English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Global forest cover is critical to the provision of certain ecosystemservices. With the advent of the google earth engine cloud platform, fineresolution global land cover mapping task could be accomplished in a matter ofdays instead of years. The amount of global forest cover (GFC) products hasbeen steadily increasing in the last decades. However, it's hard for users toselect suitable one due to great differences between these products, and theaccuracy of these GFC products has not been verified on global scale. Toprovide guidelines for users and producers, it is urgent to produce avalidation sample set at the global level. However, this labeling task is timeand labor consuming, which has been the main obstacle to the progress of globalland cover mapping. In this research, a labor-efficient semi-automaticframework is introduced to build a biggest ever Forest Sample Set (FSS)contained 395280 scattered samples categorized as forest, shrubland, grassland,impervious surface, etc. On the other hand, to provide guidelines for theusers, we comprehensively validated the local and global mapping accuracy ofall existing 30m GFC products, and analyzed and mapped the agreement of them.Moreover, to provide guidelines for the producers, optimal sampling strategywas proposed to improve the global forest classification. Furthermore, a newglobal forest cover named GlobeForest2020 has been generated, which proved toimprove the previous highest state-of-the-art accuracies (obtained by Gong etal., 2017) by 2.77% in uncertain grids and by 1.11% in certain grids.

Improving Global Forest Mapping by Semi-automatic Sample Labeling with Deep Learning on Google Earth Images