CSIRO and Microsoft to Use AI to Tackle Human-Made Environmental Problems



Plastic pollution in Australian rivers.

Image: CSIRO

It is estimated that as much as 12 million tonnes of plastic are found in rivers and oceans every year, posing a huge threat to wildlife and the environment.

This is one of the main challenges that the Commonwealth Scientific and Industrial Research Organization (CSIRO) seeks to address, using technologies such as artificial intelligence (AI) and machine learning (ML) to interpret data collected during surveys of beaches and oceans, as well as videos of rivers. and storm drains to identify and track garbage flows in waterways.

By partnering with Microsoft, the Australian science agency will examine how to tackle plastic waste, as well as illegal fishing, and how it can help boost agriculture.

By collecting data on the spread and concentration of plastic, CSIRO uses AI and ML to analyze where plastic might end up and also what actions can be taken on earth to reduce the likelihood of plastic entering the pathways. navigable waters and oceans.

The “reverse vending machines”, where the public can recycle bottles and cans in exchange for a fee, is also on the exploration list.

See also: Plastic Bank treats plastic like currency to fight waste and poverty

CSIRO hopes to combat illegal fishing by analyzing information gathered from high-resolution cameras and underwater microphones to help manage fisheries in Australia’s marine reserves, such as the Great Barrier Reef.


Explosives fishing, also known as ‘blasting fishing’, in Indonesia.

Image: CSIRO

CSIRO is concerned that 80% of the world’s fisheries are either at full capacity or overexploited, with illegal fishing being a major problem. According to the organization, illegal fishing costs fishing up to $ 23 billion a year.

To this end, the partnership will also see work on detecting explosives fishing in Indonesia through the use of underwater microphones to detect illegal activity.

This program currently uses AI to detect sounds that indicate illegal activity, and the team aims to pair it with automated cameras in the future, to detect prohibited activity and identify perpetrators.

With the aim of boosting agriculture, CSIRO will provide farmers with “personalized digital information” from a range of data sources, including sensors and satellites. He also hopes to provide in-depth domain knowledge integrated with analysis and modeling to provide insight into tactical and strategic decision-making, which he says includes soil condition, crop growth and management. agricultural.


Farmers in a sugarcane field in Queensland, seen with LiDAR detection

Image: CSIRO

This work will begin at CSIRO’s new Agricultural Research Center in Boorowa, NSW, a specially constructed 290 hectare facility that aims to develop the ‘Australian farms of the future’ by testing emerging technologies in plant science, agronomy and farming systems at assistance from CSIRO. and Microsoft technologies.

See also: The Internet of Wild Things: technology and the fight against biodiversity loss and climate change (TechRepublic cover story) | Download the free PDF version (TechRepublic)

CSIRO said the partnership will also contribute to CSIRO’s managed data ecosystem and digital academy projects which have been described as transforming CSIRO’s digital landscape with new technologies, data capabilities and skills, while also bringing the latest digital technology from Microsoft to CSIRO’s broader research.

“This partnership transforms science and technology into real-life solutions for real people, from the Great Barrier Reef to suburban waterways, farms and environments across the country,” said CSIRO CEO, Dr. Larry Marshall.

“Everything CSIRO does is done through partnerships across Australia and around the world. “

According to Marshall, partnerships outside the organization have proven to be beneficial. He highlighted the work done by CSIRO with Bininj co-researchers, Kakadu National Park rangers, Microsoft, Parks Australia, North Australian National Environmental Science Program, University of Western Australia, Charles Darwin University and Kakadu National Park which have “woven” AI together. software with traditional knowledge to solve complex environmental management problems and care for important species and habitats.

“The combination of indigenous knowledge, AI, data visualization and scientific research has enabled indigenous researchers and rangers to label and interpret drone images, collected through Kakadu, and then to using them to help protect the environment, ”he said.

“The results and analyzes are then made available to the forest rangers via a dashboard designed in partnership with the traditional owners according to their cultural values ​​and the season. Rangers access it on a mobile device to support their decision-making on the ground in partnership with Traditional Owners. This resulted in a return of the magpie geese to an area that had been affected by an invasive grass species that has now been brought under control. “



Leave A Reply

Your email address will not be published.