Segmentation of XCO2 images with deep learning: application to synthetic plumes from cities and power plants

• Published in: Geoscientific Model Development 2023-07, Vol.16 (13), p.3997-4016
• Main Authors: Joffrey Dumont Le Brazidec, Vanderbecken, Pierre, Farchi, Alban, Bocquet, Marc, Lian, Jinghui, Broquet, Grégoire, Kuhlmann, Gerrit, Danjou, Alexandre, Lauvaux, Thomas
• Format: Article
• Language: English
• Subjects: Algorithms; Anthropogenic factors; Artificial neural networks; Atmospheric models; Boundary conditions; Carbon dioxide; Cities; Coders; Computer simulation; Datasets; Deep learning; Distribution; Emissions; Emitters; Errors; Estimation; Hot spots; Image processing; Image segmentation; Industrial plant emissions; Machine learning; Modelling; Monitoring; Neural networks; Nitrogen dioxide; Plumes; Power plants; Satellite imagery; Satellite monitoring; Satellite observation; Satellites; Sciences of the Universe; Signal to noise ratio; Simulation; Support systems; Surface fluxes
• ISSN: 1991-962X; 1991-9603; 1991-959X; 1991-962X; 1991-959X; 1991-9603
• DOI: 10.5194/gmd-16-3997-2023

Under the Copernicus programme, an operational CO2 Monitoring Verification and Support system (CO2MVS) is being developed and will exploit data from future satellites monitoring the distribution of CO2 within the atmosphere. Methods for estimating CO2 emissions from significant local emitters (hotspots; i.e. cities or power plants) can greatly benefit from the availability of such satellite images that display the atmospheric plumes of CO2. Indeed, local emissions are strongly correlated to the size, shape, and concentration distribution of the corresponding plume, which is a visible consequence of the emission. The estimation of emissions from a given source can therefore directly benefit from the detection of its associated plumes in the satellite image.In this study, we address the problem of plume segmentation (i.e. the problem of finding all pixels in an image that constitute a city or power plant plume). This represents a significant challenge, as the signal from CO2 plumes induced by emissions from cities or power plants is inherently difficult to detect, since it rarely exceeds values of a few parts per million (ppm) and is perturbed by variable regional CO2 background signals and observation errors. To address this key issue, we investigate the potential of deep learning methods and in particular convolutional neural networks to learn to distinguish plume-specific spatial features from background or instrument features. Specifically, a U-Net algorithm, an image-to-image convolutional neural network with a state-of-the-art encoder, is used to transform an XCO2 field into an image representing the positions of the targeted plume. Our models are trained on hourly 1 km simulated XCO2 fields in the regions of Paris, Berlin, and several power plants in Germany. Each field represents the plume of the hotspot, with the background consisting of the signal of anthropogenic and biogenic CO2 surface fluxes near to or far from the targeted source and the simulated satellite observation errors.The performance of the deep learning method is thereafter evaluated and compared with a plume segmentation technique based on thresholding in two contexts, namely (1) where the model is trained and tested on data from the same region and (2) where the model is trained and tested in two different regions. In both contexts, our method outperforms the usual segmentation technique based on thresholding and demonstrates its ability to generalise in various cases, with respect