no code implementations • 1 Feb 2024 • Christoph Lange, Isabel Thiele, Lara Santolin, Sebastian L. Riedel, Maxim Borisyak, Peter Neubauer, M. Nicolas Cruz Bournazou
This is of interest in scenarios where large amounts of historical data are available but are currently not used for model training.
no code implementations • 6 Dec 2023 • Judit Aizpuru, Maxim Borisyak, Peter Neubauer, M. Nicolas Cruz Bournazou
We demonstrate the framework's capabilities by fitting a hybrid model based on a simple mechanistic growth model for E. coli with data generated in-silico by a much more complex one and identifying missing kinetics.
no code implementations • 5 Dec 2023 • Maxim Borisyak, Stefan Born, Peter Neubauer, Mariano Nicolas Cruz-Bournazou
We consider a training procedure that combines Neural Networks and mechanistic models.
no code implementations • 4 Dec 2023 • Maxim Borisyak, Stefan Born, Peter Neubauer, Mariano Nicolas Cruz-Bournazou
The method is agnostic to the particular nature of the time series and can be adapted for any task, for example, online monitoring, predictive control, design of experiments, etc.
no code implementations • 1 Dec 2023 • Niels Krausch, Martin Doff-Sotta, Mark Canon, Peter Neubauer, Mariano Nicolas Cruz Bournazou
Bioprocesses are often characterized by nonlinear and uncertain dynamics.
no code implementations • 2 Sep 2022 • Nghia Duong-Trung, Stefan Born, Jong Woo Kim, Marie-Therese Schermeyer, Katharina Paulick, Maxim Borisyak, Mariano Nicolas Cruz-Bournazou, Thorben Werner, Randolf Scholz, Lars Schmidt-Thieme, Peter Neubauer, Ernesto Martinez
ML can be seen as a set of tools that contribute to the automation of the whole experimental cycle, including model building and practical planning, thus allowing human experts to focus on the more demanding and overarching cognitive tasks.
no code implementations • 14 Mar 2022 • Jong Woo Kim, Niels Krausch, Judit Aizpuru, Tilman Barz, Sergio Lucia, Peter Neubauer, Mariano Nicolas Cruz Bournazou
We discuss the application of a nonlinear model predictive control (MPC) and a moving horizon estimation (MHE) to achieve an optimal operation of \textit{E. coli} fed-batch cultivations with intermittent bolus feeding.
no code implementations • 25 Dec 2021 • Judit Aizpuru, Annina Karolin Kemmer, Jong Woo Kim, Stefan Born, Peter Neubauer, Mariano N. Cruz Bournazou, Tilman Barz
TheDissolved Oxygen Tension is often the only measurement which is available online, and therefore, a good understanding of the errors in this signal is important for performing a robust estimation. Some of the expected errors will provoke uncertainties in the time-domain of the measurement, and in those cases, the common Weighted Least Squares estimation procedure can fail providing good results.
no code implementations • 20 Dec 2021 • Jong Woo Kim, Niels Krausch, Judit Aizpuru, Tilman Barz, Sergio Lucia, Ernesto C. Martínez, Peter Neubauer, Mariano Nicolas Cruz Bournazou
Optimal experimental design for parameter precision attempts to maximize the information content in experimental data for a most effective identification of parametric model.