According to Australia’s peak motoring body, the Australian Automobile Association (AAA), the 12 months to January 31, the nation’s road toll climbed to 1,257, a 5.4 per cent increase on the same period a year ago.

This figure also sees a 30.8 per cent rise in road deaths in NSW, 39.7 per cent in South Australia and 14.8 per cent in Victoria.

The surge in road deaths in January is continued from the second half of 2023, which saw 683 deaths recorded – the deadliest half on Aussie roads since 2010.

2023 was Australia’s deadliest on the roads in five and a half years, when 1270 people were killed in the 12 months to March 2018.

Last year’s toll was 6.8 per cent more than 2022, but only 3.6 per cent when excluding Victoria, a state which saw the greatest loss of life on the road in 15 years.

Now there are plenty of causes of road death, with the Transport Accident Commission (TAC) pointing to intoxication, fatigue and drivers not wearing seatbelts.

Others call for stronger police enforcement to correct dangerous driving habits and for government to review speed limits on country roads.

While other factors that may be more prevalent overseas (road deaths being a global issue), include road design issues and damage.

A new study in Greece has seen a new machine learning model that can predict car crash sites, which they hope can be used globally.

This new research published in Transportation Research Record, was a collaboration between University of Massachusetts-Amherst civil and environmental engineer professors Jimi Oke, Eleni Christofa and Simos Gerasimidi and civil engineers from Egnatia Odos, a publicly owned engineering firm in Greece.

They found that the most influential features across almost 15km of roads in 7000 locations in Greece, included road design issues like abrupt speed limit changes or ​​guardrail issues, damage (cracks on the road), and incomplete signage and road markings.

With road designs varying around the world, these issues can be found regardless suggests Oke, who uses the US as an example.

“The problem itself is globally applicable—not just to Greece,” he said.

“The indicators themselves are universal types of observations, so there’s no reason to believe that they wouldn’t be generalisable to the US.”

He also notes that this approach can be readily deployed on new data from other locations, and puts decades of road data to good use.

“We have all these measures that we can use to predict the crash risk on our roads and that is a big step in improving safety outcomes for everyone.”

“We had 60-some-odd indicators. But now, we can just really focus our money on capturing the ones that we need.

“One could dig deeper to understand how a certain feature actually could contribute to crashes.”

This could then measure to see if fixing the issue would actively reduce the number of incidents that occur.

Oke also envisioned how this could be used to train AI for real-time road condition monitoring, which Gerasimidis calls exciting.

“This is a big initiative we are doing here and it has specific engineering outcomes,” he said.

“The purpose was to do this AI study and bring it up to (Greek) officials to say ‘look what we can do.’

“It is very difficult to use AI and come up with specific results that could be implemented, and I think this study is one of them.

“It is now up to the Greek officials to utilise these new tools to mitigate the huge problem of car crash fatalities. We are very eager to see our findings lead to improving this problem.”