Identification of high nature value grassland with remote sensing and minimal field data

详细信息    查看全文

• 作者：Stefanie Stenzel^a ; ^{stefanie.stenzel@partner.kit.edu} ; Fabian Ewald Fassnacht^a ; Benjamin Mack^b ; Sebastian Schmidtlein^a
• 关键词：High nature value farmland ; HNV ; Common agricultural policy ; Nature conservation ; Grassland ; Remote sensing ; One-class classification ; Maxent ; RapidEye
• 刊名：Ecological Indicators
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：74
• 期：Complete
• 页码：28-38
• 全文大小：2141 K
• 卷排序：74

文摘

We used multi-seasonal, multispectral remote sensing data in combination with sparse field data to identify high nature value grassland. There seems to be a signal in the reflectance of grasslands that makes it possible to differentiate high nature value grasslands from intensively used grasslands. Several oneclass classifers have been tested, BiasedSVM and Maxent are our winners.