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 crops using remote sensing technology is important for food securityand land management. Machine learning-based methods has become a popularapproach for crop mapping in recent years. However, the key to machinelearning, acquiring ample and accurate samples, is usually time-consuming andlaborious. To solve this problem, a crop mapping method in the small sample/nosample case that integrating domain knowledge and using a cascadedclassification framework that combine a weak classifier learned from sampleswith strong features and a strong classifier trained by samples with weakfeature was proposed. First, based on the domain knowledge of various crops, alow-capacity classifier such as decision tree was applied to acquire thosepixels with distinctive features and complete observation sequences as "strongfeature" samples. Then, to improve the representativeness of these samples,sample augmentation strategy that artificially remove the observations of"strong feature" samples according to the average valid observation proportionin target area was applied. Finally, based on the original samples andaugmented samples, a large-capacity classifier such as random forest wastrained for crop mapping. The method achieved an overall accuracy of 82% in theMAP crop recognition competition held by Syngenta Group, China in 2021 (thirdprize, ranked fourth). This method integrates domain knowledge to overcome thedifficulties of sample acquisition, providing a convenient, fast and accuratesolution for crop mapping.

Crop mapping in the small sample/no sample case: an approach using a two-level cascade classifier and integrating domain knowledge