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

Abstract

A reliable and accurate forecasting model for crop yields is of crucial importance for efficient decision-making processing 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 between 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 yieldin 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 observedyieldswithhighcoverageprobability.TheprobabilitydensitycurvesshowthatQRF-Emethodhasa very high ability to forecast quality prediction intervals with a higher coverage probability. The feature importancegaveascoreoftheimportanceofeachweathervariableinbuildingthequantilerandomforestmodel. The farmer and other stakeholders are able to realize the specific weather variable that affects the yield of a selectedcropthroughfeatureimportance.Theproposedmethodanditsapplicationoncropyielddatasetarethe firstofitskindinliterature.