From Data to Decision: A Statistically Robust LCA Framework for Prioritising Sustainability Levers in Speciality Agriculture

Traditional Life Cycle Assessment (LCA) often provides single-point estimates that lack the statistical rigour required for high-stakes investment decisions in the agri-food sector. To bridge the gap between data uncertainty and actionable management, this study proposes a robust decision-support framework integrating Monte Carlo uncertainty analysis with inferential statistics (ANOVA and Tukey HSD). We applied this methodology to the industrial production of Dictyophora rubrovolvata, a climate-sensitive crop representing the “energy–food nexus.” The study aimed to distinguish genuine environmental performance differences from background data variability. The probabilistic modelling revealed that electricity consumption is the paramount ecological hotspot. Furthermore, the statistical tests confirmed that differences in regional grid composition generate significant variances in impact categories (p < 0.001), validating that the environmental benefits of low-carbon grids are systematic and robust. By transforming complex uncertainty data into clear statistical hierarchies, this framework enables producers and policymakers to identify and prioritise high-impact sustainability levers with confidence, providing a generalisable blueprint for the environmental management of energy-intensive agricultural systems.