A Local Model Based on Environmental Variables Clustering for Estimating Foliar Phosphorus of Rubber Trees with Vis-NIR Spectroscopic Data

Abstract

Existing local models based on multiple environmental variables clustering (LM-MEVC) treat the influences of environmental factors on leaf phosphorus concentration (LPC) of rubber trees (Hevea brasiliensis) equally when grouping samples. In fact, the effects that environmental factors assert on LPC are different. So, environmental factors need to be treated differently so that the different effects can be taken into consideration when dividing samples into clusters or groups. According to this basic idea, a local model based on weighted environmental variables clustering (LM-WEVC) was developed. This approach used weighted environmental factors as clustering variables to group samples. Within each cluster or group of samples, an estimation model was established. In order to verify its effectiveness in predicting LPC of rubber trees, the proposed method was applied to a case study in Hainan Island, China. Leaf samples were collected from three different sampling periods, and were used separately to test LM-WEVC. Coefficient of determination (R²), root mean squared error (RMSE), and ratio of prediction deviation (RPD) were employed as evaluation criterion. Performance of LM-WEVC was compared with that of LM-MEVC (a local model based on multiple environmental variables clustering). Results indicated that for the three sampling periods, the prediction accuracies of LM-WEVC were always much higher than those of LM-MEVC. The values of R2 of LM-WEVC were 26.46%, 38.07%, and 23.51% higher than those of LM-MEVC for the first, the second and the third sampling period, respectively; the values of RPD of LM-WEVC were 37.17%, 12.94%, and 28.81% higher than those of LM-MEVC for the first, the second, and the third sampling period, respectively; and the values of RMSE of LM-WEVC were 28.57%, 11.54%, and 23.68% lower than those of LM-MEVC for the first, the second, and the third sampling period, respectively. These results demonstrate that LM-WEVC was effective in estimating LPC of rubber trees, and also confirmed our hypothesis that environmental factors unequally influenced LPC of rubber trees.

Keywords: K-means clustering, partial least squares regression, hyperspectral reflectance, regional scale, environmental factors