Sensitivity Analysis on Policy-Augmented Graphical Hybrid Models with Shapley Value Estimation

TL;DR

This paper introduces a computationally efficient sensitivity analysis framework using Shapley values for policy-augmented graphical hybrid models, aiding risk understanding and process control in biomanufacturing.

Contribution

It develops a novel SV-based sensitivity analysis method tailored for nonlinear and linear Gaussian pKG models, with improved efficiency through permutation sampling and variance reduction techniques.

Findings

Efficient SV estimation for complex bioprocess models.

Enhanced sampling methods improve accuracy and speed.

Framework supports better process interpretation and control.

Abstract

Driven by the critical challenges in biomanufacturing, including high complexity and high uncertainty, we propose a comprehensive and computationally efficient sensitivity analysis framework for general nonlinear policy-augmented knowledge graphical (pKG) hybrid models that characterize the risk- and science-based understandings of underlying stochastic decision process mechanisms. The criticality of each input (i.e., random factors, policy parameters, and model parameters) is measured by applying Shapley value (SV) sensitivity analysis to pKG (called SV-pKG), accounting for process causal interdependences. To quickly assess the SV for heavily instrumented bioprocesses, we approximate their dynamics with linear Gaussian pKG models and improve the SV estimation efficiency by utilizing the linear Gaussian properties. In addition, we propose an effective permutation sampling method with TFWW transformation and variance reduction techniques, namely the quasi-Monte Carlo and antithetic sampling methods, to further improve the sampling efficiency and estimation accuracy of SV for both general nonlinear and linear Gaussian pKG models. Our proposed framework can benefit efficient interpretation and support stable optimal process control in biomanufacturing.