This study reports the profiling of volatile compounds generated during microwave-assisted chemical pre-treatment of sorghum leaves. Compounds including acetic acid (0-186.26 ng/g SL), furfural (0-240.80 ng/g SL), 5-hydroxymethylfurfural (HMF) (0-19.20 ng/g SL) and phenol (0-7.76 ng/g SL) were detected. The reducing sugar production was optimized. An intelligent model based on Artificial Neural Networks (ANNs) was developed and validated to predict a profile of 21 volatile compounds under novel pre-treatment conditions. This model gave R-2-values of up to 0.93. Knowledge extraction revealed furfural and phenol exhibited high sensitivity to acid-and alkali concentration and S:L ratio, while phenol showed high sensitivity to microwave duration and intensity. Furthermore, furfural production was majorly dependent on acid concentration and fit a dosage-response relationship model with a 2.5% HCl threshold. Significant non-linearities were observed between pre-treatment conditions and the profile of various compounds. This tool reduces analytical costs through virtual analytical instrumentation, improving process economics. (C) 2016 Elsevier Ltd. All rights reserved.