Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-647363
GNN-DM: A Graph Neural Network Framework for Real-World Gas Distribution Mapping
- Gas distribution mapping (GDM) is essential for industrial safety and environmental monitoring, as it enables real-time hazard detection and air quality assessment. Traditional GDM methods, such as kernel-based techniques, struggle to reconstruct complex gas plume dynamics accurately. While deep learning has shown promise for GDM, two critical challenges hinder its practical use: the scarcity of available training data and the incompatibility of conventional architectures with irregular sensor layouts. To address these limitations, we propose GNN-DM, a graph neural network-based model for GDM that incorporates the relational structure of sensor networks to infer high-resolution maps from minimal, irregular inputs. The model is pretrained on synthetic gas dispersion data generated from measured wind data and fine-tuned on two industrial datasets collected on a ferry car deck and in a hot rolling mill. Compared with established GDM techniques, GNN-DM achieves higher accuracy on syntheticGas distribution mapping (GDM) is essential for industrial safety and environmental monitoring, as it enables real-time hazard detection and air quality assessment. Traditional GDM methods, such as kernel-based techniques, struggle to reconstruct complex gas plume dynamics accurately. While deep learning has shown promise for GDM, two critical challenges hinder its practical use: the scarcity of available training data and the incompatibility of conventional architectures with irregular sensor layouts. To address these limitations, we propose GNN-DM, a graph neural network-based model for GDM that incorporates the relational structure of sensor networks to infer high-resolution maps from minimal, irregular inputs. The model is pretrained on synthetic gas dispersion data generated from measured wind data and fine-tuned on two industrial datasets collected on a ferry car deck and in a hot rolling mill. Compared with established GDM techniques, GNN-DM achieves higher accuracy on synthetic and real-world data, highlighting the potential of graph-based learning for practical gas mapping applications.…


| Autor*innen: | Nicolas P. WinklerORCiD, Patrick P. NeumannORCiD, Natalia Albizu, Erik SchaffernichtORCiD, Achim J. LilienthalORCiD |
|---|---|
| Dokumenttyp: | Zeitschriftenartikel |
| Veröffentlichungsform: | Verlagsliteratur |
| Sprache: | Englisch |
| Titel des übergeordneten Werkes (Englisch): | IEEE Sensors Journal |
| Jahr der Erstveröffentlichung: | 2025 |
| Organisationseinheit der BAM: | 8 Zerstörungsfreie Prüfung |
| 8 Zerstörungsfreie Prüfung / 8.1 Sensorik, mess- und prüftechnische Verfahren | |
| Veröffentlichende Institution: | Bundesanstalt für Materialforschung und -prüfung (BAM) |
| Verlag: | Institute of Electrical and Electronics Engineers (IEEE) |
| Jahrgang/Band: | 25 |
| Ausgabe/Heft: | 22 |
| Erste Seite: | 42171 |
| Letzte Seite: | 42179 |
| DDC-Klassifikation: | Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Sanitär- und Kommunaltechnik; Umwelttechnik |
| Freie Schlagwörter: | Deep learning; Environmental monitoring; Sensor networks; Transfer learning |
| Themenfelder/Aktivitätsfelder der BAM: | Umwelt |
| DOI: | 10.1109/JSEN.2025.3617158 |
| URN: | urn:nbn:de:kobv:b43-647363 |
| ISSN: | 1530-437X |
| Verfügbarkeit des Dokuments: | Datei für die Öffentlichkeit verfügbar ("Open Access") |
| Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |
| Datum der Freischaltung: | 17.11.2025 |
| Referierte Publikation: | Ja |
| Datum der Eintragung als referierte Publikation: | 22.12.2025 |
| Schriftenreihen ohne Nummerierung: | Wissenschaftliche Artikel der BAM |


