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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Crop yield forecasting depends on many interactive factors, including cropgenotype, weather, soil, and management practices. This study analyzes theperformance of machine learning and deep learning methods for winter wheatyield prediction using an extensive dataset of weather, soil, and cropphenology variables in 271 counties across Germany from 1999 to 2019. Weproposed a Convolutional Neural Network (CNN) model, which uses a 1-dimensionalconvolution operation to capture the time dependencies of environmentalvariables. We used eight supervised machine learning models as baselines andevaluated their predictive performance using RMSE, MAE, and correlationcoefficient metrics to benchmark the yield prediction results. Our findingssuggested that nonlinear models such as the proposed CNN, Deep Neural Network(DNN), and XGBoost were more effective in understanding the relationshipbetween the crop yield and input data compared to the linear models. Ourproposed CNN model outperformed all other baseline models used for winter wheatyield prediction (7 to 14% lower RMSE, 3 to 15% lower MAE, and 4 to 50% highercorrelation coefficient than the best performing baseline across test data). Weaggregated soil moisture and meteorological features at the weekly resolutionto address the seasonality of the data. We also moved beyond prediction andinterpreted the outputs of our proposed CNN model using SHAP and force plotswhich provided key insights in explaining the yield prediction results(importance of variables by time). We found DUL, wind speed at week ten, andradiation amount at week seven as the most critical features in winter wheatyield prediction.

Winter wheat yield prediction using convolutional neural networks from environmental and phenological data