In-Depth Analysis of the Effective Factors in Green Supply Chain Management in the Offshore Industry

Abstract

The proposed study is based on the hybrid framework, which is a convergence between machine learning algorithms and fuzzy decision-making techniques to determine and rank the most important factors regarding the Green Supply Chain Management (GSCM) within the offshore industry under the influence of climate change. The research follows a three-phase methodology: (1) systematic literature review and expert consultation to establish the dimensions of relevancy in GSCM (2) hybrid fuzzy Delphi machine learning to quantify uncertainty and elicit expert opinion (3) an Analytic Network Process to establish interdependency and global priorities. The framework was applied to Saudi Arabia’s Arabian Gulf offshore sector, where four primary GSCM dimensions and twelve operational indicators were validated with expert consensus levels between 0.82 and 0.93. Results show that climate change adaptation mechanisms represent the most influential dimension (global weight = 0.334), while Climate Risk Assessment Protocols rank as the top indicator (0.127). The hybrid model got an accuracy of 0.863 which was 34.4 percent higher than the traditional methods in predicting disruption and 44.3 percent in risk assessment accuracy. Three offshore validation indicated performance improvement of 11 to 25. These results have shown that the process of combining machine learning and fuzzy logic makes GSCM decision-making much more effective, providing a pragmatic and climate-adaptive architecture to make offshore operations more sustainable and resilient.

Article history: Received (August 19, 2025); Revised (November 20, 2025); Accepted (December 18, 2025); Published online (February 18, 2026)