Bioprocess Dynamic Modelling Data for Fermentation and Algal Photo-Production

A study by Max Mowbray at the University of Manchester explores the application of Gradient Boosting for dynamic modelling and prediction in bioprocesses. The work includes case studies on fermentation and algal photo-production processes, comparing the data efficiency of Gradient Boosting against artificial neural networks. It concludes that Gradient Boosting may offer advantages for predictive modelling with small experimental datasets.

Use Cases

• Building predictive models for fermentation processes based on dynamic operational data.
• Optimizing algal photo-production systems using ensemble learning techniques.
• Comparing the performance of Gradient Boosting and neural networks for bioprocess modelling.
• Developing data-efficient models for bioprocess digitalisation where experimental data is limited.

Strengths

• Focuses on data efficiency, a key challenge for bioprocesses where generating large experimental datasets is difficult.
• Includes experimental verification across a broad spectrum of process operating conditions.
• Compares an emerging ensemble learning algorithm (Gradient Boosting) against a predominant method (artificial neural networks).

Limitations

• Row count, column names, and sample data are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

University of Manchester

Collection Method

Likely contains experimental data from case studies on fermentation and algal photo-production processes.