To better understand the potential of soils, understanding how soil properties vary over time and in-field is essential to optimize the cultivation and site-specific technologies in crop pro-duction. This article aimed at determining the within-field mapping of soil chemical and physical properties, vegetation index, and yield of maize in 2002, 2006, 2010, 2013, and 2017, respectively. The objectives of this five-year field study were: (i) to assess the spatial and temporal variability of attributes related to the maize yield; and (ii) to analyse the temporal stability of management zones. The experiment was carried out in a 15.3 ha research field in Hungary. The soil measurements in-cluded sand, silt, clay content (%), pH, phosphorous (P2O5), potassium (K2O), and zinc (Zn) in the topsoil (30 cm). The apparent soil electrical conductivity was measured in two layers (0–30 cm and 30–90 cm, mS/m) in 2010, in 2013, and in 2017. The soil properties and maize yields were evaluated in 62 management zones, covering the whole research area. The properties were characterized as the spatial-temporal variability of these parameters and crop yields. Classic statistics and geostatis-tics were used to analyze the results. The maize yields were significantly positively correlated (r = 0.62–0.73) with the apparent electrical conductivity (Veris_N3, Veris_N4) in 2013 and 2017, and with clay content (r = 0.56–0.81) in 2002, 2013, and 2017.

In order to meet the requirements of sustainability and to determine yield drivers and limiting factors, it is now more likely that traditional yield modelling will be carried out using artificial intelligence (AI). The aim of this study was to predict maize yields using AI that uses spatio-temporal training data. The paper has advanced a new method of maize yield prediction, which is based on spatio-temporal data mining. To find the best solution, various models were used: counter-propagation artificial neural networks (CP-ANNs), XY-fused Querynetworks (XY-Fs), supervised Kohonen networks (SKNs), neural networks with Rectangular Linear Activations (ReLU), extreme gradient boosting (XGBoost), support-vector machine (SVM), and different subsets of the independent variables in five vegetation periods. Input variables for modelling included: soil parameters (pH, P2O5, K2O, Zn, clay content, ECa, draught force, Cone index), micro-relief averages, and meteorological parameters for the 63 treatment units in a 15.3 ha research field. The best performing method (XGBoost) reached 92.1% and 95.3% accuracy on the training and the test sets. Additionally, a novel method was introduced to treat individual units in a lattice system. The lattice-based smoothing performed an additional increase in Area under the curve (AUC) to 97.5% over the individual predictions of the XGBoost model. The models were developed using 48 different subsets of variables to determine which variables consistently contributed to prediction accuracy. By comparing the resulting models, it was shown that the best regression model was Extreme Gradient Boosting Trees, with 92.1% accuracy (on the training set). In addition, the method calculates the influence of the spatial distribution of site-specific soil fertility on maize grain yields. This paper provides a new method of spatio-temporal data analyses, taking the most important influencing factors on maize yields into account.

The aim of this study was to predict maize yield by artificial intelligence using spatio-temporal training data. Counter-propagation artificial neural networks (CP-ANNs), XY-fused networks (XY-Fs), supervised Kohonen networks (SKNs), extreme gradient boosting (XGBoost) and support-vector machine (SVM) were used for predicting maize yield in 5 vegetation periods. Input variables for modelling were: soil parameters (pH, P2O5, K2O, Zn, Clay content, ECa, draught force, Cone index), and micro-relief averages and meteorological parameters for the 63 treatment units. The best performing method (XGBoost) attained 92.1 and 95.3% of accuracy on the training and the test set.