Amazon deploys AI to achieve sustainability goals
Amazon is pursuing sustainability across its enterprise with help from artificial intelligence (AI).
The e-tail giant, which is investing billions of dollars in a wide variety of AI initiatives, is dedicating some of those efforts toward its Climate Pledge effort to become net zero carbon across its entire business by 2040.
In a corporate blog post, the company detailed a number of AI-based sustainability projects. Following are highlights:
Carbon footprint estimation
According to Amazon, it can take a person hundreds of hours to research and calculate the carbon footprint for a single product. To streamline that process, Amazon has developed Flamingo, an AI-based algorithm that leverages natural language processing to match text descriptions for Environmental Impact Factors (EIF), a commonly accepted measurement for calculating the carbon impact of an item, with specific products.
Amazon is already utilizing the Flamingo algorithm to calculate the environmental impacts of a wide variety of products sold on its site. In one pilot, the algorithm reduced the time scientists spent mapping 15,000 Amazon products from a month down to several hours. Flamingo is also available for other companies to use in order to help accelerate their sustainability goals.
Identifying defective produce
A growing number of Amazon Fresh grocery teams are using machine learning (ML)-based solutions to automate store shelf monitoring for fruits and vegetables. The technology analyzes crate images to detect visual imperfections on produce, such as cracks, cuts and pressure damage.
To ensure defective produce is recycled whenever possible, Amazon Fresh resells the usable portion to local contractors who further resell the produce at reduced prices for use cases like feeding to livestock, in an effort to ensure less food goes to waste.
Identifying damaged goods
Amazon is also using AI technology across a growing number of fulfillment centers to detect damaged goods, with the goal of decreasing the number of damaged items that get sent to and returned by customers.
The AI is three times more effective at identifying damaged goods than human beings, according to the e-tailer, and has been trained by analyzing millions of photos of undamaged and damaged items.
If a product can’t be shipped directly to a customer due to imperfections, the item is flagged to an Amazon associate who assesses the product and reroutes it to be resold at a reduced price, donated, or otherwise reused.