Predicting starch content of cassava with near infrared spectroscopy in Ugandan cassava germplasm

Abstract

In Uganda, efforts are underway to improve starch content through conventional breeding as a strategy for increasing adoption of new cassava varieties for both food and industry. However, only few samples can be quantified, limiting the gains in breeding. A database of 115 clones was used to evaluate the potential of Near infrared spectroscopy to predict starch content in cassava. Starch content ranged from 21.48 to 73.97% dry basis. The performance of standard normal variate and de-trend with second derivative calculated on two data points and smoothing plus combination of standard multiplicative scatter correction with second derivative calculated on two data points and smoothing were the best fit mathematical treatments for the calibrations developed. Near infrared spectroscopy predictions for starch content (R 2 = 0.85, and r 2 = 0.55) developed were reliable, thus usable for screening of cassava starch content at early stages of breeding.