Xerra News Cat

Something’s fishy—new funding to tackle illegal activities at sea using machine learning and data analytics

By February 25, 2021No Comments

A partnership between Aotearoa’s Xerra and Australia’s FrontierSI kicks off this week, with $100K AUD awarded to Xerra to help the Australian Geospatial-Intelligence Organisation’s Analytics Lab Program (AGO Labs) build new industry capability in the areas of machine learning and analytics.

Xerra is one of New Zealand’s commercially focused regional research institutes, and one of 3 successful applicants for funding in round 1 of the 2021 AGO Labs program. Xerra’s work focuses on remote sensing and data analytics, which in the past year has culminated in their flagship product—Starboard Maritime Intelligence, a platform that uses satellite data and machine learning technologies to monitor maritime activity.

Xerra and AGO analysts will work together to develop a model to detect anomalies in maritime vessel behaviour at sea, in particular identifying vessels whose behaviour (e.g. speed, location, track shape) deviates from the normal activity for vessels of its type. This work will enable AGO analysts to focus their attention on vessels that are anomalous, or behaving in out of the ordinary ways.

This work will be a continuation of Xerra’s research and algorithm development for the Starboard platform—using vessel transponder data (AIS) and satellite data to analyse vessel behaviour at sea, searching for evidence of illegal, unreported and unregulated (IUU) fishing, human rights abuses, and other related activities.

“We’re excited to be working in collaboration with AGO, FrontierSI and their analysts to better understand the questions they ask when looking at maritime vessel behaviour—what is ‘normal’ behaviour, and what signifies a deviation from that,” said Joseph Corbett, Data Scientist at Xerra and project lead for this work.

“AIS offers a significant potential for gaining maritime domain awareness, but large data volumes and data quality issues prohibit effective manual analysis at scale. Our objective is to develop an automated anomaly detection model based on recurrent neural networks—a machine learning technique commonly used to model sequences of data—to learn the behaviours of different vessel types, and ultimately enable us to detect when a behaviour deviates from ‘normal’.” Corbett continued.

The successful round 1 partners were announced earlier this month by AGO Labs program funding coordinators, FrontierSI. Chief Executive Officer Graeme Kernich remarked, ‘We would like to congratulate Xerra on their outstanding submission and are delighted to partner with them as part of AGO on the AGO Labs program.”

“The Program outcomes will improve the way in which AGO and the Department of Defence work with companies like Xerra, to test new innovations and applications and develop solutions, all with the objective of strengthening partnerships to build geospatial intelligence capability.’’ Kernich said.