Research Paper Prediction and classification of sugar content of sugarcane based on skin scanning using visible and shortwave near infrared Nazmi Mat Nawi a,c, *, Guangnan Chen a,b , Troy Jensen a,b , Saman Abdanan Mehdizadeh d a Faculty of Engineering and Surveying, University of Southern Queensland, Toowoomba, QLD 4350, Australia b National Centre for Engineering in Agriculture (NCEA), University of Southern Queensland, Toowoomba, QLD 4350, Australia c Department of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia d Department of Agricultural Machinery and Mechanization, Ramin Khuzestan University of Agriculture and Natural Resources, Khuzestan, Iran article info Article history: Received 2 January 2013 Received in revised form 27 February 2013 Accepted 8 March 2013 Published online 19 April 2013 The potential application of a visible and shortwave near infrared (Vis/SWNIR) spectro- scopic technique as a low cost alternative to predict sugar content based on skin scanning was evaluated. Two hundred and ninety one internode samples representing three different commercial sugarcane varieties were used. Each sample was scanned at four scanning points to obtain the spectra data which was later correlated with its  Brix (soluble solids content) values. Partial least square (PLS) model was developed and applied to both calibration and prediction samples. Using reflectance spectra data, the model had a coef- ficient of determination (R 2 ) of 0.91 and root means square error of predictions (RMSEP) of 0.721  Brix. The artificial neural network (ANN) was also applied to classify spectra data into five  Brix categories. The ANN has yielded good classification performance, ranging from 50 to 100% accuracy with an average accuracy of 83.1%. These results demonstrated that the Vis/SWNIR spectroscopy technique could be applied to predict sugarcane  Brix in the field based skin scanning method. ª 2013 IAgrE. Published by Elsevier Ltd. All rights reserved. 1. Introduction Precision agriculture (PA) is a valuable management strategy to enhance farm profits through efficient application of crop inputs by matching them with variations of crop yield and quality in the field (Wendte, Skotnikov, & Thomas, 2001). The primary requirements for PA application are yield monitoring and mapping. To date, several studies have been carried out to produce a yield map in sugarcane industries around the world, including Australia (Cox, Harris, Pax, & Dick, 1996), Brazil (Magalha ˜ es & Cerri, 2007) and the US (Price, Johnson, Viator, Larsen, & Peters, 2011). However, an extensive review published by Bramley (2009) regarding PA application in sug- arcane industry revealed that current PA technologies only monitor the yield but do not have the ability to measure product quality. This is a serious limitation because both yield * Corresponding author. Department of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia. E-mail addresses: nazmi@eng.upm.edu.my, naj_miey@hotmail.com (N. Mat Nawi). Available online at www.sciencedirect.com journal homepage: www.elsevier.com/locate/issn/15375110 biosystems engineering 115 (2013) 154 e161 1537-5110/$ e see front matter ª 2013 IAgrE. Published by Elsevier Ltd. All rights reserved. http://dx.doi.org/10.1016/j.biosystemseng.2013.03.005