• Energy Research

Hydrogen is gaining traction as a key energy carrier due to its clean combustion, high energy content, and versatility. As the world shifts towards sustainable energy, hydrogen demand is rapidly increasing. This paper introduces a novel hybrid time series modeling approach, designed and developed to accurately predict hydrogen demand by mixing linear and nonlinear models and accounting for the impact of non-recurring events and dynamic energy market changes over time. The model incorporates key economic variables like hydrogen price, oil price, natural gas price, and gross domestic product (GDP) per capita. To address these challenges, we propose a four-part framework comprising the Hodrick–Prescott (HP) filter, the autoregressive fractionally integrated moving average (ARFIMA) model, the enhanced empirical wavelet transform (EEWT), and high-order fuzzy cognitive maps (HFCM). The HP filter extracts recurring structural patterns around specific data points and resolves challenges in hybridizing linear and nonlinear models. The ARFIMA model, equipped with statistical memory, captures linear trends in the data. Meanwhile, the EEWT handles non-stationary time series by adaptively decomposing data. HFCM integrates the outputs from these components, with ridge regression fine-tuning the HFCM to handle complex time series dynamics. Validation using stochastic, non-Gaussian synthetic data demonstrates that this model significantly enhances prediction performance. The methodology offers notable improvements in prediction accuracy and stability compared to existing models, with implications for optimizing hydrogen production and storage systems. The proposed approach is also a valuable tool for policy formulation in renewable energy and smart energy transitions, offering a robust solution for forecasting hydrogen demand.

Sustainable development emergent subfields have been rapidly evolving, and their popularity increased in recent years. Sustainable development is a broad concept having numerous sub-concepts including, but not limited to, circular economy, sustainability, renewable energy, green supply chain, reverse logistics, and waste management. This polymorphism makes decision-making in this field to be an abstruse task. In this perplexing circumstance, the presence of VUCA conditions makes decision-making even more challenging. By taking advantage of artificial intelligence tools and approaches, this paper aims to study with a concentration on sustainable development-related decision-making under VUCA phenomena elements using bibliometric and network analyses which can propose numerous novel insights into the most recent research trends in this area by analyzing the most influential and cited research articles, keywords, author collaboration network, institutions, and countries that finally provides results not previously fully comprehended or assessed by other studies on this topic. In this study, an extensive systematic literature review and bibliometric analysis are conducted using 534 research articles out of more than 3600. From the content analysis part, four clusters have been found. The decision parameters, presumptions, and research goal(s) for each model are pointed out too. The findings contribute to both conceptual and practical managerial aspects and provide a powerful roadmap for future research directions in this field, such as how real-life multidimensionality can be considered in sustainable development-related decision-making, or what are the effects of the VUCA in sustainable development considering the circular economy and waste management intersection.