A decision-support framework for industrial green transformation: empirical analysis of the northeast industrial district in China

Extensive industrial development in the Northeast Industrial District (NID) has led to significant resource depletion and ecological degradation, impacting both the target of peak carbon dioxide emissions for 2030 and the broader strategy for industrial green transformation (IGT) in China. In this context, this study explores the decision-support framework integrating the prediction model, cloud model, and gray relational model. Empirical results indicate that the optimized VBO-GM (1, 1) model reflects a superior capacity compared to the other prediction models, with mean absolute percentage error values consistently below 10% across all training datasets. According to the predictions of the optimal VBO-GM (1, 1) model, the IGT efficiency levels of the three provinces are expected to remain relatively low from 2021 to 2030. It highlights the significant challenges facing high-quality IGT in the NID region, characterized by a relatively lower proportion of cleaner energy and substantial industrial pollution emissions. Despite increases in innovation investment and R&D personnel inputs, improvements in outputs may be less than optimal due to inefficient conversion processes. Moreover, policymakers need to carefully balance innovation investment between internal and external R&D expenditures. This allocation is critical in formulating effective policies aimed at promoting sustainable industrial development and mitigating environmental impact.