Table S1 - Determining the Most Important Physiological and Agronomic Traits Contributing to Maize Grain Yield through Machine Learning Algorithms: A New Avenue in Intelligent Agriculture

Final dataset for running machine learning algorithms including the 166 records (rows) (derived from field and literature experiments) and 22 traits (features/columns). The traits were kernel number per ear, nitrogen (N) fertilizer applied (kg ha−1), plant density (plant ha−1), sowing date-location (country), stem dry weight (g plant−1), kernel dry weight (mg), duration of the grain filling period (°C day), kernel growth rate (mg °C day−1), Phosphorous (P) fertilizer applied (kg ha−1), mean kernel weight (mg), grain yield (g m−2), season duration (days), days to silking, leaf dry weight (g plant−1), mean kernel weight (mg), cob dry weight (g plant−1), soil pH, potassium (K) fertilizer applied (kg ha−1), hybrid type, defoliation, soil type, and the maximum kernel water content (MKWC) (mg). The yield was set as the output variable and the rest of variables as input (predictor) variables.
(XLS)