no code implementations • 21 Mar 2024 • Daniel Mayfrank, Na Young Ahn, Alexander Mitsos, Manuel Dahmen
We present a method for end-to-end learning of Koopman surrogate models for optimal performance in control.
no code implementations • 13 Mar 2024 • Eleni D. Koronaki, Luise F. Kaven, Johannes M. M. Faust, Ioannis G. Kevrekidis, Alexander Mitsos
Polymer particle size constitutes a crucial characteristic of product quality in polymerization.
1 code implementation • 6 Mar 2024 • Christoforos Brozos, Jan G. Rittig, Sandip Bhattacharya, Elie Akanny, Christina Kohlmann, Alexander Mitsos
We test the predictive quality of the model for following scenarios: i) when CMC data for surfactants are present in the training of the model in at least one different temperature, and ii) CMC data for surfactants are not present in the training, i. e., generalizing to unseen surfactants.
no code implementations • 9 Jan 2024 • Jan C. Schulze, Alexander Mitsos
We use Koopman theory for data-driven model reduction of nonlinear dynamical systems with controls.
1 code implementation • 3 Jan 2024 • Christoforos Brozos, Jan G. Rittig, Sandip Bhattacharya, Elie Akanny, Christina Kohlmann, Alexander Mitsos
A key factor in the predictive ability of QSPR and GNN models is the data available for training.
no code implementations • 11 Sep 2023 • Jan C. Schulze, Danimir T. Doncevic, Nils Erwes, Alexander Mitsos
Further, we present an NMPC implementation that uses derivative computation tailored to the fixed block structure of reduced Koopman models.
no code implementations • 3 Aug 2023 • Daniel Mayfrank, Alexander Mitsos, Manuel Dahmen
(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable.
no code implementations • 31 May 2023 • Jan G. Rittig, Kobi C. Felton, Alexei A. Lapkin, Alexander Mitsos
In contrast to recent hybrid ML approaches, our approach does not rely on embedding a specific thermodynamic model inside the neural network and corresponding prediction limitations.
no code implementations • 22 Nov 2022 • Danimir T. Doncevic, Alexander Mitsos, Yue Guo, Qianxiao Li, Felix Dietrich, Manuel Dahmen, Ioannis G. Kevrekidis
Meta-learning of numerical algorithms for a given task consists of the data-driven identification and adaptation of an algorithmic structure and the associated hyperparameters.
no code implementations • 27 Jul 2022 • Artur M. Schweidtmann, Jan G. Rittig, Jana M. Weber, Martin Grohe, Manuel Dahmen, Kai Leonhard, Alexander Mitsos
We recommend using sum pooling for the prediction of properties that depend on molecular size and compare pooling functions for properties that are molecular size-independent.
no code implementations • 25 Jul 2022 • Jan G. Rittig, Qinghe Gao, Manuel Dahmen, Alexander Mitsos, Artur M. Schweidtmann
Molecular property prediction is of crucial importance in many disciplines such as drug discovery, molecular biology, or material and process design.
no code implementations • 23 Jun 2022 • Jan G. Rittig, Karim Ben Hicham, Artur M. Schweidtmann, Manuel Dahmen, Alexander Mitsos
We train the GNN on a database including more than 40, 000 AC values and compare it to a state-of-the-art MCM.
no code implementations • 1 Jun 2022 • Jan G. Rittig, Martin Ritzert, Artur M. Schweidtmann, Stefanie Winkler, Jana M. Weber, Philipp Morsch, K. Alexander Heufer, Martin Grohe, Alexander Mitsos, Manuel Dahmen
We propose a modular graph-ML CAMD framework that integrates generative graph-ML models with graph neural networks and optimization, enabling the design of molecules with desired ignition properties in a continuous molecular space.
no code implementations • 27 May 2022 • Eike Cramer, Dirk Witthaut, Alexander Mitsos, Manuel Dahmen
This work proposes a probabilistic modeling approach that models the intraday price difference to the day-ahead contracts.
no code implementations • 5 Apr 2022 • Eike Cramer, Leonard Paeleke, Alexander Mitsos, Manuel Dahmen
We present a specialized scenario generation method that utilizes forecast information to generate scenarios for day-ahead scheduling problems.
no code implementations • 8 Mar 2022 • Eike Cramer, Felix Rauh, Alexander Mitsos, Raúl Tempone, Manuel Dahmen
To model manifold data using normalizing flows, we employ isometric autoencoders to design embeddings with explicit inverses that do not distort the probability distribution.
no code implementations • 27 Oct 2021 • Eike Cramer, Leonardo Rydin Gorjão, Alexander Mitsos, Benjamin Schäfer, Dirk Witthaut, Manuel Dahmen
The design and operation of modern energy systems are heavily influenced by time-dependent and uncertain parameters, e. g., renewable electricity generation, load-demand, and electricity prices.
no code implementations • 21 Apr 2021 • Eike Cramer, Alexander Mitsos, Raul Tempone, Manuel Dahmen
We train the resulting principal component flow (PCF) on data of PV and wind power generation as well as load demand in Germany in the years 2013 to 2015.
no code implementations • 7 Feb 2021 • Simon Olofsson, Eduardo S. Schultz, Adel Mhamdi, Alexander Mitsos, Marc Peter Deisenroth, Ruth Misener
Typically, several rival mechanistic models can explain the available data, so design of dynamic experiments for model discrimination helps optimally collect additional data by finding experimental settings that maximise model prediction divergence.
no code implementations • 21 May 2020 • Artur M. Schweidtmann, Dominik Bongartz, Daniel Grothe, Tim Kerkenhoff, Xiaopeng Lin, Jaromil Najman, Alexander Mitsos
Often, Gaussian processes are trained on datasets and are subsequently embedded as surrogate models in optimization problems.