Algerian Journal of Renewable Energy and Sustainable Development
Volume 8, Numéro 1, Pages 27-36
2026-06-15
Authors : Abulgasem Bashir Nadia . A Ayad Hesham . Daeri Amer .
Rapid urbanization and limited digital infrastructure challenge waste management in cities like Tripoli, Libya. This study proposes a simulation-based AI framework integrating multi-modal vision transformers for waste classification, reinforcement learning for dynamic routing, and a knowledge graph for circular economy matching. Using a synthetic environment built from regional audits, OpenStreetMap, and socio-spatial data, the framework reduced collection distance by 28–32%, improved classification F1-score to 84.7%, and increased recycler matching by 2.6× over fixed-schedule baselines across 50 Monte Carlo runs (p < 0.001). The work provides a policy-ready blueprint for data-scarce cities aligned with UNSustainable Development Goals (SDGs) 11 and 12.
Smart waste management; Simulation; reinforcement learning; vision transformers; AI for sustainability.
Amraoui Soumia
.
Almi Hassiba
.
pages 669-686.
Merzouki Yasser
.
pages 77-89.
Gharbi Samia
.
pages 541-557.
Djeddi Sarah
.
pages 182-201.
Bennecer Afaf
.
Bouguelaa Mohammed
.
pages 94-110.