Consumer products contribute to more than 75% 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 (EIFs) 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. A key challenge in automation is that EIF databases are incomplete. Flamingo uses industry sector classification as an intermediate layer to identify when there are no good matches in the database. On a dataset of 664 products, our method achieves an EIF matching precision of 75%.

Sustainable transition to low carbon and zero waste economy requires a macroscopic evaluation of opportunities and impact of adopting emerging technologies in a region. However, a full assessment of current physical flow and waste is a tedious task, thus leading to a lack of comprehensive assessment before scale up and adoption of emerging technologies. Utilizing the mechanistic models developed for engineering and biological systems with the macroeconomic framework of Input–Output models, we propose a novel integrated approach to fully map the physical economy, that automates the process of mapping industrial flows and wastes in a region. The approach is demonstrated by mapping the agro-based physical economy of the state of Illinois, USA by using mechanistic models for 10 agro-based sectors, which have a high impact on waste generation. Each model mechanistically simulates the material transformation processes in the economic sector and provides the necessary material flow information for physical economy mapping. The model for physical economy developed in the form of a Physical Input–Output Table (PIOT) captures the interindustry physical interactions in the region and waste flows, thus providing insight into the opportunities to implement circular economy strategies i.e., adoption of recycling technologies on a large scale. In Illinois, adoption of technologies for industrial waste-water and hog manure recycling will have the highest impact by reducing >62% of hog industry waste outputs, >99% of soybean hull waste, and >96% of dry corn milling (corn ethanol production) waste reduction. A small % reduction in nitrogen fertilizer manufacturing waste was also observed. The physical economy model revealed that the urea sector had the highest material use of 5.52 × 10⁸ tons and green bean farming with the lowest material use of 1.30 × 10⁵ tons for the year modeled (2018). The mechanistic modeling also allowed elemental flows across the physical economy to be captured, with the urea sector using 8.25 × 10⁷ tons of elemental carbon per operation-year (highest) and green bean farming using 3.90 × 10⁴ tons of elemental carbon per operation-year (least). The approach proposed here establishes a connection between engineering and physical economy modeling community for standardizing the mapping of physical economy that can provide insights for successfully transitioning to a low carbon and zero waste circular economy.

Products contribute to carbon emissions in each phase of their life cycle, from manufacturing to disposal. Estimating the embodied carbon in products is a key step towards understanding their impact, and undertaking mitigation actions. Precise carbon attribution is challenging at scale, requiring both domain expertise and granular supply chain data. As a first-order approximation, standard reports use Economic Input-Output based Life Cycle Assessment (EIO-LCA) which estimates carbon emissions per dollar at an industry sector level using transactions between different parts of the economy. EIO-LCA models map products to an industry sector, and uses the corresponding carbon per dollar estimates to calculate the embodied carbon footprint of a product. An LCA expert needs to map each product to one of upwards of 1000 potential industry sectors. To reduce the annotation burden, the standard practice is to group products by categories, and map categories to their corresponding industry sector. We present CaML, an algorithm to automate EIO-LCA using semantic text similarity matching by leveraging the text descriptions of the product and the industry sector. CaML uses a pre-trained sentence transformer model to rank the top-5 matches, and asks a human to check if any of them are a good match. We annotated 40K products with non-experts. Our results reveal that pre-defined product categories are heterogeneous with respect to EIO-LCA industry sectors, and lead to a large mean absolute percentage error (MAPE) of 51% in kgCO2e/$. CaML outperforms the previous manually intensive method, yielding a MAPE of 22% with no domain labels (zero-shot). We compared annotations of a small sample of 210 products with LCA experts, and find that CaML accuracy is comparable to that of annotations by non-experts.

Life Cycle Analysis (LCA) has long been utilized for decision making about the sustainability of products. LCA provides information about the total emissions generated for a given functional unit of a product, which is utilized by industries or consumers for comparing two products with regards to environmental performance. However, many existing LCAs utilize data that is representative of an average system with regards to life cycle stage, thus providing an aggregate picture. It has been shown that regional variation may lead to large variation in the environmental impacts of a product, specifically dealing with energy consumption, related emissions and resource consumptions. Hence, improving the reliability of LCA results for decision making with regards to environmental performance needs regional models to be incorporated for building a life cycle inventory that is representative of the origin of products from a certain region. In this work, we present the integration of regionalized data from process systems models and other sources to build regional LCA models and quantify the spatial variations per unit of biodiesel produced in the state of Indiana for environmental impact. In order to include regional variation, we have incorporated information about plant capacity for producing biodiesel from North and Central Indiana. The LCA model built is a cradle-to-gate. Once the region-specific models are built, the data were utilized in SimaPro to integrate with upstream processes to perform a life cycle impact assessment (LCIA). We report the results per liter of biodiesel from northern and central Indiana facilities in this work. The impact categories studied were global warming potential (kg CO₂ eq) and freshwater eutrophication (kg P eq). While there were a lot of variations at individual county level, both regions had a similar global warming potential impact and the northern region had relatively lower eutrophication impacts.