Yield and Quality Prediction of Winter Rapeseed—Artificial Neural Network and Random Forest Models

As one of the greatest agricultural challenges, yield prediction is an important issue for producers, stakeholders, and global trade market. Most variation in attributed to environmental factors such as climate conditions, soil type cultivation practices. Artificial neural networks (ANNs) random forest regression (RFR) are machine learning tools that used unambiguously crop prediction. There limited research regarding application these mathematical models rapeseed quality. A four-year study (2015–2018) was carried out Republic Serbia with 40 winter genotypes. The field trial designed a randomized complete block design three replications. ANN, based on Broyden–Fletcher–Goldfarb–Shanno iterative algorithm, RFR were seed yield, oil protein content, 1000 weight, year production genotype. best 2016, when highest achieved, 2994 kg/ha 1402 kg/ha, respectively. model showed better capabilities compared ANN (the r2 values output variables 0.944, 0.935, 0.912, 0.886, 0.936 0.900, respectively).