{"title":"Fuzzy C-means for Deforestation Identification Based on Remote Sensing Image","authors":"Setiawan Afandi, Y. Herdiyeni, L. Prasetyo","doi":"10.1109/ICACSIS.2014.7065848","DOIUrl":null,"url":null,"abstract":"This research report about Fuzzy C-Means for Deforestation Identification Based On Remote Sensing Image. Deforestation means that changes forest area into another functions. Clustering is a method of classify objects into related groups (clusters). While, Fuzzy C-Means clustering is a technique that each data is determined by the degree of membership. In this research, the data used are MODIS EVI 250 m in 2000 and 2012 to identify deforestation rate in Java island. MODIS EVI is one of kind MODIS image which is able to detect vegetation based on photosynthesis rate and vegetation density. The number of clusters used were 13 clusters. This research had succeeded to classify areas based on the value of EVI like areas who had a high EVI values (forests, plantations, grass land), moderate values (agricultural area), and low values (build up area, mining area, pond, and other land cover). But, EVI value is only influenced by photosynthesis rate and vegetation density. Thus, EVI value is not well to identify forest areas, this is because the value of EVI in forest areas are almost same with plantations, savanna, etc.","PeriodicalId":443250,"journal":{"name":"2014 International Conference on Advanced Computer Science and Information System","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 International Conference on Advanced Computer Science and Information System","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICACSIS.2014.7065848","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This research report about Fuzzy C-Means for Deforestation Identification Based On Remote Sensing Image. Deforestation means that changes forest area into another functions. Clustering is a method of classify objects into related groups (clusters). While, Fuzzy C-Means clustering is a technique that each data is determined by the degree of membership. In this research, the data used are MODIS EVI 250 m in 2000 and 2012 to identify deforestation rate in Java island. MODIS EVI is one of kind MODIS image which is able to detect vegetation based on photosynthesis rate and vegetation density. The number of clusters used were 13 clusters. This research had succeeded to classify areas based on the value of EVI like areas who had a high EVI values (forests, plantations, grass land), moderate values (agricultural area), and low values (build up area, mining area, pond, and other land cover). But, EVI value is only influenced by photosynthesis rate and vegetation density. Thus, EVI value is not well to identify forest areas, this is because the value of EVI in forest areas are almost same with plantations, savanna, etc.
本文研究了基于遥感影像的森林砍伐模糊c均值识别方法。森林砍伐意味着将森林变为另一种功能。聚类是一种将对象划分为相关组(聚类)的方法。而模糊c均值聚类是一种由隶属度决定每个数据的聚类技术。本研究使用2000年和2012年MODIS EVI 250 m数据来确定爪哇岛的森林砍伐率。MODIS EVI是一种基于光合速率和植被密度对植被进行检测的MODIS图像。使用的集群数量为13个集群。本研究成功地将EVI值划分为高EVI值区域(森林、人工林、草地)、中等EVI值区域(农业区)和低EVI值区域(建成区、矿区、池塘等土地覆盖)。而EVI值仅受光合速率和植被密度的影响。因此,EVI值并不能很好地识别森林区域,这是因为森林区域的EVI值与人工林、稀树草原等几乎相同。