Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: A systematic scientific machine learning approach

• Type: Article in International Scientific Journal
• Date: 2023

Authors

Santana, VV (Author) Other; Costa, E (Author) Other; Rebello, CM (Author) Other; Ana M. Ribeiro (Author) FEUP; Rackauckas, C (Author) Other; Nogueira, IBR (Author) Other

Journal

Title: Chemical Engineering Science

Vol. 282

ISSN: 0009-2509

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-00Z-3X9

DOI: 10.1016/j.ces.2023.119223

Abstract (EN): This study presents a systematic machine learning approach for creating efficient hybrid models and discovering sorption uptake models in non-linear advection-diffusion-sorption systems. It demonstrates an effective method to train these complex systems using gradient-based optimizers, adjoint sensitivity analysis, and JIT-compiled vector Jacobian products, combined with spatial discretization and adaptive integrators. Sparse and symbolic regression were employed to identify missing functions in the artificial neural network. The robustness of the proposed method was tested on an in-silico data set of noisy breakthrough curve observations of fixed-bed adsorption, resulting in a well-fitted hybrid model. The study successfully reconstructed sorption uptake kinetics using sparse and symbolic regression, and accurately predicted breakthrough curves using identified polynomials, highlighting the potential of the proposed framework for discovering sorption kinetic law structures.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15