Challenges and opportunities in synthesizing historical geospatial data using statistical models
详细信息 查看全文
- 作者：M.V. Eitzela ; mveitzel@ucsc.edu" class="auth_mail" title="E-mail the corresponding author ; Maggi Kellya ; Iryna Dronovab ; Yana Valachovicc ; Lenya Quinn-Davidsonc ; Jon Solerad ; Perry de Valpinea
- 关键词：OBIA ; Object-Based Image Analysis ; DEM ; Digital Elevation Model ; GAM ; Generalized Additive Model ; NAIP ; National Agricultural Imagery Program ; NDVI ; Normalized Difference Vegetation Index ; GLCM ; Gray-level Co-occurrence Matrix ; MRF ; Markovian Random Field ; GIS ; Geographic Information Systems ; RMSE ; Root Mean Squared Error
- 刊名：Ecological Informatics
- 出版年：2016
- 出版时间：January 2016
- 年：2016
- 卷：31
- 期：Complete
- 页码：100-111
- 全文大小：1990 K
文摘
- •
Modern mapping technology allows us to make quantitative use of historical data.
- •
We use Object-Based Image Analysis to map woody cover change from historical images.
- •
We model woody cover as a function of historical cover and topographic variables.
- •
We use Generalized Additive Models to account for spatial autocorrelation.
- •
Results of statistical models are highly dependent on the size of raster cells used.