TY - CONF A1 - Winkler, Nicolas P. A1 - Kotlyar, O. A1 - Schaffernicht, E. A1 - Fan, H. A1 - Matsukura, H. A1 - Ishida, H. A1 - Neumann, Patrick P. A1 - Lilienthal, A. J. ED - Tardioli, D. ED - Matellán, V. ED - Heredia, G. ED - Silva, M. F. ED - Marques, L. T1 - Learning From the Past: Sequential Deep Learning for Gas Distribution Mapping N2 - To better understand the dynamics in hazardous environments, gas distribution mapping aims to map the gas concentration levels of a specified area precisely. Sampling is typically carried out in a spatially sparse manner, either with a mobile robot or a sensor network and concentration values between known data points have to be interpolated. In this paper, we investigate sequential deep learning models that are able to map the gas distribution based on a multiple time step input from a sensor network. We propose a novel hybrid convolutional LSTM - transpose convolutional structure that we train with synthetic gas distribution data. Our results show that learning the spatial and temporal correlation of gas plume patterns outperforms a non-sequential neural network model. T2 - ROBOT2022: Fifth Iberian Robotics Conference CY - Zaragoza, Spain DA - 22.11.2022 KW - Gas Distribution Mapping KW - Spatial Interpolation KW - Sequential Learning KW - Convolutional LSTM PY - 2023 SN - 978-3-031-21061-7 DO - https://doi.org/10.1007/978-3-031-21062-4_15 SP - 178 EP - 188 PB - Springer International Publishing AN - OPUS4-56414 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. A1 - Matsukura, H. A1 - Neumann, Patrick P. A1 - Schaffernicht, E. A1 - Ishida, H. A1 - Lilienthal, A. J. ED - Rudnitskaya, A. T1 - Super-Resolution for Gas Distribution Mapping: Convolutional Encoder-Decoder Network N2 - 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 and outperforms simpler interpolation techniques. T2 - 19th International Symposium on Olfaction and Electronic Nose CY - Aveiro, Portugal DA - 29.05.2022 KW - Gas Distribution Mapping KW - Spatial Interpolation KW - Deep Learning KW - Super-Resolution KW - Sensor Network PY - 2022 SN - 978-1-6654-5860-3 DO - https://doi.org/10.1109/isoen54820.2022.9789555 SP - 1 EP - 3 PB - IEEE CY - USA AN - OPUS4-54955 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Winkler, Nicolas P. A1 - Kotlyar, O. A1 - Schaffernicht, E. A1 - Matsukura, H. A1 - Ishida, H. A1 - Neumann, Patrick P. A1 - Lilienthal, A. J. T1 - Super-resolution for Gas Distribution Mapping N2 - Gas Distribution Mapping (GDM) is a valuable tool for monitoring the distribution of gases in a wide range of applications, including environmental monitoring, emergency response, and industrial safety. While GDM is actively researched in the scope of gas-sensitive mobile robots (Mobile Robot Olfaction), there is a potential for broader applications utilizing sensor networks. This study aims to address the lack of deep learning approaches in GDM and explore their potential for improved mapping of gas distributions. In this paper, we introduce Gas Distribution Decoder (GDD), a learning-based GDM method. GDD is a deep neural network for spatial interpolation between sparsely distributed sensor measurements that was trained on an extensive data set of realistic-shaped synthetic gas plumes based on actual airflow measurements. As access to ground truth representations of gas distributions remains a challenge in GDM research, we make our data sets, along with our models, publicly available. We test and compare GDD with state-of-the-art models on synthetic and real-world data. Our findings demonstrate that GDD significantly outperforms existing models, demonstrating a 35% improvement in accuracy on synthetic data when measured using the Root Mean Squared Error over the entire distribution map. Notably, GDD appears to have superior capabilities in reconstructing the edges and characteristic shapes of gas plumes compared to traditional models. These potentials offer new possibilities for more accurate and efficient environmental monitoring, and we hope to inspire other researchers to explore learning-based GDM. KW - Gas distribution mapping KW - Spatial interpolation KW - Sensor networks KW - Deep learning PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-607786 DO - https://doi.org/10.1016/j.snb.2024.136267 SN - 0925-4005 VL - 419 SP - 1 EP - 12 PB - Elsevier B.V. AN - OPUS4-60778 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -