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/

Zendy Plus

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

Zendy Tools

Zendy Open

A reliable and accurate forecasting model for crop yields is of crucialimportance for efficient decision-making process in the agricultural sector.However, due to weather extremes and uncertainties, most forecasting models forcrop yield are not reliable and accurate. For measuring the uncertainty andobtaining further information of future crop yields, a probability densityforecasting model based on quantile random forest and Epanechnikov kernelfunction (QRF-SJ) is proposed. The nonlinear structure of random forest isapplied to change the quantile regression model for building the probabilisticforecasting model. Epanechnikov kernel function and solve-the equation plug-inapproach of Sheather and Jones are used in the kernel density estimation. Acase study using the annual crop yield of groundnut and millet in Ghana ispresented to illustrate the efficiency and robustness of the proposedtechnique. The values of the prediction interval coverage probability andprediction interval normalized average width for the two crops show that theconstructed prediction intervals capture the observed yields with high coverageprobability. The probability density curves show that QRF-SJ method has a veryhigh ability to forecast quality prediction intervals with a higher coverageprobability. The feature importance gave a score of the importance of eachweather variable in building the quantile regression forest model. The farmerand other stakeholders are able to realize the specific weather variable thataffect the yield of a selected crop through feature importance. The proposedmethod and its application on crop yield dataset are the first of its kind inliterature.

Crop yield probability density forecasting via quantile random forest and Epanechnikov Kernel function