First results from the Phenology-Based Synthesis classifier using Landsat 8 imagery
A fully automatic phenology based synthesis classification (PBS) algorithm was developed to map land
cover based on medium spatial resolution satellite data using Google Earth Engine (GEE) cloud
computing platform. Vegetation seasonality, especially in the tropical dry regions, can lead
conventional algorithms based on a single date image classification to “misclassify” land cover types,
as the selected date might reflect only a particular stage of the natural phenological cycle. The PBS
classifier operates with occurrence rules applied to a selection of single date image classifications
(SDC) of the study area to assign the most appropriate land cover class.
Since the launch of Landsat 8 2013, it has been possible to acquire imagery at any point on the Earth
every 16 days with exceptional radiometric quality. The relatively high global acquisition frequency
and the open data policy allow near real time land cover mapping and monitoring with automated tools
such as the PBS classifier.
We mapped four protected areas and their 20km buffer zones from different ecoregions in Sub-Saharan
Africa using the PBS classifier to present its first results. Accuracy assessment was carried out through
a visual interpretation of very high resolution images using a WEB-GIS interface. The combined
overall accuracy was over 90% which demonstrates the potential of the classifier and the power of
cloud computing in geospatial sciences.
SIMONETTI Dario;
SIMONETTI Edoardo;
SZANTOI Zoltan;
LUPI Andrea;
EVA Hugh;
2015-04-13
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
JRC95065
1545-598X,
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7061922&sortType%3Dasc_p_Sequence%26filter%3DAND%26rowsPerPage%3D75,
https://publications.jrc.ec.europa.eu/repository/handle/JRC95065,
10.1109/LGRS.2015.2409982,
Additional supporting files
File name | Description | File type | |