Data-driven sustainability assessment of advanced manufacturing processes

Unit manufacturing processes often involve conflicting objectives: achieving high throughput and productivity while minimizing environmental impacts, reducing costs, and ensuring product quality. In this context, computational methods are instrumental in deriving quantitative indicators from process data and supporting data-driven decision-making. Computational, including optimization-based, methods are commonly employed to quantify and compare the performance of alternative processes. However, most existing studies focus on specific use cases, resulting in fragmented insights. Therefore, this paper surveys state-of-the-art data- and model-driven methods used to quantify sustainability performance in unit manufacturing processes. Specifically, we review sustainability evaluation methods applied to three major categories of unit manufacturing processes: additive, subtractive, and formative. We highlight that life cycle assessment (LCA) is effective for quantitative environmental system assessment; however, compiling reliable life cycle inventories is time-consuming and often requires proprietary software tools. In contrast, bottom-up parametric modeling approaches, which describe system behavior based on individual process parameters, have proved effective in evaluating complex systems and enabling flexible what-if analyses. The paper further investigates the integration of these modeling methods with data-driven analytical approaches such as multi-criteria decision-making and artificial intelligence–based algorithms for extracting actionable information. Based on this review, we propose a holistic data-driven framework for resource-informed assessment of manufacturing sustainability.