Computer imitates brain to predict algal outbreaks

While conventional approaches to the prediction of outbreaks of blue-green algae have been unsuccessful, there has been some success using a computer modelling process which mimics the human brain. The artificial neural networks utilised by the computer model enable it to ‘learn’ the key factors which contribute to an algal outbreak, enabling it to predict major blooms before they arise.

Adelaide University student Gavin Bowden has supplied the computer model with data compiled from water samples collected every week over the last 20 years by SA Water and the Murray-Darling Basin Commission.

“A range of environmental factors in the water are taken into account by the model,” explains Bowden. “These include nutrients, such as nitrogen and phosphorous, the flow and temperature of the water, turbidity and colour. There are other factors which influence the development of blue-green algae, but the beauty of using neural networks is that you can get reasonable predictions by including just the major factors.

“The importance of predicting blooms is that, due to the associated algal toxins, they represent a major water quality problem and their treatment can be costly,” adds Bowden. “If the model forecasts a bloom four weeks in advance, industry can get the appropriate treatment process ready and tackle the problem straight away, saving time, money and maintaining the quality of the water.”

Early results, although not 100% accurate, show the peaks and troughs of algal bloom development. Bowden believes that in six months he will have a fine-tuned, fully workable model which can be used by United Utilities Australia to predict blooms.