pollution and also deterioration of bare land with more builtup and dumping of garbage. This study mainly focuses on the comparison of three different classifiers namely Mahalanobis Distance Classifier, Neural Net Classifier (NN) and Adaptive Coherence Estimator in ENVI 5.1 for LULC classification from Landsat images, to select the best suitable method of classifier for the different features. The classified LULC features are categorized as built-up areas, waterbodies, agriculture land, hilly areas, forest and bare land. The accuracy was analyzed by finding the error matrix using google earth and photo interpretation, which had helped to get the accurate accuracy. The overall analysis shows that the Adaptive Coherence Estimator overperformed to other classifiers studied in this work. The change analysis map of the Landsat images generated using QGIS2.14.4 indicates the overall changes.