Wheat Yield Prediction through Soil Properties Using Principle Component Analysis



An evaluation of the relationship between crop yield and soil properties would be useful in estimating the fluctuations in yield, and in an implementation of correct field management. The study was conducted in farmer operated wheat fields in Sorkhankalateh district, 25 km northeast of Gorgan, Golestan province, Iran. Soil samples (0-30 cm depth) were collected just after crop planting at the end of autumn 2004 from a 100 × 180m plot as a nested grid (n=101). A 1 m2 plot of wheat was harvested at each 101 previously sampled sites at the end of spring. Statistical results showed that frequency distribution of the data was normal. ESP had the variability of CV=12.36% while pH was of the lowest variability (CV=0.59%). For principal component analysis, 7 principal components were used in the study. Selection criterion then was employed for explaining the effective parameters in each component. The eigenvector for each PC, therefore was selected on the basis of having a value larger than the SC value. The results showed that such soil fertility parameters as available P (0.847), OM% (0.810), total N (0.742), available K (0.727) and CEC (0.725) bore larger loadings and therefore had the major role in soil variability. The results suggest that soil and crop yield variability were affected by management. The results of principle component analysis indicated that variability within the field was mostly derived from fertility parameters with multi-regression models explaining 57% of total variability of the yield in wheat.