AI-Assisted Digital Monitoring Systems for Sustainable Archipelagic Sea Transportation Management.

Abstract

Indonesia's archipelagic sea transportation network constitutes one of the world's most geographically complex logistics systems, connecting over 17,000 islands while confronting escalating environmental regulatory demands under the IMO's Carbon Intensity Indicator (CII) and Energy Efficiency Existing Ship Index (EEXI) frameworks. Despite the urgency of decarbonization compliance, Indonesian domestic shipping fleets lack integrated AI-assisted monitoring systems capable of delivering real-time sustainability performance data at the operational level. This study investigates the design principles, implementation feasibility, and performance outcomes of AI-assisted digital monitoring systems applied to sustainable archipelagic sea transportation management. Employing a mixed-methods design involving 90 participants — comprising fleet operators, port authority officials, maritime technology experts, and government transportation regulators — alongside document analysis of applicable IMO regulatory frameworks and system performance data from pilot monitoring implementations, data were analyzed through thematic analysis, cross-group comparison, and narrative synthesis. Findings reveal critical infrastructure gaps in current domestic monitoring capacity, significant stakeholder readiness for AI-assisted system integration, and measurable sustainability performance improvements in pilot deployments. The study proposes an Archipelagic Sustainable Monitoring Architecture (ASMA) framework as a replicable model for AI-assisted sea transportation sustainability governance, contributing empirically grounded design principles to both maritime transportation management scholarship and Indonesia's national decarbonization policy agenda.