Companies' indirect emissions still a blind spot

Embargoed until: Publicly released: 2023-11-16 06:00

Australia; New Zealand; QLD

Photo by Rhys Moult on Unsplash

To get a true picture of a company's environmental impact, we need to take into account emissions from their entire supply chain - including producing the raw materials, distributing the products, and how they're disposed of. New research from New Zealand and Australian scientists finds the data on these indirect "Scope 3" emissions vary significantly across major data collectors. AI has been suggested as a way to predict missing data from companies, but the study also finds that current models struggle with accuracy.

Journal/
conference: PLOS Climate

Research:Paper

Organisation/s: University of Otago, Griffith University, The University of New South Wales

Funder: This paper is a by-product of a commercial agreement between EMMI (Emmi Solutions Pty Ltd) and the University of Otago, and more recently the Griffith University, to apply machine learning models to predict carbon footprints that builds on Quyen Nguyen and Ivan Diaz-Rainey’s earlier work (Nguyen et al. 2021, Energy Economics, 95, 105129). As such, EMMI provided funding for the work that underpinned the research and which EMMI is using, or will use, for commercial purposes in their products and services. The paper is not a deliverable of this agreement, rather, as mentioned before, it is a byproduct of it. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of all authors are articulated in the ’author contributions’ section.

Media Contact/s

Contact details are only visible to registered journalists.