The application of spectroscopic methods to predict sugarcane quality based on stalk cross-sectional scanning
Article
Article Title | The application of spectroscopic methods to predict sugarcane quality based on stalk cross-sectional scanning |
---|---|
Article Category | Article |
Authors | Nawi, Nazmi Mat (Author), Jensen, Troy (Author) and Chen, Guangnan (Author) |
Journal Title | American Society of Sugar Cane Technologists Journal |
Journal Citation | 32, pp. 16-27 |
Number of Pages | 12 |
Year | 2012 |
Place of Publication | Baton Rouge, LA. United States |
Web Address (URL) | http://www.assct.org/journal/JASSCT%20PDF%20Files/volume%2032/Nazmi%20-%20Revised%20paper%20for%20JASST%20v2012-3-12.pdf |
Abstract | With the increasing adoption of Precision Agriculture (PA) technique in the sugarcane industry, there is a growing need for a reliable method of in-field quality measurement. However, current PA monitoring systems can only monitor cane yield and have no ability to measure the product quality. Thus, the purpose of this study was to evaluate the ability of the spectroscopic techniques as a rapid and non-destructive tool to predict quality properties of sugarcane in the field. Both handheld Vis/NIR (350-1075 nm) and full range (350 - 2500 nm) spectroradiometers were used to determine the quality attributes of sugarcane by scanning the cross-sectional surface of the stalk. NIR calibration models were constructed using a set of 100 stalks, each which were further cut into three sections of top, middle and bottom sections. After preprocessing treatments, Partial Least Squares (PLS) method was used to interpret spectra and to develop calibration model for sugarcane quality. The overall coefficient of determination (r2) for Brix, Pol, CCS and fibre as predicted by the Vis/NIR for all sample sections were 0.68, 0.71, 0.70 and 0.56 respectively. The corresponding r2 for Brix, Pol, CCS and fibre as predicted by the FRs were 0.76, 0.76, 0.81 and 0.68 respectively. It was found that by using Vis/NIR, the top section can achieve r2 of 0.89 for CCS prediction. The results suggested that spectroscopy based on stalk cross-sectional scanning is a feasible method for mapping and predicting sugarcane quality in the field. |
Keywords | sugarcane; commercial cane sugar (CCS); quality attributes; NIR; spectroradiometer |
ANZSRC Field of Research 2020 | 300206. Agricultural spatial analysis and modelling |
460304. Computer vision | |
409901. Agricultural engineering | |
Public Notes | Open access journal. |
Byline Affiliations | National Centre for Engineering in Agriculture |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q13x3/the-application-of-spectroscopic-methods-to-predict-sugarcane-quality-based-on-stalk-cross-sectional-scanning
Download files
2215
total views499
total downloads1
views this month2
downloads this month