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

Forecasting crop yields is becoming increasingly important under the current context inwhich food security needs to be ensured despite the challenges brought by climate change, an expandingworld population accompanied by rising incomes, increasing soil erosion, and decreasingwater resources. Temperature, radiation, water availability and other environmental conditions influence crop growth, development, andfinal grain yield in a complex nonlinearmanner.Machine learning (ML) techniques, and deep learning (DL)methods in particular, can account for such nonlinear relations between yield and its covariates. However, they typically lack transparency and interpretability, since theway the predictions are derived is not directly evident. Yet, in the context of yield forecasting, understandingwhich are the underlying factors behind both a predicted loss or gain is of great relevance. Here, we explore how to benefit from the increased predictive performance ofDLmethods whilemaintaining the ability to interpret how themodels achieve their results. To do so, we applied a deep neural network tomultivariate time series of vegetation andmeteorological data to estimate the wheat yield in the IndianWheat Belt. Then, we visualized and analyzed the features and yield drivers learned by themodel with the use of regression activationmaps. TheDLmodel outperformed other testedmodels (ridge regression and random forest) and facilitated the interpretation of variables and processes that lead to yield variability. The learned features weremostly related to the length of the growing season, and temperature and light conditions during this time. For example, our results showed that high yields in 2012were associatedwith low temperatures accompanied by sunny conditions during the growing period. The proposedmethodology can be used for other crops and regions in order to facilitate application ofDLmodels in agriculture.

Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt