Data Analytics and Machine Learning Applications in Fermentation Processes and Molecular Property Prediction - Dissertation

Aug 5, 2026

Upload by Eden

Multivariate data analytics and machine learning support bioprocess optimization and molecular property prediction across three connected research goals. The study models foaming occurrence in batch fermentation using multiway partial least squares, selecting exhaust differential pressure and integrating plant data with batch-wise and observation-wise unfolding to improve monitoring and explain process-variable effects. It also advances molecular property prediction via deep neural network hyperparameter optimization, comparing random search, Bayesian optimization, and hyperband. Finally, contamination risk is reduced through one-class SVM and autoencoders with parallelized HPO in Optuna, achieving high recall without sacrificing precision or specificity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages195

Reading Time8 h 11 min

AccessFree to download

Abstract

Foaming monitoring in batch fermentation (MPLS)

Hyperparameter optimization for deep learning MPP

Contamination detection and reduction with machine learning

Data Analytics and Machine Learning Applications in Fermentation Processes and Molecular Property Prediction Xuan Dung (James) Nguyen Dissertation submitted to the faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of Doctor of Philosophy In Chemical Engineering Yih-An Liu, Chair Steven P. Wrenn Sanket A. Deshmukh Christopher C. McDowell May 6, 2025 Blacksburg, Virginia Keywords: foaming, multiway partial least square, fermentation, multivariate statistics, hyperparameter tuning, machine learning, deep learning, contamination detection, autoencoders Data Analytics and Machine Learning Applications in Fermentation Processes and Molecular Property Prediction Xuan Dung (James) Nguyen ABSTRACT Multivariate data analytics (MVDA) and machine learning (ML) have been playing a crucial role in bioprocesses and molecular property prediction. Our study encompasses three main aspects: 1) using data analytics to analyze the occurrence of foaming in batch fermentation processes using multiway partial least square (MPLS) approaches; 2) using hyperparameter optimization methods in deep learning for the improvement of molecular property prediction, and 3) using machine learning models to predict and reduce contamination risk. For the first project, MPLS methods are used to develop interpretative correlation models to monitor the foaming occurrence and, hence, improve batch fermentation. The exhaust differential pressure is chosen as a quality variable to quantify the foaming occurrence and considers three-dimensional datasets of different batches, process variables, and measurements. Batch-wise unfolding (BWU) and observation-wise unfolding (OWU) of plant datasets are also integrated with standard, dynamic, and kernel PLS methods. The results show that dynamic PLS (DPLS) with OWU and time-lagged quality variables is the most efficient, accurate, and easy to implement. The BWU approach is useful for analyzing the differences between batches and identifying abnormalities and outliers, while the OWU quantifies the variation within a batch. With OWU, the DPLS method with one unit of time lag in the quality variable is the most effective, accurate, and easy to implement. With both BWU and OWU, the quantitative effects of process variables on the quality variable are identified and then used to guide to improve fermentation performance. The second project presents a methodology for hyperparameter optimization (HPO) in deep neural networks for accurate and efficient molecular property prediction (MPP) . Most prior applications of deep neural networks for MPP have paid only limited or no attention at all to HPO. Thus resulting in suboptimal values of predicted properties. To improve the efficiency and accuracy of deep learning models for MPP, we must optimize as many hyperparameters as possible and choose a software platform to enable the parallel execution of HPO. This project compares the random search, Bayesian optimization, and hyperband algorithms, together with the Bayesian-hyperband combination within the software packages of Kernas Turner and Optuna for HPO. In the end, the conclusion is that the hyperband algorithm, which has not been used in previous MPP studies, is most computationally efficient; it gives MPP results that are optimal or nearly optimal in terms of prediction accuracy. Based on two case studies, the use of the Python library Kernas Turner for HPO is recommended. Last but not least, the third project demonstrates an accurate and efficient methodology for fermentation contamination detection and reduction using machine learning methods. We identify two different machine learning methods including one-class support vector machine (OCSVM) and autoencoders (AEs), optimize as many hyperparameters as possible, and choose an open, user-friendly, and powerful Python platform called Optuna, a software platform to enab

FAQs

How does the research analyze foaming in batch fermentation processes?

It uses multiway partial least squares approaches to build interpretative correlation models for monitoring foaming occurrence, quantified with exhaust differential pressure. Batch-wise unfolding and observation-wise unfolding are integrated with standard, dynamic, and kernel PLS methods to identify variations and outliers.

What role does hyperparameter optimization play in molecular property prediction?

The dissertation presents a methodology that optimizes deep neural network hyperparameters to improve prediction accuracy and efficiency. It compares random search, Bayesian optimization, and hyperband (including Bayesian-hyperband) and concludes that hyperband is most computationally efficient, with Kernas Turner recommended for HPO in case studies.

Which methods are used for contamination detection and how is performance measured?

Contaminated batches are detected using one-class support vector machine and autoencoders with extensive hyperparameter optimization. Results report recall up to 1.0 for contamination prediction while maintaining strong precision and specificity for non-contaminated batches, and independent variables are identified to guide regulation strategies.

Aug 5, 2026

Upload by Eden