Prediction of Sprouting Capacity Using Near-infrared Spectroscopy in Potato Tubers

Abstract

The potential of near infra-red spectroscopy (NIRS) for predicting the sprouting capacity of potato (Solanum tuberosum L.) tubers was investigated. The experiment was conducted for 2 years using 'Superior' and 'Atlantic' potatoes. A total of 380 potato tubers (200, Superior; 180, Atlantic) weighing 100-200 g were scanned by NIRS, and the sample sets were divided into four groups; three groups were classified based on the cultivars or years as follows: 'Superior', 2004; 'Superior', 2005; 'Atlantic', 2005; the fourth group contained the total number of samples. The reference value for the sprouting capacities was measured by determining the sprout weight after 30 days of incubation at 20°C. The first derivative transformation equation for raw optical data was standardized by applying standard normal variate (SNV) and detrending (DT) algorithms, and calibration equations between them were developed by modified partial least square (MPLS) regression. The coefficient of determination (r 2 ) ranged from 0.868 to 0.965 with a standard error of calibration (SEC) from 0.31 to 0.40 for the calibration sets; r 2 ranged from 0.724 to 0.904 with a standard error of prediction (SEP) from 0.532 to 0.602 for the four validation sets. These results indicate that the calibration model obtained from this experiment is applicable to all the different cultivars for different years, and the NIRS method is a powerful tool for the predictive assessment of the sprouting capacity of potato tubers.

Prediction of the Leaf Primordia of Potato Tubers Using Sensor Fusion and Wavelength Selection

“…Whereas, the r(RPD) values obtained from the VIS/NIR hyperspectral imaging systems were 0.47(1.14) for FL1879 and 0.43(1.10) for R.Norkotah. Additionally, prediction results obtained from the fused data in this study are comparable to the work conducted by Jeong et al [27] for estimating potato sprouting using NIR diffuse reflectance data. The latter study had r(RPD) values of 0.94(2.0) for the calibration models using cross validation.…”

A comparison of different optical instruments and machine learning techniques to identify sprouting activity in potatoes during storage

“…Ultraviolet (UV), visible (Vis), and near-infrared (NIR) spectroscopic techniques have been successfully developed into commercial technologies for sorting and grading fruits and vegetables based on shape, size, defect presence, and color. In the case of potatoes, several studies have been conducted for using spectroscopic systems in evaluating various constituents including specific gravity [16], dry matter [16][17][18], and carbohydrates [19][20][21][22].…”

Precautionary analysis of sprouting potato eyes using hyperspectral imaging technology

“…Some researches were carried out to detect sprouted potatoes [7,8] . Jeong et al [7] took sprout capacity (generally expressed as the sprout weight of uniform tubers after a standard sprouting procedure) as the indicator to determine the physiological age of potato tubers, and investigated the potential of near infra-red spectroscopy (NIRS) for predicting the sprout capacity.…”