WELLINGTON, March 25 (Xinhua) -- Scientists in New Zealand have developed an artificial intelligence (AI) tool that can predict wildfire risk up to 30 times faster than many current systems.

The system uses machine learning to analyze weather station data and detect patterns that often occur before fires ignite, offering faster warnings and significant cost savings for fire agencies, a statement from New Zealand's University of Canterbury (UC) said Wednesday.

Unlike many official warning systems that currently update once daily, the AI-based forecasting system refreshes every 30 minutes, providing near real-time insight into changing fire risk, according to the study published in the International Journal of Wildland Fire.

"We originally developed the model as a proof of concept in one region. However, in this new study, we tested it across multiple regions to see whether the approach works under different fire weather conditions," said Alberto Ardid, a UC lecturer in civil and environmental engineering who led the study.

The machine-learning system improved forecasting performance by 10 to 30 percent, using more than 60 years of historical weather and fire data, researchers said.

Economic modelling suggested the AI system could double the economic savings when compared with existing forecasting tools by reducing missed fires and unnecessary false alarms.

Researchers believe faster, data-driven fire forecasting could help agencies plan responses earlier and more effectively as climate change intensifies wildfire risks. ■