TechPrufer
Get started
Meta
Meta logoMeta · Feature trail

AI for Scope 3 Emission Estimates

1 post · Oct 2025

What this trail covers

Meta is developing and open-sourcing a methodology that leverages AI to improve the estimation of Scope 3 emissions for IT hardware. This involves identifying similar components using NLP, extracting data from heterogeneous sources using LLMs, and applying generative AI to create a standardized taxonomy for IT hardware emissions. The goal is to drive industry-wide adoption of sustainable manufacturing practices by providing accurate and granular carbon footprint data.

All Meta trails
  1. How Meta Is Leveraging AI To Improve the Quality of Scope 3 Emission Estimates for IT HardwareThis post details Meta's methodology for improving Scope 3 emission estimates for IT hardware using AI. It describes the use of NLP (TF-IDF, Cosine similarity) to identify similar components and apply existing Product Carbon Footprints (PCFs). It also explains how Large Language Models (LLMs), specifically Llama 3.1, are used to extract data from heterogeneous sources for parameterized models and to apply generative AI as a categorization algorithm for creating a new, standard taxonomy of IT hardware emissions. The post highlights the benefits of LLMs in handling varied phrasing, units, and synonyms, and discusses the application of these techniques to memory and cable components, as well as the creation of a component-level breakdown of IT hardware emissions.