ArticleJournal of industrial microbiology & biotechnology2026
Hybrid modeling for industrial fermentation processes with an "Intra-Batch Experimental Design".
Article in Journal of industrial microbiology & biotechnology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
Abstract
Successful development of a predictive digital twin or digital shadow enabling improved batch planning and process optimization of industrial fungal fermentation relies on the fidelity of oxygen transfer rate modeling. Such models depend, among other factors, on viscosity. Traditional process models use mechanistic approaches to describe the apparent viscosity but face challenges due to its inherent complex behavior, requiring many assumptions and often relying on tedious offline rheological measurements. This article presents a novel model development framework, which significantly reduces associated experimental costs and eliminates the need for offline rheological measurement. First, a method for developing a model for the oxygen mass transfer coefficient (kLa) at pilot scale is presented, reducing experimental effort from nine to two fermentations while achieving an R² of 0.92 with online data compared to an R² of 0.67 with offline data. Alongside the mechanistic model, which links biological yields to the fungal growth rate, three machine learning algorithms were evaluated as a data-driven soft sensor for predicting online viscosity across different strains and scales. The outcome is a hybrid model that requires less manual lab work for its development while predicting the dynamics of six pilot-scale fermentations under a variety of operating conditions with a modest improvement in accuracy. Results emphasize the importance of integrating online sensor technologies into mathematical model development and highlight their role in advancing data-driven methods. By lowering the costs and efforts of model development, this study contributes to the long-term vision of automated model development for industrial applications. One-sentence summary This study presents a novel hybrid modeling approach that minimizes experimental efforts by replacing offline viscosity measurements with online dynamic viscosity data to predict oxygen transfer for industrial fungal fermentation processes at a 550 L pilot scale, enabling more time, and cost-efficient bioprocess model development.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.