Microbially induced concrete corrosion (MICC) in sewer infrastructure constitutes one of the most economically damaging deterioration mechanisms in urban water systems, costing billions of dollars annually in repair, rehabilitation, and replacement. While extensive research has characterized biogenic sulfuric acid attack, sulfate-reducing bacteria activity, and individual mitigation approaches, critical gaps remain at the convergence of nano-material science, real-time sensor integration, machine learning (ML), and life-cycle sustainability assessment. This study addresses four primary research gaps identified through systematic analysis of the existing literature: (1) the absence of a validated IoT-integrated ML framework for real-time corrosion rate prediction; (2) the unexplored synergistic potential of ternary nano-particle systems (TiO₂+SiO₂+ZnO) in cementitious coatings under actual MICC conditions; (3) the lack of comprehensive life-cycle carbon footprint analyses comparing mitigation strategies; and (4) the non-integration of mitigation approaches into a unified optimisation framework. Laboratory-scale experiments were conducted, exposing eight coating formulations to simulated biogenic sulfuric acid (pH 1.2–1.8) over 90 days, while a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model was trained on a 5-year IoT sensor dataset comprising H₂S concentration, pH, relative humidity, temperature, and biofilm thickness from 42 monitoring nodes across three gravity sewer networks. Results demonstrate that the hybrid nano-coating (TiO₂:SiO₂:ZnO = 1:1:1 wt%) reduced corrosion mass loss by 81.6% and improved flexural strength to 7.8 MPa compared to plain OPC controls. The CNN-LSTM model achieved a prediction accuracy of 95.6% and RMSE of 1.21 mm/year, significantly outperforming conventional ML approaches. Life-cycle analysis over a 50-year horizon confirmed that the integrated hybrid strategy reduces CO₂-equivalent emissions by 63.5% and costs by 65% versus unmitigated infrastructure. These findings provide a roadmap for sustainable, data-driven sewer corrosion management in smart city contexts.