| Title: |
Neural network-based surrogate model for 3D edge-plasma transport in the standard configuration of W7-X |
| Authors: |
W7-X Team; Luo, Y.; Xu, S.; Liang, Y.; Wang, E.; Cai, J.; Knieps, A.; Pei, R.; Tan, Muzhi; Feng, Y.; Reiter, D.; Brezinsek, S.; Harting, D.; Krychowiak, M.; Gradic, D.; Jakubowski, M. |
| Source: |
Nuclear Fusion, 66 (1), 016038 ; ISSN: 0029-5515, 1741-4326 |
| Publisher Information: |
International Atomic Energy Agency |
| Publication Year: |
2025 |
| Collection: |
KITopen (Karlsruhe Institute of Technologie) |
| Subject Terms: |
ddc:600; Technology; info:eu-repo/classification/ddc/600 |
| Description: |
This paper presents a neural-network surrogate model for Wendelstein 7-X (W7-X) edge transport simulations, trained on an EMC3-EIRENE dataset that spans nearly the entire operating-parameter space currently explored in the W7-X standard configuration. The model uses an autoencoder to compress EMC3-EIRENE outputs into a low-dimensional latent space representation, then a neural regressor maps EMC3-EIRENE input parameters to those latent vectors, and finally both components are fine-tuned together to predict outputs directly from inputs. In benchmark tests, the improved surrogate outperforms a traditional multilayer perceptron model, most notably in predicting detached regime. Leave-one-value-out evaluation indicates high accuracy within the interpolation domain, with minor degradation when extrapolating. Relative to full EMC3-EIRENE runs, the surrogate provides over a 108 - fold speedup, enabling large-scale parameter scans or real-time feedback control based on 3D transport simulations to become feasible in the future. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| ISSN: |
0029-5515; 1741-4326 |
| Relation: |
info:eu-repo/grantAgreement/EC/EURATOM/101052200/EU//EUROfusion; info:eu-repo/semantics/altIdentifier/wos/001625806500001; info:eu-repo/semantics/altIdentifier/issn/0029-5515; info:eu-repo/semantics/altIdentifier/issn/1741-4326; https://publikationen.bibliothek.kit.edu/1000188250 |
| Availability: |
https://publikationen.bibliothek.kit.edu/1000188250 |
| Rights: |
info:eu-repo/semantics/openAccess |
| Accession Number: |
edsbas.C61AE881 |
| Database: |
BASE |