Advancing multi-site emission control: A physics-informed transfer learning framework with mixture of experts for carbon-pollutant synergy

2026-04-29

AI Summary

This study addresses the challenges of simultaneously controlling carbon emissions and multiple pollutants from municipal solid waste incineration plants under heterogeneous operating conditions, as well as the poor cross-plant generalizability of existing data-driven models. To overcome these limitations, the authors propose a transferable system-level modeling framework that integrates physical constraints, operational heterogeneity, and carbon–pollutant coupling mechanisms. A novel physics-informed transfer learning approach based on a Mixture-of-Experts (MoE) architecture is introduced, incorporating conservation-law regularization and expert routing to enable cross-plant knowledge transfer without full model retraining. An interpretable digital twin system is developed for condition-aware operational guidance. Unified risk assessment and emission prediction are achieved via a Carbon–Pollutant Synergy Index (CPSI). Validated across 13 incineration plants, the framework achieves source-domain R² values of 0.668–0.904 for pollutants and 0.666–0.970 for CPSI; after transfer to 12 target plants, performance remains robust (pollutants R²: 0.661–0.842; CPSI: 0.610–0.841).

Abstract

Municipal solid waste incineration is increasingly central to urban waste management, yet its sustainability benefit depends on controlling carbon emissions and multiple air pollutants under highly heterogeneous operating conditions. Current data-driven models are often accurate within individual plants but are difficult to transfer across facilities, limiting their value for scalable emission-control strategies. Here we show that multi-site emission behaviour can be represented through transferable system-level structures when physical constraints, operating-regime heterogeneity and carbon--pollutant coupling are jointly considered. We develop a physics-informed transfer learning framework built on a carbon--pollutant mixture-of-experts model, which combines regime-dependent expert routing with conservation-based regularization and a carbon--pollutant synergistic index for integrated risk evaluation. Across 13 municipal solid waste incineration plants, the model captured both pollutant-specific emissions and system-level risk, achieving source-domain average pollutant $R^2$ values of 0.668--0.904 and CPSI $R^2$ values of 0.666--0.970. After transfer from a reference facility to 12 target plants, average pollutant $R^2$ remained between 0.661 and 0.842, while CPSI retained comparable transferability ($R^2$ = 0.610--0.841). Expert-utilization patterns further indicate that adaptation occurs through structured re-weighting of operating regimes rather than complete model re-learning. By extending the learned representation into an interpretable digital twin, this framework provides a route from emission prediction to regime-aware operational navigation, supporting scalable carbon--pollutant synergistic control across heterogeneous waste-to-energy systems.

Problem

• multi-site emission control
• transfer learning
• carbon-pollutant synergy
• municipal solid waste incineration
• operating-regime heterogeneity

Innovation

• physics-informed transfer learning
• mixture of experts
• carbon-pollutant synergy
• operating-regime heterogeneity
• interpretable digital twin