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

TL;DR

This paper introduces a physics-informed transfer learning framework with a mixture of experts for multi-site emission control in waste incineration, enabling scalable and transferable pollutant emission predictions across diverse facilities.

Contribution

It develops a novel transfer learning approach that incorporates physical constraints and regime-specific experts for accurate emission modeling across multiple plants.

Findings

Model achieved high pollutant prediction accuracy with R^2 up to 0.904.

Transferability of the model maintained high R^2 values across different plants.

Structured re-weighting of operating regimes enables adaptation without full re-learning.

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.