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

Accurate and timely detection of plant stress is essential for yieldprotection, allowing better-targeted intervention strategies. Recent advancesin remote sensing and deep learning have shown great potential for rapidnon-invasive detection of plant stress in a fully automated and reproduciblemanner. However, the existing models always face several challenges: 1)computational inefficiency and the misclassifications between the differentstresses with similar symptoms; and 2) the poor interpretability of thehost-stress interaction. In this work, we propose a novel fast FourierConvolutional Neural Network (FFDNN) for accurate and explainable detection oftwo plant stresses with similar symptoms (i.e. Wheat Yellow Rust And NitrogenDeficiency). Specifically, unlike the existing CNN models, the main componentsof the proposed model include: 1) a fast Fourier convolutional block, a newlyfast Fourier transformation kernel as the basic perception unit, to substitutethe traditional convolutional kernel to capture both local and global responsesto plant stress in various time-scale and improve computing efficiency withreduced learning parameters in Fourier domain; 2) Capsule Feature Encoder toencapsulate the extracted features into a series of vector features torepresent part-to-whole relationship with the hierarchical structure of thehost-stress interactions of the specific stress. In addition, in order toalleviate over-fitting, a photochemical vegetation indices-based filter isplaced as pre-processing operator to remove the non-photochemical noises fromthe input Sentinel-2 time series.

A Fast Fourier Convolutional Deep Neural Network For Accurate and  Explainable Discrimination Of Wheat Yellow Rust And Nitrogen Deficiency From  Sentinel-2 Time-Series Data