Table 1.
Physical and chemical properties of the soil used in the pots.
Table 2.
Chemical characteristics of the irrigation water.
Fig 1.
Structure of artificial neural network for sunflower grain yield prediction.
LL: Leaf length; LW: Leaf width; PL: Petiole length; LN: Leaf number; SD: Stem diameter; PH: Plant height; HDW: Head dried weight; HSW: Hundred-seed weight; DF: Date to flowering; HD: Head diameter.
Fig 2.
Structure ANFIS model based on two input parameters (for the sample) to predict sunflower seed yield.
Table 3.
The parameters of the GEP method utilized in the present investigation.
Fig 3.
Sunflower seed yield prediction steps using ANN, ANFIS, and GEP models.
Fig 4.
Scatter plot of the observed (actual) vs. predicted values of sunflower grain yield with the ANN model in the test phase: (a) Normal conditions and (b) Salinity stress conditions.
Fig 5.
Scatter plot of the observed (actual) vs. predicted values of sunflower grain yield with the ANFIS model in the test stage: (a) Normal conditions and (b) Salinity stress conditions.
Table 4.
Descriptive statistics for agricultural traits measured in the population of inbred sunflower recombinant lines.
Table 5.
Evaluating the efficacy of three models (ANN, ANFIS, and GEP) to predict sunflower grain yield under normal and salt stress.
Fig 6.
Scatter plot of the observed (actual) vs. predicted values of sunflower grain yield with the GEP model in the test stage: (a) Normal conditions and (b) Salinity stress conditions.
Fig 7.
Comparison of the accuracy evaluation statistics of models (ANN, ANFIS, and GEP) to predict the yield of sunflower grains in the test stage: (a) Normal conditions and (b) Salt stress conditions.
Fig 8.
Taylor diagrams to compare the performance of models (ANN, ANFIS, and GEP) to predict the yield of sunflower grains in the test stage: (a) Normal conditions and (b) Salt stress conditions.
Fig 9.
Violin diagrams of models (ANN, ANFIS, and GEP) to predict the yield of sunflower grains in the test stage: (a) Normal conditions and (b) Salt stress conditions.