Heinlein, Alexander ORCID: 0000-0003-1578-8104, Klawonn, Axel ORCID: 0000-0003-4765-7387, Lanser, Martin and Weber, Janine (2021). Predicting the geometric location of critical edges in adaptive GDSW overlapping domain decomposition methods using deep learning. Technical Report.


Download (1MB) | Preview


Overlapping GDSW domain decomposition methods are considered for diffusion problems in two dimensions discretized by finite elements. For a diffusion coefficient with high contrast, the condition number is usually dependent on it. A remedy is given by adaptive domain decomposition methods, where the coarse space is enhanced by additional coarse basis functions. These are chosen problem-dependently by solving small local eigenvalue problems. Here, the eigenvalue problems (EVPs) are associated with the edges of the domain decomposition interface; edges, where these EVPs have to be solved are denoted as critical edges. For many applications, not all edges are critical and the solution of the EVPs is not necessary. In an earlier work, a strategy to predict the location of critical edges, based on deep learning, has been proposed for adaptive FETI-DP, a class of nonoverlapping methods. In the present work, this strategy is successfully applied to adaptive GDSW; differences in the classification process for this overlapping method are described. Choosing the classification threshold has been a challenge in all these approaches. Here, for the first time, a heuristic based on the receiver operating characteristic (ROC) curve and the precision-recall graph is discussed. Results for a challenging realistic coefficient function are presented.

Item Type: Preprints, Working Papers or Reports (Technical Report)
CreatorsEmailORCIDORCID Put Code
Heinlein, Alexanderalexander.heinlein@uni-koeln.deorcid.org/0000-0003-1578-8104UNSPECIFIED
Klawonn, Axelaxel.klawonn@uni-koeln.deorcid.org/0000-0003-4765-7387UNSPECIFIED
Lanser, Martinmartin.lanser@uni-koeln.deUNSPECIFIEDUNSPECIFIED
Weber, Janinejanine.weber@uni-koeln.deUNSPECIFIEDUNSPECIFIED
URN: urn:nbn:de:hbz:38-362571
Series Name at the University of Cologne: Technical report series. Center for Data and Simulation Science
Volume: 2021,2
Date: 12 March 2021
Language: English
Faculty: Central Institutions / Interdisciplinary Research Centers
Divisions: Weitere Institute, Arbeits- und Forschungsgruppen > Center for Data and Simulation Science (CDS)
Subjects: Data processing Computer science
Technology (Applied sciences)
Uncontrolled Keywords:
machine learningEnglish
deep learningEnglish
domain decomposition methodsEnglish
adaptive coarse spacesEnglish
finite elementsEnglish
Refereed: No
URI: http://kups.ub.uni-koeln.de/id/eprint/36257


Downloads per month over past year


Actions (login required)

View Item View Item