Combining machine learning and ontological data handling for multi-source classification of nature conservation areas
详细信息 查看全文
- 作者：Niklas Morana ; niklas@niklasmoran.com" class="auth_mail" title="E-mail the corresponding author ; Simon Nielanda ; Gregor Tintrup gen. Suntrupb ; Birgit Kleinschmita
- 关键词：Remote sensing ; Ontology ; Biotope classification ; Machine learning ; Nature conservation ; OWL ; EUNIS ; GEOBIA ; Grasslands
- 刊名：International Journal of Applied Earth Observation and Geoinformation
- 出版年：2017
- 出版时间：February 2017
- 年：2017
- 卷：54
- 期：Complete
- 页码：124-133
- 全文大小：1919 K
文摘
- •
The importance of the Topographic Position Index (TPI) in determining the wetness of grasslands suggests that the wetter grasslands are found in areas lower than their surrounding.
- •
The developed grassland indicators wetness and alkalinity had an overall accuracy of 85% for alkalinity and 76% for wetness.
- •
The ontology-based classifier used reasoning to correctly classify 95% of dry and alkaline grasslands.