This study aims to explore the application of artificial intelligence (AI) in the resolution of sustainability challenges, with a specific focus on environmental studies. Given the rapidly evolving nature of this field, there is an urgent need for more frequent and dynamic reviews to keep pace with the innovative applications of AI. Through a systematic analysis of 191 research articles, we classified AI techniques applied in the field of sustainability. Our review found that 65% of the studies applied supervised learning methods, 18% employed unsupervised learning, and 17% utilized reinforcement learning approaches. The review highlights that artificial neural networks (ANN), are the most commonly applied AI techniques in sustainability contexts, accounting for 23% of the reviewed methods. This comprehensive overview of AI techniques identifies key trends and proposes new research avenues to address the complex issue of achieving the Sustainable Development Goals (SDGs). Graphic

This review draws on a systematic literature review and bibliometric analysis to examine how Digital Twins (DTs), Extended Reality (XR), and Artificial Intelligence (AI) support the reconfiguration of Cyber–Physical Systems (CPSs) in modern manufacturing. The review aims to provide an updated overview of these technologies’ roles in CPS reconfiguration, summarize best practices, and suggest future research directions. In a two-phase process, we first analyzed related work to assess the current state of assisted manufacturing reconfiguration and identify gaps in existing reviews. Based on these insights, an adapted PRISMA methodology was applied to screen 165 articles from the Scopus and Web of Science databases, focusing on those published between 2019 and 2025 addressing DT, XR, and AI integration in Reconfigurable Manufacturing Systems (RMSs). After applying the exclusion criteria, 38 articles were selected for final analysis. The findings highlight the individual and combined impact of DTs, XR, and AI on reconfiguration processes. DTs notably reduce reconfiguration time and improve system availability, AI enhances decision-making, and XR improves human–machine interactions. Despite these advancements, a research gap exists regarding the combined application of these technologies, indicating potential areas for future exploration. The reviewed studies recognized limitations, especially due to diverse study designs and methodologies that may introduce risks of bias, yet the review offers insight into the current DT, XR, and AI landscape in RMS and suggests areas for future research.

Sustainability has become a critical global concern, focusing on key environmental goals such as achieving net-zero emissions by 2050, reducing waste, and increasing the use of recycled materials in products. These efforts often involve companies striving to minimize their carbon footprints and enhance resource efficiency. Artificial intelligence (AI) has demonstrated significant potential in tackling these sustainability challenges. This study aims to evaluate the various aspects that must be considered when deploying AI for sustainability solutions. Employing a SWOT analysis methodology, we assessed the strengths, weaknesses, opportunities, and threats of 70 research articles associated with AI in this context. The study offers two main contributions. Firstly, it presents a detailed SWOT analysis highlighting recent advancements in AI and its role in promoting sustainability. Key findings include the importance of data availability and quality as critical enablers for AI’s effectiveness in sustainable applications, and the necessity of AI explainability to mitigate risks, particularly for smaller companies facing financial constraints in adopting AI. Secondly, the study identifies future research areas, emphasizing the need for appropriate regulations and the evaluation of general-purpose models, such as the latest large language models, in sustainability initiatives. This research contributes to the growing body of knowledge on AI’s role in sustainability by providing insights and recommendations for researchers, practitioners, and policymakers, thus paving the way for further exploration at the intersection of AI and sustainable development.

This study presents a comprehensive evaluation of initial sampling techniques within the context of Bayesian Optimization (BO), a machine learning technique intended for the optimization of intricate and expensive functions. We assessed its efficacy in optimizing both theoretical benchmark functions and real-world applications. The findings reveal that, while BO is inherently robust and effective in a wide range of optimization problems, the integration of structured initial sampling methods, such as Latin Hypercube Sampling (LHS) and fractional factorial design (FFD) in the context of Design of Experiments (DoE), can significantly alter its performance. In addition, by systematically exploring different optimization strategies, the study highlights how LHS and FFD, followed by BO, can, for example, lead to substantial reductions in energy consumption—up to approximately 67.45% compared to average consumption. In conclusion, this study contributes to the growing body of knowledge on BO by demonstrating the value of early sampling techniques in enhancing BO effectiveness. This study offers a roadmap for future studies to build on in the pursuit of more efficient and effective optimization strategies in complex real-world scenarios.

The global push for sustainable production, driven by initiatives like the Paris Agreement and the European Green Deal, necessitates reducing CO₂ emissions in industrial processes. Additive manufacturing (AM), with its potential for material efficiency and decentralization, offers promising opportunities for lowering carbon footprints. Due to the significant importance of enhancing the performance of AM via the fine-tuning of printing parameters, this study investigates the dual objectives of understanding parameter influences and leveraging artificial intelligence (AI) to predict CO₂ emissions in fused deposition modeling (FDM) processes. A full-factorial experimental design with 81 test prints was conducted, varying four key parameters—layer height, infill density, perimeters, and nozzle temperature—at three levels (min, mid, and max). The results highlight infill density as the most influential factor, significantly impacting material usage, energy consumption, and overall CO₂ emissions. Five AI algorithms were employed for predictive modeling, with XGBoost demonstrating the highest accuracy in forecasting emissions. By systematically analyzing process interdependencies and providing quantitative insights, this study advances sustainable 3D printing practices. The findings offer practical implications for optimizing AM processes, benefiting both researchers and industrial stakeholders aiming to reduce CO₂ emissions without compromising product integrity.

This study introduces a comprehensive knowledge graph (KG)-based framework designed to support sustainable decision-making by integrating, enriching, and analyzing heterogeneous data sources. The proposed methodology leverages domain expertise, real-world data, and synthetic data generated through language models to address challenges in life cycle assessment (LCA), particularly data scarcity and inconsistency. By modeling the entire product lifecycle, including engineering, production, usage, and disposal phases, the framework facilitates early-stage design decision-making and provides actionable insights for sustainability improvements. The methodology is validated through a case study on 3D printing (3DP), demonstrating its ability to manage complex data, highlight relationships between engineering decisions and environmental impacts, and mitigate data scarcity in the early phases of product development in the context of LCAs. In conclusion, the results demonstrate the framework’s potential to drive sustainable innovation in manufacturing.