Super-Resolution for Gas Distribution Mapping: Convolutional Encoder-Decoder Network
- Gas distribution mapping is important to have an accurate understanding of gas concentration levels in hazardous environments. A major problem is that in-situ gas sensors are only able to measure concentrations at their specific location. The gas distribution in-between the sampling locations must therefore be modeled. In this research, we interpret the task of spatial interpolation between sparsely distributed sensors as a task of enhancing an image's resolution, namely super-resolution. Because autoencoders are proven to perform well for this super-resolution task, we trained a convolutional encoder-decoder neural network to map the gas distribution over a spatially sparse sensor network. Due to the difficulty to collect real-world gas distribution data and missing ground truth, we used synthetic data generated with a gas distribution simulator for training and evaluation of the model. Our results show that the neural network was able to learn the behavior of gas plumes andGas distribution mapping is important to have an accurate understanding of gas concentration levels in hazardous environments. A major problem is that in-situ gas sensors are only able to measure concentrations at their specific location. The gas distribution in-between the sampling locations must therefore be modeled. In this research, we interpret the task of spatial interpolation between sparsely distributed sensors as a task of enhancing an image's resolution, namely super-resolution. Because autoencoders are proven to perform well for this super-resolution task, we trained a convolutional encoder-decoder neural network to map the gas distribution over a spatially sparse sensor network. Due to the difficulty to collect real-world gas distribution data and missing ground truth, we used synthetic data generated with a gas distribution simulator for training and evaluation of the model. Our results show that the neural network was able to learn the behavior of gas plumes and outperforms simpler interpolation techniques.…
Autor*innen: | Nicolas P. WinklerORCiD, H. Matsukura, Patrick P. NeumannORCiD, E. Schaffernicht, H. Ishida, A. J. Lilienthal |
---|---|
Persönliche Herausgeber*innen: | A. Rudnitskaya |
Dokumenttyp: | Beitrag zu einem Tagungsband |
Veröffentlichungsform: | Graue Literatur |
Sprache: | Englisch |
Titel des übergeordneten Werkes (Englisch): | 2022 IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) Proceedings |
Jahr der Erstveröffentlichung: | 2022 |
Organisationseinheit der BAM: | 8 Zerstörungsfreie Prüfung |
8 Zerstörungsfreie Prüfung / 8.1 Sensorik, mess- und prüftechnische Verfahren | |
Verlag: | IEEE |
Verlagsort: | USA |
Erste Seite: | 1 |
Letzte Seite: | 3 |
DDC-Klassifikation: | Naturwissenschaften und Mathematik / Chemie / Analytische Chemie |
Freie Schlagwörter: | Deep Learning; Gas Distribution Mapping; Sensor Network; Spatial Interpolation; Super-Resolution |
Themenfelder/Aktivitätsfelder der BAM: | Umwelt |
Umwelt / Sensorik | |
Veranstaltung: | 19th International Symposium on Olfaction and Electronic Nose |
Veranstaltungsort: | Aveiro, Portugal |
Beginndatum der Veranstaltung: | 29.05.2022 |
Enddatum der Veranstaltung: | 01.06.2022 |
DOI: | 10.1109/isoen54820.2022.9789555 |
ISBN: | 978-1-6654-5860-3 |
Verfügbarkeit des Dokuments: | Datei im Netzwerk der BAM verfügbar ("Closed Access") |
Datum der Freischaltung: | 08.06.2022 |
Referierte Publikation: | Ja |
Datum der Eintragung als referierte Publikation: | 26.09.2022 |