64736 2025 eng 42171 42179 22 25 article Institute of Electrical and Electronics Engineers (IEEE) 1 -- -- -- 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 synthetic and real-world data, highlighting the potential of graph-based learning for practical gas mapping applications. IEEE Sensors Journal 1530-437X 10.1109/JSEN.2025.3617158 urn:nbn:de:kobv:b43-647363 true journal-article https://creativecommons.org/licenses/by/4.0/legalcode crossref PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorIdentifierOrcid_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorIdentifierOrcid_5,PublisherName,TitleMain_1,TitleParent_1,PageFirst,PageLast,Issue,Volume,PublishedYear,IdentifierIssn,Enrichmentlocal_crossrefLicence doi-import 22.12.2025 Creative Commons - CC BY - Namensnennung 4.0 International Nicolas P. Winkler Patrick P. Neumann Natalia Albizu Erik Schaffernicht Achim J. Lilienthal eng uncontrolled Environmental monitoring eng uncontrolled Sensor networks eng uncontrolled Transfer learning eng uncontrolled Deep learning Sanitär- und Kommunaltechnik; Umwelttechnik 8 Zerstörungsfreie Prüfung 8.1 Sensorik, mess- und prüftechnische Verfahren Umwelt Verlagsliteratur Datei für die Öffentlichkeit verfügbar ("Open Access") Wissenschaftliche Artikel der BAM Bundesanstalt für Materialforschung und -prüfung (BAM) https://opus4.kobv.de/opus4-bam/files/64736/GNN-DM_A_Graph_Neural_Network_Framework_for_Real-World_Gas_Distribution_Mapping.pdf