PARTITIONING THE WHEAT GRAINS BY THE UNIFORMITY OF PROTEIN QUALITY BASED ON REMOTE SENSING

Tian Weixin, Chen Chen, Xiaoyu Song, Dong Ren, and Jihua Wang

Keywords

Protein quality, uniformity, remote sensing, M5 model tree

Abstract

Separating the wheat grains by its protein quality (PQ) uniformity can add the values of the wheat. This paper proposed an approach to predict the PQ uniformity of wheat when they are growing on field and help partitioning them on PQ uniformity by region. We first partitioned the experimental plot as three scales of 10 m × 10 m, 15 m × 15 m, 20 m × 20 m and used three different methods to ascertain that the best scale to partition the wheat grains by the PQ uniformity was the 10 m × 10 m, and the best method was the M5 model tree. Secondly, we used the M5 model tree on the 10 m × 10 m scale, and applied the spatial information to reinforce the partition performance. Compared with the traditional approach based on Kriging, the method proposed in the paper improved the stability performance of the traditional approach without losing accuracy.

Important Links:

Go Back