How Google AI can Improve the Recycling Value Chain

Share this article
Share this article
Prioritise Us on Google
Google's AI model CircularNet can help tackle material recovery in recycling. Credit: Getty
Google’s open AI and machine learning model CircularNet has been used to create a recycling commerce startup in India with 90% waste sorting accuracy

Half of global plastic production is for single-use and only 9% of plastic is recycled, according to the World Economic Forum.

It is predicted that, by 2050, there will be more plastic than fish in the oceans unless serious action is taken to stop it.

The disposal of single-use plastic also has an economic impact, as 95% of its value is lost after its initial use.

Thanks to Google, there is a solution that can help improve waste management and recover materials across the value chain.

Youtube Placeholder

Google’s recycling solution

Google has developed an open source AI and machine learning model called CircularNet to help support better material recovery.

It is designed to make waste identification more accessible, accurate and scalable by using an open source model based on globally sourced data.

After being trained on thousands of real-world photos, CircularNet can recognise materials in images of waste so that they can be accurately separated.

The model can recognise the type of material, the form they take such as bottles or cans and specific plastic types including HDPE and PET.

CircularNet provides real-time waste stream insights and is flexible so it can be used across many different waste streams and geographical locations.

It can be utilised in order to reduce contamination in incoming and outgoing waste flows and increase landfill diversion through more accurate sorting.

The technology works by capturing images at different points in material recovery facilities which creates a data-driven approach to recycling.

The model can be used and adapted by various stakeholders across the waste management ecosystem, which help drive circularity and sustainability in the sector.

Kate Brandt, Chief Sustainability Officer at Google, said on LinkedIn: ā€œDoubling the global recycling rate could save over 10 gigatons of carbon over the next 30 years.

Kate Brandt, Chief Sustainability Officer at Google

ā€œAt Google, we see a clear opportunity to apply AI to help meet this opportunity.

ā€œThis is the opportunity of AI in action: using technology to create efficiency, reduce waste and unlock economic growth.ā€

A new life for waste materials

CircularNet has been recognised as a solution to improve circularity in the value chain by the World Business Council for Sustainable Development (WBCSD).

The WBCSD’s Circular Transition Indicators (CTI) Enabling Solutions methodology is used to assess a product or company’s contribution to circularity.

CTI Enabling Solutions help companies accurately measure their business solutions so that they can make credible, consistent and comprehensive claims about their products.

The WBCSD has verified that CircularNet does not physically alter materials or products being sorted or introduce any substances that could inhibit recovery.

It is a solution that operates at the end-of-life stage of products, providing analytics that improve material recovery and recycling and can extend the life of the materials.

Nathan Gassman, Circular Economy Lead at Google, says: ā€œWBCSD’s CTI Enabling Solutions methodology helped our team formally analyse and validate CircularNet’s impact with ease.

ā€œThe methodology strikes the right balance of simplicity and depth and is designed to help companies assess and create solutions that drive meaningful impact.

ā€œAt Google, we aim to maximise the reuse of finite resources across our operations, products and supply chains - while enabling others to do the same.

ā€œThere is a nice alignment and we see significant value in this framework.ā€

How Google AI powers recycling in India

CircularNet has been utilised in India to create Recykal, the fastest-growing waste commerce marketplace startup in Asia.

India lacks a robust recycling infrastructure, meaning around 30 million metric tonnes of landfill waste is left in towers in Delhi.

Recykal is powered by Google AI and it has achieved more than 90% accurate detection of metals, bottles, PET, HDPE and LDPE plastics.

The service means that recyclers across India are receiving pure dry waste without contamination, which increases the value of the waste by around six times.

Recykal’s B2B marketplace allows plastic, paper, metal, e-waste and batteries to be sold across more than 30 Indian states and union territories.

Recykal says it diverts 50,000 metric tonnes of waste away from landfill every month.

Chetan Baregar, Associate Director of Marketing at Recykal, says: ā€œIf material isn’t going to be recycled, then it’s going to eventually end up as land, water or air pollution.

Chetan Baregar, Associate Director of Marketing at Recykal

“Using the CircularNet AI technology, we’re helping brands reach their sustainability goals, providing governments with actionable insights and sourcing businesses better and cheaper materials.

“The technology is helping to benefit India as a whole.”

Company portals

Executives