Resources > Latest News > What are the uses for data science in the water sector

What are the uses for data science in the water sector?

The digital revolution is bolstered by all kinds of buzzwords, but the fast-growing field of data science is beginning to offer water utilities the opportunity to make real change for their customers.

THIESS Data Science and Analytics, Innovation and Technology Manager Virginia Wheway said interest in data science has been spreading across industries, offering real-world results for organisations bold enough to venture.

“It’s no surprise that more and more data is being collected around the world, and I am sure that water organisations are facing the same level of data production,” Wheway said during her presentation at Ozwater’19.

“The world is producing data rapidly, but there is still a real gap between what is being used for decision-making and what is produced.

“And only 12% of executives feel like they understand the impact that data science can have on their organisation.”

Wheway said that while the world’s appetite for data science is growing, there’s still a need for organisations to understand what is required to turn data into useful information.

“If you are in the process of setting up a team, or thinking about what a data science team might do, you really need to bring it back to where you are at as an organisation in terms of data maturity,” she said.

“Some organisations that are at a lower level of maturity in terms of data systems make the mistake of hiring staff with PhDs in machine learning, who then end up sitting around with nothing to work on.”

Wheway said the capability of data systems moves from reporting through to analysis, with analysis then enabling monitoring and, eventually, prediction.

“Reporting is about what has happened. If things are not happening efficiently, you can then move to analysis. But you can’t move onto analysis until you have reliable data,” she said.

“Of course, the Holy Grail is prediction. And the step after that is prescription; that’s when the machines take over and start prescribing what to do in any event.”

While Wheway said many companies are still in the reporting and analysis phase of data science capability, Sydney Water Customer Hub Manager Darren Cash said the utility’s first foray into the Internet of Things (IoT) is paving the way for prediction, perhaps sooner than you’d think.

“Essentially, the vision for my team is to be proactive in our communications with customers, and predictive in the way that we manage our assets, and IoT is one of the enablers,” Cash said.

“Since last year, we have rolled our processes out to all areas of operations. One of the key focuses was minimising the impact of disruptions on our customers. We used a geospatial tool that we developed for the team.”

Despite not being able to predict disruptions just yet, Cash said Sydney Water has already seen improvements in customer relations that make the effort worthwhile.

“Some of the results have included minimising disruption impact to over 140,000 customers, which includes a financial saving from customer rebates paid due to disruptions,” he said.

“We’ve notified 80,000 customers about water disruptions in advance. Over 35,000 have been kept informed about progress on faults that have been recorded.

“Furthermore, since we went to live operations and have been sending these notifications, we have noticed a 40% reduction in inbound calls. It makes sense; if you tell people what’s going on, they are less likely to call.”

Cash said Sydney Water is also improving its understanding of the types of problems customers are having, which will help to more effectively predict issues in future.

“Generally, we have to wait for the disruption to happen before we are able to do anything about it,” he said.

“But we want to get to the point where we can identify issues before they affect our customers. There are a few enablers that will allow us to do that and we see IoT as one of those.

“We might still just be responding to something that has happened, but this experience is going to give us an indication of where we need to take predictive action to help our customers in the future.”