Prediction of the Hemp Yield Using Artificial Intelligence Methods

Abstract

The aim of this study was to determine the usefulness of artificial neural networks (ANN) in the process of forecasting the yield of hemp seeds (Cannabis sativa L.) of the Henola variety. The field experiments (various doses of mineral fertilization, sowing date, row spacing) results were also used to generate neural models. The highest straw (15.90 Mg∙ha−1) and seed (2.93 Mg∙ha−1) yield were obtained for the highest dose of mineral fertilization and sowing date at the turn of April and May in Wielkopolska Region resulted in the highest yields of both straw (14.70 Mg∙ha−1) and seeds (2.66 Mg∙ha−1). As a result of the conducted research, two linear models of ANN s were generated. The 4: 8–1: 1 model, used to forecast the seed yield was characterized by an accuracy of nearly 91%, and the RMSPE error less than 34%. The second model, the 4: 4–1: 1 network, was used to forecast the straw yield and had The test quality nearly 74%, and the RMSPE error 26%.

Keywords

• yield forecasting
• hemp cultivation
• artificial neural networks
• parameters of affecting yield
• cannabis sativa
• hemp seed
• hemp straw