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

Climate change is posing new challenges to crop-related concerns includingfood insecurity, supply stability and economic planning. As one of the centralchallenges, crop yield prediction has become a pressing task in the machinelearning field. Despite its importance, the prediction task is exceptionallycomplicated since crop yields depend on various factors such as weather, landsurface, soil quality as well as their interactions. In recent years, machinelearning models have been successfully applied in this domain. However, thesemodels either restrict their tasks to a relatively small region, or only studyover a single or few years, which makes them hard to generalize spatially andtemporally. In this paper, we introduce a novel graph-based recurrent neuralnetwork for crop yield prediction, to incorporate both geographical andtemporal knowledge in the model, and further boost predictive power. Our methodis trained, validated, and tested on over 2000 counties from 41 states in theUS mainland, covering years from 1981 to 2019. As far as we know, this is thefirst machine learning method that embeds geographical knowledge in crop yieldprediction and predicts the crop yields at county level nationwide. We alsolaid a solid foundation for the comparison with other machine learningbaselines by applying well-known linear models, tree-based models, deeplearning methods and comparing their performance. Experiments show that ourproposed method consistently outperforms the existing state-of-the-art methodson various metrics, validating the effectiveness of geospatial and temporalinformation.

A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction