Artificial intelligence-enhanced policy evaluation of short- and long-term hydrogen strategies in emerging and advanced economies

A fundamental challenge in global energy transition strategies lies in determining which hydrogen types should be prioritized in the short and long term. While existing literature predominantly addresses technical and engineering aspects, there is a significant gap in comparative strategic evaluations across countries and development levels. This study aims to fill this gap by proposing an artificial intelligence-enhanced multi-criteria decision-making framework to assess hydrogen energy strategies in advanced (G7) and emerging (E7) economies. The proposed model integrates Koch Snowflake Fuzzy Sets (KSFS) with an artificial intelligence-driven expert weighting system to reduce subjectivity and improve decision robustness. Two advanced decision-making techniques—Compromise Ranking with Improved Accuracy Score (CIMAS) and Measurement of Alternatives and Ranking according to Compromise Solution (MARCOS)—are employed to analyze national preferences under uncertainty. The findings reveal that E7 countries prioritize cost efficiency in the short term and shift focus to technical infrastructure in the long term, while G7 countries consistently emphasize environmental sustainability. Regarding hydrogen types, E7 economies prefer blue hydrogen in the short term and green hydrogen in the long term, whereas G7 nations favor green hydrogen throughout. This study contributes to the interface of artificial intelligence and energy policy by providing a transparent, scalable, and policy-relevant framework for evaluating hydrogen strategies. The integration of artificial intelligence into expert judgment modeling enhances both analytical rigor and practical applicability in decarbonization planning.