Login

Proceedings

Find matching any: Reset
Add filter to result:
Snap-shot Hyperspectral Camera for Potassium Prediction of Peach Trees Using Multivariate Analysis
J. J. Maja, M. Abenina, M. Cutulle, J. Melgar, H. Liu
Clemson University

Hyperspectral imaging (HSI) is an emerging technology being utilized in agriculture. This system could be used to monitor the overall health of plants or pest disease detection. As sensing technology advances, measuring nutrient levels and disease detection also progresses. This study aimed to predict the levels of potassium (K) content in peach leaves with the new snapshot hyperspectral camera. The study was conducted at the Clemson University Musser Fruit Research Farm (Seneca, SC, USA, 34.61 N, 82.87 W) during the months of September to October of 2020~2021. Three rows with three trees each were selected for this study. Young, full-sized leaves with petioles attached were picked around the tree with high and medium K content (45 leaves) and 50 leaves for the peach trees with low potassium content due to their size. Hyperspectral images were acquired from a randomly selected fresh peach leaf from multiple trees with varying potassium levels. The collected leaves were bagged for the three potassium levels. Fifteen leaves each were placed in the sample bags for the high and medium K trees and seventeen leaves each for the low K trees. The mature leaf samples were collected from the midportion or near the base of the tree’s current season’s terminal growth. The samples were then placed in one big paper bag and brought to the Clemson Agricultural Service Laboratory to run a plant tissue analysis on the nutrient content levels. Four pretreatment methods (Multiplicative Scatter Effect[MSC], Savitzky-Golay first derivative, Savitzky-Golay second derivative, and standard normal variate [SNV]) were applied to the raw data and used Partial Least Square (PLS) to develop a model for each of the pretreatment. The R2 values for each pre-treatment method were 0.8099, 0.6723, 0.5586, and 0.8446, respectively. The SNV prediction model has the highest accuracy and was used to predict the K nutrient using the validation data. The result showed a slightly lower R2=0.8101 as compared to the training. This study showed that the HSI could predict K content in Peach tree cultivars.   

Keyword: hyperspectral imaging, potassium, precision agriculture, multivariate analysis