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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Geospatial datasets derived from remote sensing data by means of machinelearning methods are often based on probabilistic outputs of abstract nature,which are difficult to translate into interpretable measures. For example, theGlobal Human Settlement Layer GHS-BUILT-S2 product reports the probability ofthe presence of built-up areas in 2018 in a global 10 m x 10 m grid. However,practitioners typically require interpretable measures such as binary surfacesindicating the presence or absence of built-up areas or estimates of sub-pixelbuilt-up surface fractions. Herein, we assess the relationship between thebuilt-up probability in GHS-BUILT-S2 and reference built-up surface fractionsderived from a highly reliable reference database for several regions in theUnited States. Furthermore, we identify a binarization threshold using anagreement maximization method that creates binary built-up land data from thesebuilt-up probabilities. These binary surfaces are input to a spatiallyexplicit, scale-sensitive accuracy assessment which includes the use of anovel, visual-analytical tool which we call focal precision-recall signatureplots. Our analysis reveals that a threshold of 0.5 applied to GHS-BUILT-S2maximizes the agreement with binarized built-up land data derived from thereference built-up area fraction. We find high levels of accuracy (i.e.,county-level F-1 scores of almost 0.8 on average) in the derived built-upareas, and consistently high accuracy along the rural-urban gradient in ourstudy area. These results reveal considerable accuracy improvements in humansettlement models based on Sentinel-2 data and deep learning, in both rural andurban areas, as compared to earlier, Landsat-based versions of the Global HumanSettlement Layer.

Spatially explicit accuracy assessment of deep learning-based, fine-resolution built-up land data in the United States