Abstract
This study analyzed meteorological constraints on winter wheat yield in the northern Japanese island, Hokkaido, and developed a machine learning model to predict municipality-level yields from meteorological data. Compared to most wheat producing areas, this island is characterized by wet climate owing to greater annual precipitation and abundant snowmelt water supply in spring. Based on yield statistics collected from 119 municipalities for 14 years (N = 1,516) and high-resolution surface meteorological data, correlation analyses showed that precipitation, daily minimum air temperature, and irradiance during the grain-filling period had significant effects on the yield throughout the island while the effect of snow depth in early winter and spring was dependent on sites. Using 10-d mean meteorological data within a certain period between seeding and harvest as predictor variables and one-year-leave-out cross-validation procedure, performance of machine learning models based on neural network (NN), random forest (RF), support vector machine regression (SVR), partial least squares regression (PLS), and cubist regression (CB) were compared to a multiple linear regression model (MLR) and a null model that returns an average yield of the municipality. The root mean square errors of PLS, SVR, and RF were 872, 982, and 1,024 kg ha−1 and were smaller than those of MLR (1,068 kg ha−1) and null model (1,035 kg ha−1). These models outperformed the controls in other metrics including Pearson’s correlation coefficient and Nash-Sutcliffe efficiency. Variable importance analysis on PLS indicated that minimum air temperature and precipitation during the grain-filling period had major roles in the prediction and excluding predictors in this period (i.e. yield forecast with a longer lead-time) decreased forecast performance of the models. These results were consistent with our understanding of meteorological impacts on wheat yield, suggesting usefulness of explainable machine learning in meteorological crop yield prediction under wet climate.
Highlights
Crop yield prediction models are undoubtedly required for agricultural practices
In most southern and central regions, the smallest yields were recorded in 2009 or 2018 with heavy summer rain. These data indicate that winter wheat yield should be affected by regional-scale meteorology
We developed a machine learning model based on the partial least squares method that predicts and forecasts wheat yield reasonably well
Summary
Crop yield prediction models are undoubtedly required for agricultural practices. Statistical regression methods, including multiple linear regression, have been sometimes used for crop yield prediction in earlier studies. With increased available data sources and predictor variables, studies have attempted to predict crop yield using machine learning instead of the multiple linear regression method [3]. Several earlier studies applied artificial neural networks for crop yield prediction. Wang et al [10] proposed a model consists of long short-term memory and convolution neural networks to predict winter wheat yield at county level in China (RMSE: 721 kg ha−1). Machine learning techniques have been utilized to predict yields of other crops [e.g. 12, 13] and to monitor evapotranspiration for water resources engineering [e.g. 14, 15] Some of these studies have analyzed the importance of predictor variables to improve models’ interpretability and predictive performance [7, 9, 11, 12]. Shahhosseini et al [17] extended the APSIM model to calculate various features related to plant growth and used them and other features as inputs for machine learning models to predict corn yield in the US
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.
