Abstract
Reliable multimodal monitoring in crystallization processes remains challenging due to heterogeneous PAT signal quality, sensor drift, asynchronous sampling and nonstationary noise. This work presents a machine-learning-assisted fusion framework that integrates multimodal PAT alignment, estimation and physics-guided regularisation to generate coherent concentration and particle-size trajectories. A mechanistically informed simulation platform is developed to produce synthetic Raman, FTIR, FBRM and image-based crystal size data with realistically simulated drift, heteroscedastic noise, dropouts and distortion patterns. Sensor reliability is inferred through a Random Forest model trained on variance-normalised discrepancies and quality metrics, which allows the dynamic adjustment of channel contributions. Across modalities, the Random Forest achieves MAE values of 0.03-0.20 for probability-type indicators and shows stable explanatory power for variance-inflation factors on particle-size channels (R2 = 0.81-0.93). Two representative PAT scenarios illustrate the performance of the proposed framework under different cross-sensor discrepancy structures, demonstrating improved robustness, reduced local variance and enhanced physical coherence compared with individual signals. Overall, the results highlight the potential of multimodal information fusion as a foundation for trustworthy online monitoring and modelling in crystallization.