The Sustainability Data Science Life Cycle for automating multi-purpose LCA workflows for the analysis of large product portfolios

Abstract

Life Cycle Assessment (LCA) is a powerful and sophisticated tool to gain deep understanding of the environmental hotspots and optimization potentials of products. Yet, its cost-intensive manual data engineering and analysis workflows restrain its wider application in eco-design, green procurement, supply chain management, sustainable investment or other relevant business processes. Especially for large product portfolios and increasing reporting requirements, traditional LCA workflows and tools often fail to provide the necessary scalability. The Sustainability Data Science Life Cycle (S-DSLC) is a concept for workflow automation for multi-purpose LCA of large product portfolios. The concept integrates the frameworks of LCA, the cross-industry standard process for data mining (CRISP-DM), and the Data Science Life Cycle (DSLC). Key aspects of the concept are deep business-, stakeholder and user-understanding, deployment of LCA results in interactive browser tools (i.e. LCA-dashboards and Guided Analytics) tailored to the needs of individual roles and business processes, as well as the automation of data preparation, model generation and Life Cycle Impact Assessment based on modern data analytic tools. The demonstration of the concept shows substantial scalability improvements for dealing with large product portfolios and broad application of LCA results in various business processes.

Bringing Light into the Dark—Overview of Environmental Impacts of Carbon Fiber Production and Potential Levers for Reduction

“…In this case, modelling by hand in standard LCA software might no longer be the best choice and (semi-)automated approaches for LCIA calculations, as illustrated for extensive product portfolios before [ 68 , 69 ], should be considered. On the one hand, these approaches require adaptation to the specific challenges in carbon fiber production.…”

Analysis and Visualisation of Large Scale Life Cycle Assessment Results: A Case Study on an Adaptive, Multilayer Membrane Façade

“…Both approaches can enhance practicability when dealing with complex products and high variance because they significantly reduce the effort required for data collection and structuring [18]. Advancements in common computer hard-and software, as well as the availability of data resulting from increased digitalisation, enable LCA practitioners to extract and use this data to model, calculate, and assess millions of product configurations in an automated or partly automated fashion [19][20][21][22]. However, commonly used methods for the visualisation of LCA results might not be suitable to analyse and interpret vast amounts of data points, potentially increasing the risk of misinterpretation [23,24].…”

“…The Sustainability Data Science Life Cycle (S-DSLC), proposed by Wehner et al [21], is a concept for automating LCA workflows and providing LCA-derived insights for largescale product portfolios. It consists of seven phases, encompassing the understanding and preparation, processing, and analysis of LCA data, as well as the application and monitoring of LCA-derived insights to drive sustainability in businesses.…”

“…Temporal distribution. [21], with the goal and scope of the CLASS workflow [22] and the visualisation from this manuscript.…”

How to Simplify Life Cycle Assessment for Industrial Applications—A Comprehensive Review

“…Ferrari et al [65] described the architecture and application of a dynamic LCA system that integrates the ERP system with a customized LCA tool. Wehner et al [66] proposed a workflow automation concept, the Sustainability Data Science Life Cycle (S-DSLC) concept. The LCA methodology is combined with the standard process for data mining (CRISP-DM) and the Data Science Life Cycle (DSLC).…”