{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T22:16:05Z","timestamp":1762640165408,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["2023NSCQ-MSX3709"],"award-info":[{"award-number":["2023NSCQ-MSX3709"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Estimation of anthropogenic carbon dioxide (CO2) emission sources and natural sinks (i.e., CO2 fluxes) is essential for the development of climate policies. Satellite observations provide an opportunity for top-down inversion of CO2 fluxes, which can be used to improve the results of bottom-up estimation. This study proposes to develop a new top-down CO2 flux estimation method based on deep learning, as well as satellite observations, and an atmospheric chemical transport model. This method utilizes two deep learning models: the concentration correction model and the concentration\u2013flux inversion model. The former optimizes the GEOS-Chem-simulated CO2 concentration using Orbiting Carbon Observatory-2 (OCO-2) satellite observations, while the latter establishes the complicated relationship between CO2 concentration and CO2 flux. Results showed that both deep learning models demonstrated excellent prediction performance, with a mean bias of 0.461 ppm for the concentration correction model and an annual mean correlation coefficient of 0.920 for the concentration\u2013flux inversion model. A posterior CO2 flux was obtained through a two-step optimization process using these well-trained models. Our findings indicate that the posterior estimations of CO2 flux sources in eastern China and northern Europe have been significantly reduced compared to the prior estimations. This study provides a new perspective on top-down CO2 flux inversion using satellite observation. With advancements in deep learning algorithms and increased satellite observations, this method may become an effective approach for CO2 flux inversion in the future.<\/jats:p>","DOI":"10.3390\/rs16193694","type":"journal-article","created":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T03:26:36Z","timestamp":1728012396000},"page":"3694","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A New Method for Top-Down Inversion Estimation of Carbon Dioxide Flux Based on Deep Learning"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1994-5880","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing 100871, China"},{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400044, China"}]},{"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"Yubei District Meteorological Office of Chongqing, Chongqing 401120, China"}]},{"given":"Ruilin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400044, China"}]},{"given":"Xiaoyu","family":"Hu","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400044, China"}]},{"given":"Leyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400044, China"}]},{"given":"Lang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400044, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"ref_1","unstructured":"IPCC (2014). Climate Change 2014: Synthesis Report, Cambridge University Press."},{"key":"ref_2","unstructured":"UNFCCC (2015). Adoption of the Paris Agreement, United Nations Framework Convention on Climate Change; UN. Available online: https:\/\/unfccc.int\/resource\/docs\/2015\/cop21\/eng\/l09r01.pdf."},{"key":"ref_3","unstructured":"IPCC (2021). Climate Change 2021: The Physical Science Basis, Cambridge University Press."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e2218563120","DOI":"10.1073\/pnas.2218563120","article-title":"Knowledge gaps are making it harder to formulate national climate policies","volume":"120","author":"Feng","year":"2023","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1038\/nature14677","article-title":"Reduced carbon emission estimates from fossil fuel combustion and cement production in China","volume":"524","author":"Liu","year":"2015","journal-title":"Nature"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1038\/nclimate2963","article-title":"Uncertainties around reductions in China\u2019s coal use and CO2 emissions","volume":"6","author":"Korsbakken","year":"2016","journal-title":"Nat. Clim. Chang."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1007\/s11430-021-9892-6","article-title":"Estimation of China\u2019s terrestrial ecosystem carbon sink: Methods, progress and prospects","volume":"65","author":"Piao","year":"2022","journal-title":"Sci. China Earth Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1038\/s41586-020-2849-9","article-title":"Large Chinese land carbon sink estimated from atmospheric carbon dioxide data","volume":"586","author":"Wang","year":"2020","journal-title":"Nature"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"805","DOI":"10.5194\/gmd-8-805-2015","article-title":"A global carbon assimilation system using a modified ensemble Kalman filter","volume":"8","author":"Zhang","year":"2015","journal-title":"Geosci. Model Dev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.5194\/acp-21-1963-2021","article-title":"Regional CO2 fluxes from 2010 to 2015 inferred from GOSAT XCO2 retrievals using a new version of the Global Carbon Assimilation System","volume":"21","author":"Jiang","year":"2021","journal-title":"Atmos. Chem. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1007\/s11434-014-0238-1","article-title":"The Chinese carbon cycle data-assimilation system (Tan-Tracker)","volume":"59","author":"Tian","year":"2014","journal-title":"Chin. Sci. Bull."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.5194\/gmd-9-2999-2016","article-title":"Constraining a land-surface model with multiple observations by application of the MPI-Carbon Cycle Data Assimilation System V1.0","volume":"9","author":"Kaminski","year":"2016","journal-title":"Geosci. Model Dev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3500","DOI":"10.1002\/2013JD021297","article-title":"Net terrestrial CO2 exchange over China during 2001\u20132010 estimated with an ensemble data assimilation system for atmospheric CO2","volume":"119","author":"Zhang","year":"2014","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2785","DOI":"10.5194\/gmd-10-2785-2017","article-title":"The CarbonTracker Data Assimilation Shell (CTDAS) v1.0: Implementation and global carbon balance 2001\u20132015","volume":"10","author":"Luijkx","year":"2017","journal-title":"Geosci. Model Dev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1111\/j.1365-2486.2009.02078.x","article-title":"Seven years of recent European net terrestrial carbon dioxide exchange constrained by atmospheric observations","volume":"16","author":"Peters","year":"2010","journal-title":"Glob. Chang. Biol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"18925","DOI":"10.1073\/pnas.0708986104","article-title":"An atmospheric perspective on North American carbon dioxide exchange: CarbonTracker","volume":"104","author":"Peters","year":"2007","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"D24304","DOI":"10.1029\/2005JD006157","article-title":"An ensemble data assimilation system to estimate CO2 surface fluxes from atmospheric trace gas observations","volume":"110","author":"Peters","year":"2005","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"D16306","DOI":"10.1029\/2010JD015366","article-title":"Assessing the impact of satellite, aircraft, and surface observations on CO2 flux estimation using an ensemble-based 4-D data assimilation system","volume":"116","author":"Miyazaki","year":"2011","journal-title":"J. Geophys. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"10769","DOI":"10.5194\/acp-22-10769-2022","article-title":"Global and regional carbon budget for 2015\u20132020 inferred from OCO-2 based on an ensemble Kalman filter coupled with GEOS-Chem","volume":"22","author":"Kong","year":"2022","journal-title":"Atmos. Chem. Phys."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lin, X., Ma, J., Chen, H., Shen, F., Ahmad, S., and Li, Z. (2022). Carbon Emissions Estimation and Spatiotemporal Analysis of China at City Level Based on Multi-Dimensional Data and Machine Learning. Remote Sens., 14.","DOI":"10.3390\/rs14133014"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Cai, Q., and Zhu, L. (2024). Calculation of CO2 Emissions from China at Regional Scales Using Remote Sensing Data. Remote Sens., 16.","DOI":"10.3390\/rs16030544"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"159588","DOI":"10.1016\/j.scitotenv.2022.159588","article-title":"Mapping contiguous XCO2 by machine learning and analyzing the spatio-temporal variation in China from 2003 to 2019","volume":"858","author":"Zhang","year":"2023","journal-title":"Sci. Total Environ."},{"key":"ref_23","first-page":"103063","article-title":"Deriving gapless CO2 concentrations using a geographically weighted neural network: China, 2014\u20132020","volume":"114","author":"Zhang","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hua, Y., Zhao, X., Sun, W., and Sun, Q. (2024). Satellite-Based Reconstruction of Atmospheric CO2 Concentration over China Using a Hybrid CNN and Spatiotemporal Kriging Model. Remote Sensing, 16.","DOI":"10.3390\/rs16132433"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4641","DOI":"10.5194\/gmd-14-4641-2021","article-title":"Exploring deep learning for air pollutant emission estimation","volume":"14","author":"Huang","year":"2021","journal-title":"Geosci. Model Dev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.atmosenv.2019.02.002","article-title":"Neural network predictions of pollutant emissions from open burning of crop residues: Application to air quality forecasts in southern China","volume":"204","author":"Feng","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"161951","DOI":"10.1016\/j.scitotenv.2023.161951","article-title":"Development of an integrated machine-learning and data assimilation framework for NOx emission inversion","volume":"871","author":"Chen","year":"2023","journal-title":"Sci. Total Environ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"23073","DOI":"10.1029\/2001JD000807","article-title":"Global Modeling of Tropospheric Chemistry with Assimilated Meteorology: Model Description and Evaluation","volume":"106","author":"Bey","year":"2001","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6029","DOI":"10.5194\/acp-11-6029-2011","article-title":"Inverse modeling of CO2 sources and sinks using satellite observations of CO2 from TES and surface flask measurements","volume":"11","author":"Nassar","year":"2011","journal-title":"Atmos. Chem. Phys."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"543","DOI":"10.5194\/acp-11-543-2011","article-title":"A very high-resolution (1 km\u00d71 km) global fossil fuel CO2 emission inventory derived using a point source database and satellite observations of nighttime lights","volume":"11","author":"Oda","year":"2011","journal-title":"Atmos. Chem. Phys."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"87","DOI":"10.5194\/essd-10-87-2018","article-title":"The Open-source Data Inventory for Anthropogenic CO2, version 2016 (ODIAC2016): A global monthly fossil fuel CO2 gridded emissions data product for tracer transport simulations and surface flux inversions","volume":"10","author":"Oda","year":"2018","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1029\/2012JD018196","article-title":"Improving the temporal and spatial distribution of CO2 emissions from global fossil fuel emission data sets","volume":"118","author":"Nassar","year":"2013","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"697","DOI":"10.5194\/essd-9-697-2017","article-title":"Global fire emissions estimates during 1997\u20132016","volume":"9","author":"Randerson","year":"2017","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"969","DOI":"10.5194\/acp-20-969-2020","article-title":"Six global biomass burning emission datasets: Intercomparison and application in one global aerosol model","volume":"20","author":"Pan","year":"2020","journal-title":"Atmos. Chem. Phys."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s10872-020-00571-5","article-title":"Global trends of ocean CO2 sink and ocean acidification: An observation-based reconstruction of surface ocean inorganic carbon variables","volume":"77","author":"Iida","year":"2021","journal-title":"J. Oceanogr."},{"key":"ref_36","unstructured":"Ott, L. (2022). GEOS-Carb CASA-GFED 3-Hourly Ecosystem Exchange Fluxes 0.5 Degree x 0.625 Degree V3."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"13267","DOI":"10.5194\/acp-19-13267-2019","article-title":"Prior biosphere model impact on global terrestrial CO2 fluxes estimated from OCO-2 retrievals","volume":"19","author":"Philip","year":"2019","journal-title":"Atmos. Chem. Phys."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"15817","DOI":"10.5194\/acp-22-15817-2022","article-title":"Optimizing 4 years of CO2 biospheric fluxes from OCO-2 and in situ data in TM5: Fire emissions from GFED and inferred from MOPITT CO data","volume":"22","author":"Peiro","year":"2022","journal-title":"Atmos. Chem. Phys."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"D05305","DOI":"10.1029\/2006JD008336","article-title":"Orbiting Carbon Observatory: Inverse method and prospective error analysis","volume":"113","author":"Connor","year":"2008","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1016\/j.asr.2003.08.062","article-title":"The Orbiting Carbon Observatory (OCO) mission","volume":"34","author":"Crisp","year":"2004","journal-title":"Adv. Space Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"11400","DOI":"10.1002\/2016GL070885","article-title":"Direct space-based observations of anthropogenic CO2 emission areas from OCO-2","volume":"43","author":"Hakkarainen","year":"2016","journal-title":"Geophys. Res. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1007\/s13131-021-1844-9","article-title":"Comparisons of OCO-2 satellite derived XCO2 with in situ and modeled data over global ocean","volume":"40","author":"Zhang","year":"2021","journal-title":"Acta Oceanol. Sin."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3172371","article-title":"Retrieval of Global Carbon Dioxide From TanSat Satellite and Comprehensive Validation With TCCON Measurements and Satellite Observations","volume":"60","author":"Hong","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"D24309","DOI":"10.1029\/2005JD006390","article-title":"Inferring CO2 sources and sinks from satellite observations: Method and application to TOVS data","volume":"110","author":"Chevallier","year":"2005","journal-title":"J. Geophys. Res."},{"key":"ref_45","unstructured":"Jacobson, A.R., Schuldt, K.N., Tans, P., Arlyn, A., Miller, J.B., Oda, T., Mund, J., Weir, B., Ott, L., and Aalto, T. (2023). CarbonTracker CT2022, NOAA Global Monitoring Laboratory."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1007\/s11430-022-1036-7","article-title":"Constraint of satellite CO2 retrieval on the global carbon cycle from a Chinese atmospheric inversion system","volume":"66","author":"Jin","year":"2023","journal-title":"Sci. China Earth Sci."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"14233","DOI":"10.5194\/acp-19-14233-2019","article-title":"Objective evaluation of surface- and satellite-driven carbon dioxide atmospheric inversions","volume":"19","author":"Chevallier","year":"2019","journal-title":"Atmos. Chem. Phys."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/19\/3694\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:10:13Z","timestamp":1760112613000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/19\/3694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"references-count":48,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["rs16193694"],"URL":"https:\/\/doi.org\/10.3390\/rs16193694","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,10,3]]}}}