Search

Under the Copernicus programme, an operational CO 2 Monitoring Verification and Support system (CO 2 MVS) is being developed and will exploit data from future satellites monitoring the distribution of CO 2 within the atmosphere. Methods for estimating CO 2 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 CO 2. 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 CO 2 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 CO 2 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 XCO 2 field into an image representing the positions of the targeted plume. Our models are trained on hourly 1 km simulated XCO 2 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 CO 2 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 to city plumes, power plant plumes, and areas with multiple plumes. Although less accurate than in the first context, the ability of the algorithm to extrapolate on new geographical data is conclusive, paving the way to a promising universal segmentation model trained on a well-chosen sample of power plants and cities and able to detect the majority of the plumes from all of them. Finally, the highly accurate results for segmentation suggest the significant potential of convolutional neural networks for estimating local emissions from spaceborne imagery. [ABSTRACT FROM AUTHOR]

Under the Copernicus programme, an operational CO2 monitoring system (CO2MVS) is being developed and will exploit data from future satellites monitoring the amount 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, displaying atmospheric plumes of CO2. Indeed, local emissions are strongly correlated to the size, shape and concentrations distribution of the corresponding plume, the 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 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 German power plants. Each field represents the plume of the hotspot, the background consisting of the signal of anthropogenic and biogenic CO2 surface fluxes near 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: the first where the model is trained and tested on data from the same region, and the second 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: city plumes, power plant plumes, and areas with multiple plumes. Although less accurate than in the first context, the ability of the algorithm to extrapolate on new geographical data is conclusive, paving the way to a promising universal segmentation model, trained on a well-chosen sample of power plants and cities, and able to detect the majority of the plumes from all of them. Finally, the highly accurate results for segmentation suggest a significant potential of convolutional neural networks for estimating local emissions from spaceborne imagery. [ABSTRACT FROM AUTHOR]

High-resolution atmospheric transport simulations were used to investigate the potential for detecting carbon dioxide (CO2) plumes of the city of Berlin and neighboring power stations with the Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission, which is a proposed constellation of CO2 satellites with imaging capabilities. The potential for detecting plumes was studied for satellite images of CO2 alone or in combination with images of nitrogen dioxide (NO2) and carbon monoxide (CO) to investigate the added value of measurements of other gases coemitted with CO2 that have better signal-to-noise ratios. The additional NO2 and CO images were either generated for instruments on the same CO2M satellites (2 km × 2 km resolution) or for the Sentinel-5 instrument (7.5 km × 7.5 km) assumed to fly 2 h earlier than CO2M. Realistic CO2 , CO and NOX(=NO+NO2) fields were simulated at 1 km × 1 km horizontal resolution with the Consortium for Small-scale Modeling model extended with a module for the simulation of greenhouse gases (COSMO-GHG) for the year 2015, and they were used as input for an orbit simulator to generate synthetic observations of columns of CO2 , CO and NO2 for constellations of up to six satellites. A simple plume detection algorithm was applied to detect coherent structures in the images of CO2 , NO2 or CO against instrument noise and variability in background levels. Although six satellites with an assumed swath of 250 km were sufficient to overpass Berlin on a daily basis, only about 50 out of 365 plumes per year could be observed in conditions suitable for emission estimation due to frequent cloud cover. With the CO2 instrument only 6 and 16 of these 50 plumes could be detected assuming a high-noise (σVEG50=1.0 ppm) and low-noise (σVEG50=0.5 ppm) scenario, respectively, because the CO2 signals were often too weak. A CO instrument with specifications similar to the Sentinel-5 mission performed worse than the CO2 instrument, while the number of detectable plumes could be significantly increased to about 35 plumes with an NO2 instrument. CO2 and NO2 plumes were found to overlap to a large extent, although NOX had a limited lifetime (assumed to be 4 h) and although CO2 and NOX were emitted with different NOX:CO2 emission ratios by different source types with different temporal and vertical emission profiles. Using NO2 observations from the Sentinel-5 platform instead resulted in a significant spatial mismatch between NO2 and CO2 plumes due to the 2 h time difference between Sentinel-5 and CO2M. The plumes of the coal-fired power plant Jänschwalde were easier to detect with the CO2 instrument (about 40–45 plumes per year), but, again, an NO2 instrument could detect significantly more plumes (about 70). Auxiliary measurements of NO2 were thus found to greatly enhance the capability of detecting the location of CO2 plumes, which will be invaluable for the quantification of CO2 emissions from large point sources. [ABSTRACT FROM AUTHOR]

High-resolution atmospheric transport simulations were used to investigate the potential for detecting carbon dioxide (CO2) plumes of the city of Berlin and neighboring power stations with the Copernicus Anthropogenic Carbon Dioxide Monitoring (CO2M) mission, which is a proposed constellation of CO2 satellites with imaging capabilities. The potential for detecting plumes was studied for satellite images of CO2 alone or in combination with images of nitrogen dioxide (NO2) and carbon monoxide (CO) to investigate the added value of measurements of other gases co-emitted with CO2 that have better signal-to-noise ratios. The additional NO2 and CO images were either generated for instruments on the same CO2M satellites (2×2 km2 resolution) or for the Sentinel-5 instrument (7×7 km2) assumed to fly two hours earlier than CO2M. Realistic CO2, CO and NO2 fields were simulated at 1×1 km2 horizontal resolution with COSMO-GHG model for the year 2015, and used as input for an orbit simulator to generate synthetic observations of columns of CO2, CO and NO2 for constellations of up to six satellites. A new plume detection algorithm was applied to detect coherent structures in the images of CO2, NO2 or CO against instrument noise and variability in background levels. Although six satellites with an assumed swath of 250 km were sufficient to overpass Berlin on a daily basis, only about 50 out of 365 plumes per year could be observed in conditions suitable for emission estimation due to frequent cloud cover. With the CO2 instrument only 6 and 16 of these 50 plumes could be detected assuming a high (σVEG50 = 1.0 ppm) and low noise (σVEG50 = 0.5 ppm) scenario, respectively, because the CO2 signals were often too weak. A CO instrument with specifications similar to the Sentinel-5 mission performed worse than the CO2 instrument, while the number of detectable plumes could be significantly increased to about 35 plumes with an NO2 instrument. Using NO2 observations from the Sentinel-5 platform instead resulted in a significant spatial mismatch between NO2 and CO2 plumes due to the two hour time difference between Sentinel-5 and CO2M. The plumes of the coal-fired power plant Jänschwalde were easier to detect with the CO2 instrument (about 40–45 plumes per year), but again, an NO2 instrument performed significantly better (about 70 plumes). Auxiliary measurements of NO2 were thus found to greatly enhance the capability of detecting the location of CO2 plumes, which will be invaluable for the quantification of CO2 emissions from large point sources. [ABSTRACT FROM AUTHOR]