The tool uses applied mathematics and big data analytics to analyse intricate ground motion patterns and track location and time of landslides to forecast them up to two weeks in advance, media reported.
The new software focuses on turning algorithms and big data into risk assessment and management actions.
There are always “warning signs” in the lead-up to a collapse or slope “failure” but the tricky part is identifying what they are, University of Melbourne researcher Professor Antoinette Tordesillas said in a statement.
The early clues include motion patterns that change over time and become synchronised. They are subtle. Identifying them requires fundamental knowledge of failure at the microstructure level the movement of individual grains of earth, said Tordesillas.
The scientists are trying to identify the properties that characterise these failures in the small-scale, so as to shed light on how failure evolves in time.
“Our model decodes this data on movement and turns it into a network, allowing us to extract the hidden patterns on motion and how they are changing in space and time.
This technology was just unimaginable in a mathematical sense 30 years ago, he said.
