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

Mapping and monitoring crops is a key step towards sustainableintensification of agriculture and addressing global food security. A datasetlike ImageNet that revolutionized computer vision applications can acceleratedevelopment of novel crop mapping techniques. Currently, the United StatesDepartment of Agriculture (USDA) annually releases the Cropland Data Layer(CDL) which contains crop labels at 30m resolution for the entire United Statesof America. While CDL is state of the art and is widely used for a number ofagricultural applications, it has a number of limitations (e.g., pixelatederrors, labels carried over from previous errors and absence of input imageryalong with class labels). In this work, we create a new semantic segmentationbenchmark dataset, which we call CalCROP21, for the diverse crops in theCentral Valley region of California at 10m spatial resolution using a GoogleEarth Engine based robust image processing pipeline and a novel attention basedspatio-temporal semantic segmentation algorithm STATT. STATT uses re-sampled(interpolated) CDL labels for training, but is able to generate a betterprediction than CDL by leveraging spatial and temporal patterns in Sentinel2multi-spectral image series to effectively capture phenologic differencesamongst crops and uses attention to reduce the impact of clouds and otheratmospheric disturbances. We also present a comprehensive evaluation to showthat STATT has significantly better results when compared to the resampled CDLlabels. We have released the dataset and the processing pipeline code forgenerating the benchmark dataset.

CalCROP21: A Georeferenced multi-spectral dataset of Satellite Imagery and Crop Labels