Abstract: Household products contribute to more than 60% of global greenhouse gas (GHG) emissions, primarily through indirect contributions from the supply chain. Measurement of GHG emissions associated with products is a crucial step toward quantifying the impact of GHG emission abatement actions. Life cycle assessment (LCA), the scientific discipline for measuring GHG emissions, estimates the environmental impact associated with each stage of a product from raw material extraction to its disposal. Scaling LCA to millions of products is challenging as it requires extensive manual analysis by domain experts. To avoid repetitive analysis, environmental impact factors (EIF) of common materials and products are published for use by LCA experts. However, finding appropriate EIFs for even a single product under study can require hundreds of hours of manual work, especially for complex products. We present Flamingo, an algorithm that leverages natural language machine learning (ML) models to automatically identify an appropriate EIF given a text description.

Bio: Bharathan Balaji is a Senior Applied Scientist at Amazon Sustainability. He works on developing methods and systems that leverage machine learning (ML) to address climate change. He has published over 60 research papers in the areas of machine learning (ML), internet of things (IoT), and sustainability. He has a PhD in Computer Science and Engineering from UC San Diego, where he developed software infrastructure for reducing building energy use. He has contributed to the launch of Amazon products such as SageMaker RL and DeepRacer.

Website: https://www.linkedin.com/in/bharathanbalaji/