AI Case Study

University of Bristol Researchers detect possibility of volcanic eruption using neural networks

Researchers from the University of Bristol have developed a neural network system for flagging potential volcanic eruptions. The machine learning method analyses satellite images, compensating for distortions caused by water which can often impede analysis. Initial results had a 39% true positive identification.

Industry

Public And Social Sector

Public Services

Project Overview

The researchers "created a neural network that has churned through more than 30,000 Sentinel-1 images of more than 900 volcanoes and flagged about 100 images for closer examination. By getting an algorithm to do the initial work of sorting through the data, researchers save time that they can better spend following up on volcanoes of interest".

Reported Results

The results showed that 39% were true positives - correct detections of ground distortions. "The team is also training its neural network on synthetic data generated from simulated eruptions. That work roughly doubled the precision of the algorithm."

Technology

Function

Operations

Network Operations

Background

"Although about 800 million people live within 100 kilometres of a volcano, very few of these potential natural hazards are monitored consistently. But emerging methods are now enabling researchers to keep a constant eye on volcanoes".

Benefits

Data

The researchers use "radar observations from two satellites that make up the European Sentinel-1 mission. Depending on their location as they orbit Earth, the craft collect data on the world’s volcanoes every 6, 12 or 24 days. As they repeatedly pass over the same spot, the satellites measure the distance between themselves and the ground."