← Back to all news
arXiv Machine Learning By Keilung Choy, Wei Xie

Adjoint-Based Calibration and Optimal Control of Stochastic Multiscale Bioprocess Digital Twins

Read the original on arXiv Machine Learning →

The paper presents a bias-aware digital‑twin calibration and control framework for multiscale bioprocess models, using stochastic differential equations and quasi‑likelihood estimation with adjoint sensitivity analysis. It introduces SDE generator‑based moment expansions to quantify truncation‑induced parameter bias and forward‑backward adjoints to trace how calibration uncertainty affects value functions and policy performance. An Actor‑Simulator algorithm is proposed to jointly update model parameters, select informative experiments, and optimize control policies, achieving improved calibration accuracy, sample efficiency, and control performance in numerical studies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 21

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing

arXiv:2607. 18164v1 Announce Type: cross Abstract: Digital Twins rely on surrogate models to mirror physical systems in real time, yet these models can degrade as operating conditions evolve, a phenomenon known as concept drift.

By Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria, Seul Lee, Daniel Apley, Wei Chen
fine-tuning
More like this →
arXiv AI
Aug 24

A Hybrid Edge Cloud Digital Twin for Welfare-Constrained Control in Poultry Production

The paper presents a hybrid edge‑cloud digital twin for welfare‑constrained environmental control in poultry farms. It combines distributed sensing, on‑device state estimation, a physics‑based thermodynamic model with a learned residual, and model predictive control to adaptively manage temperature and ammonia levels. Experiments in a broiler testbed show significant improvements: temperature prediction error drops from 1.8 °C to 0.4 °C, ammonia violations fall by 90 %, and communication needs are reduced 30‑fold, with a Domain Transfer Score of 0.92 indicating strong cross‑facility robustness.

By Suresh Neethirajan
More like this →
arXiv Machine Learning
Jun 18

A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development

arXiv:2606. 19230v1 Announce Type: new Abstract: This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian process (GP) surrogate-derived quantities are reformulated as objectives of a multi-objective optimization problem, and the resulting Pareto front is exposed to a domain expert for interactive candidate selection rather than returning a single automated recommendation.

By Samuel Stricker, Claus Wirnsperger, Alessandro Butt\'e, Laura Helleckes, Gonzalo Guill\'en Gos\'albez, Antonio del Rio Chanona, Mehmet Mercang\"oz
More like this →
arXiv Machine Learning
Jun 16

Graphical conditional generative modeling for digital twin modeling

arXiv:2606. 16219v1 Announce Type: cross Abstract: Digital twin modeling, including control and data assimilation under model uncertainty, often faces an open-ended fidelity problem: adding variables, data streams, and time scales can indefinitely increase model complexity, ultimately producing systems that are difficult to maintain, validate, interpret, and use for stress or safety testing.

By Zongren Zou, Th\'eo Bourdais, Ricardo Baptista, Houman Owhadi
reinforcement-learningefficiencysafety
More like this →