Strategic Environmental Sustainability Decisions Under a Digital Twin–Based Optimization Framework

Increasing environmental requirements and the complexity of strategic decision‐making have challenged organizations to balance economic performance and environmental sustainability. This study presents an integrated framework based on digital twin and multi‐objective optimization, in which digital twin is directly integrated with the optimization model as a scenario‐based layer for generating and dynamically updating decision‐making conditions. The research data were extracted from real information of a manufacturing organization and, after refining and calibration, were supplemented with scenarios generated in the digital twin environment to enable the analysis of strategic decisions under different conditions. The results showed that with the increase in the intensity of environmental policies, the optimal level of green investment increased from 0.32 to 0.61, and at the same time, the environmental impact decreased from 61.7 to 35.2. Also, scenario‐based analyses, sensitivity analysis, temporal stability assessment, and statistical validation showed that the proposed framework is capable of extracting balanced, stable, and reliable solutions for strategic decision‐making. The main innovation of the research is in transforming the digital twin from a purely operational and simulation tool to an active mechanism for supporting scenario‐based strategic decision‐making; an approach that can strengthen the link between advanced quantitative analytics and sustainable decision‐making in industrial environments.