Forest cover classifications focus on the overall growth form (physiognomy) of the community, dominant vegetation, and species composition of the existing forest. Accurately classifying the forest cover type is important for forest inventory and silviculture. We compared classification accuracy based on Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and Satellite Pour l’Observation de la Terre (SPOT5) images for three land cover types (mixed oak forest, mixed hardwood forest, and agricultural) of the Cumberland Plateau, Jackson County, northern AL. The overall accuracy was 67 and 71 percent based on Landsat ETM+ and SPOT5 images, respectively. The most obvious commission error (misclassifying into wrong categories) was caused by mixed hardwood forest using SPOT-5 image and mixed oaks forest using Landsat ETM+ image, each was about 35 percent. The high omission error (omitting from correct categories) was associated with SPOT-5 data for the mixed hardwood and mixed oak forest. The low accuracy is typical for areas dominated by deciduous forest. Future research needs to explore the possibility of incorporating other GIS data such as variables derived from digital elevation model to improve the classification accuracy.
Wang, Yong; Parajuli, Shanta; Schweitzer, Callie; Smalley, Glendon; Lemke, Dawn; Tadesse, Wubishet; Chen, Xiongwen. 2010. Forested land cover classification on the Cumberland Plateau, Jackson County, Alabama: a comparison of Landsat ETM+ and SPOT5 images. In: Stanturf, John A., ed. 2010. Proceedings of the 14th biennial southern silvicultural research conference. Gen. Tech. Rep. SRS 121. Asheville, NC: U.S. Department of Agriculture, Forest Service, Southern Research Station. 409-413.