Abstract
Forecasting crop yields is becoming increasingly important under the current context in which food security needs to be ensured despite the challenges brought by climate change, an expanding world population accompanied by rising incomes, increasing soil erosion, and decreasing water resources. Temperature, radiation, water availability and other environmental conditions influence crop growth, development, and final grain yield in a complex nonlinear manner. 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 the way the predictions are derived is not directly evident. Yet, in the context of yield forecasting, understanding which 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 of DL methods while maintaining the ability to interpret how the models achieve their results. To do so, we applied a deep neural network to multivariate time series of vegetation and meteorological data to estimate the wheat yield in the Indian Wheat Belt. Then, we visualized and analyzed the features and yield drivers learned by the model with the use of regression activation maps. The DL model outperformed other tested models (ridge regression and random forest) and facilitated the interpretation of variables and processes that lead to yield variability. The learned features were mostly 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 2012 were associated with low temperatures accompanied by sunny conditions during the growing period. The proposed methodology can be used for other crops and regions in order to facilitate application of DL models in agriculture.
Highlights
The Food and Agriculture Organization (FAO) of the United Nations estimates that 50% more food needs to be produced by 2050 in order to feed the increasing world population (FAO 2017)
convolutional neural networks (CNNs) models provided the best results overall that were stable among model runs (S4), which shows applicability of such models to dense time series for yield estimation
Application of deep learning (DL) models for yield estimation Even though our DL modeling approach was constrained by the requirement for network explainability, it outperformed RF and RR in the yield estimation task, though RF provided a strong performance improvement as compared to RR
Summary
The Food and Agriculture Organization (FAO) of the United Nations estimates that 50% more food needs to be produced by 2050 in order to feed the increasing world population (FAO 2017). Meteorological variables influence crop growth, development, and final grain yield in a nonlinear manner and often with complex interactions (Siebert et al 2017, Akter and Rafiqul Islam 2017) These variables are accounted for in both process-based as well as statistical models to estimate crop yield (e.g. Lobell et al 2011, Iizumi et al 2018). While process-based models require detailed (and not always available) information on the farmers’ practices, recent increase in the availability of global satellite observations and advancements in statistical methods have fueled the application of machine learning (ML) models at various scales (e.g. Lobell et al 2011, Guan et al 2017, Cai et al 2019) Such models may have the capability of accounting for additional factors reducing growth and yield (e.g. pests, diseases, weeds and other perils)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
