This paper reviews the role of generative AI in predictive decision-making across engineering domains such as supply chains, manufacturing, and energy systems. It discusses models like GANs, VAEs, diffusion models, and LLMs, highlighting benefits such as synthetic data generation, reduced design cycles, and improved flexibility under uncertainty. Challenges related to data requirements, interpretability, and ethics are also addressed.
Keywords
Generative Artificial Intelligence, Predictive Decision-Making, Engineering Systems, Digital Twins
Conclusion
Generative AI complements traditional engineering methods by enabling scenario generation and uncertainty modeling. Its integration with digital twins, IoT sensing, and domain-specific models can redefine predictive decision-making. While not a replacement for human expertise, it amplifies engineers’ ability to respond to complexity and change.
References
Includes 11+ references from IEEE, Chem Rev, IJFMR, Discover AI, and Sustainable Energy Research covering generative AI, supply chain modeling, and industrial applications.
