LEARNING-ENABLED RESILIENCE ENGINEERING IN SUSTAINABLE SUPPLY NETWORKS

DOI: https://doie.org/10.65985/APER.2025248444

Authors:

Goldi Makhija

Keywords:

Artificial Intelligence, Machine Learning, Sup-ply Chain Management, Sustainability, Optimization, Resilience Engineering

Abstract:

—This paper conducts a structured synthesis of artificial intelligence and machine learning techniques that fortify supply network resilience while advancing sustainability objectives. Drawing on secondary evidence across peer-reviewed and practitioner sources, the analysis maps capability path ways—neural and sequence models for demand volatility, data-driven routing and inventory policies, natural-language analytics for visibility, and risk-aware optimization—to resilience outcomes such as disruption absorption, recovery speed, and continuity under uncertainty. The review identifies implementation constraints (data quality, model interpretability, ethical safeguards, and organizational readiness) and governance enablers (data stewardship, transparent algorithm selection, bias controls) that condition dependable performance at scale. The resulting framework links AI/ML application classes to resilience levers in planning and execution, offering staged adoption guidance that aligns sustainability priorities with robust, adaptive operations in dynamic supply ecosystems.

PDF