Enforcing coherent trends in a continuous lumping models for hydrocracking with Monte Carlo Markov Chains

• Extension of Bayesian Transfer Learning algorithm with Monte Carlo Markov Chains • Continuous Lumping model for hydrocracking reaction • Using lab and pilot plant data with different structure and information content • Use lab scale data to enforce catalyst rankings with constraints • Improve model robustness by retaining information from source models • Transfer Learning leads to coherent set of models for three catalysts • Flexible algorithm can be used with variety of heterogeneous datasets We present an extended Bayesian Transfer Learning framework that integrates heterogeneous data sources for developing robust kinetic models in industrial catalyst development. The methodology incorporates hard and soft constraints into Monte Carlo Markov Chain (MCMC) sampling, enabling multi-objective optimization with arbitrary model structures. Applied to continuous lumping models of zeolite hydrocracking catalysts, our approach strategically combines absolute measurements from pilot plant data with relative performance rankings from high-throughput screening; information that cannot be directly included due to scale-up limitations. By transferring information through prior distributions and ranking constraints, we obtain a set of coherent models that respect both absolute performance levels and relative activity and selectivity trends. Validation on unseen stacking tests confirms predictions. The impact of ranking constraints depends on design space overlap: they prove essential when catalyst generations explore different operating regimes but less critical when conditions overlap substantially. This enables efficient experimental design where costly pilot campaigns explore new conditions while inexpensive screening maintains portfolio consistency. The Bayesian framework provides rigorous uncertainty quantification. This methodology addresses a fundamental industrial challenge: optimally leveraging diverse information from experimental programs spanning different scales, costs, and information content.