Carbon-Negative Manufacturing via AI-Optimized Direct Air Capture and Circular Material Design

Abstract

The urgency of mitigating climate change has driven the need for transformative industrial strategies that move beyond carbon neutrality toward carbon-negative manufacturing. This study presents an integrated framework combining artificial intelligence–optimized direct air capture (DAC) systems with circular material design to enable sustainable industrial production. The proposed approach leverages machine learning algorithms to optimize carbon capture efficiency, energy consumption, and material lifecycle processes. A hybrid modeling architecture integrates thermodynamic simulations, process optimization and lifecycle assessment to evaluate system performance. The framework incorporates closed- loop material flows, waste valorization, and carbon utilization pathways, ensuring minimal environmental impact. Simulation results demonstrate that AI-optimized DAC systems can achieve up to 40% improvement in capture efficiency while reducing energy consumption significantly. Furthermore, circular material strategies enable net-negative emissions by reintegrating captured carbon into production cycles. The study also evaluates economic feasibility and policy implications, highlighting pathways for large-scale implementation. This research contributes to the advancement of sustainable manufacturing and provides a scalable model for achieving carbon-negative industrial systems in alignment with global climate goals.