Probabilistic forecasting of crop yields via quantile random forest and Epanechnikov Kernel function

A reliable and accurate forecasting model for crop yields is of crucial importance for efficient decision-making process in the agricultural sector. However, due to weather extremes and uncertainties, most forecasting models for crop yield are not reliable and accurate. For measuring the uncertainty in crop yield forecast, a probabilistic forecasting model based on quantile random forest and Epanechnikov kernel function (QRF-E) is proposed. The non-linear structure of random forest is applied to build the non-linear quantile regression forecast model and to capture the non-linear relationship betweeen the weather variables and crop yield.. Epanechnikov kernel function and solve-the equation plug-in approach of Sheather and Jones are used in the density estimation. A case study using groundnut and millet yield in Ghana were presented to illustrate the efficiency and robustness of the proposed technique. The values of the prediction interval coverage probability and prediction interval normalized average width for the two crops showed that, the constructed prediction intervals captured the observed yields with high coverage probability. The probability density curves show that QRF-E method has a very high ability to forecast quality prediction intervals with a higher coverage probability. The feature importance gave a score of the importance of each weather variable in building the quantile random forest model. The farmer and other stakeholders are able to realize the specific weather variable that affects the yield of a selected crop through feature importance. The proposed method and its application on crop yield dataset are the first of its kind in literature.