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

Ground referencing is essential for supervised crop mapping. However,conventional ground truthing involves extensive field surveys and postprocessing, which is costly in terms of time and labor. In this study, weapplied a convolutional neural network (CNN) model to explore the efficacy ofautomatic ground truthing via Google street view (GSV) images in two distinctfarming regions: central Illinois and southern California. We demonstrated thefeasibility and reliability of the new ground referencing technique further byperforming pixel-based crop mapping with vegetation indices as the model input.The results were evaluated using the United States Department of Agriculture(USDA) crop data layer (CDL) products. From 8,514 GSV images, the CNN modelscreened out 2,645 target crop images. These images were well classified intocrop types, including alfalfa, almond, corn, cotton, grape, soybean, andpistachio. The overall GSV image classification accuracy reached 93% inCalifornia and 97% in Illinois. We then shifted the image geographiccoordinates using fixed empirical coefficients to produce 8,173 crop referencepoints including 1,764 in Illinois and 6,409 in California. Evaluation of thesenew reference points with CDL products showed satisfactory coherence, with 94to 97% agreement. CNN-based mapping also captured the general pattern of croptype distributions. The overall differences between CDL products and ourmapping results were 4% in California and 5% in Illinois. Thus, using thesedeep learning and GSV image techniques, we have provided an efficient andcost-effective alternative method for ground referencing and crop mapping.

Google street view and deep learning: a new ground truthing approach for crop mapping