---

A machine-based odour measurement technique was developed and then used to demonstrate the relationship between odour emission rates and pond loading rates. The developed technique consisted of an artificial neural network and a commercial electronic nose, AromaScan A32S, which is a reliable, rapid, and cost-effective technique for odour measurement. The results of olfactometry and the AromaScan were used to train the artificial neural network. The trained network was able to predict the odour emission rates for the test data with a correlation coefficient of 0.98. Time averaged odour emission rates which were predicted by the odour quantification technique, were strongly correlated with organic loading rate. Consequently, it can be concluded that a heavily loaded effluent pond would produce more odour.

---

Jae Ho Sohn, B.Sc., M.A.Sc., D.E: Studied Environmental Engineering at University of Southern Queensland. Senior Environmental Scientist in Department of Employment, Economic Development and Innovation, Queensland Government, Australia.

---