Retrieving the atmospheric concentrations of carbon dioxide and methane from the European Copernicus CO2M satellite mission using artificial neural networks

IF 3.2 3区 地球科学 Q2 METEOROLOGY & ATMOSPHERIC SCIENCES
Maximilian Reuter, Michael Hilker, Stefan Noël, Antonio Di Noia, Michael Weimer, Oliver Schneising, Michael Buchwitz, Heinrich Bovensmann, John P. Burrows, Hartmut Bösch, Ruediger Lang
{"title":"Retrieving the atmospheric concentrations of carbon dioxide and methane from the European Copernicus CO2M satellite mission using artificial neural networks","authors":"Maximilian Reuter, Michael Hilker, Stefan Noël, Antonio Di Noia, Michael Weimer, Oliver Schneising, Michael Buchwitz, Heinrich Bovensmann, John P. Burrows, Hartmut Bösch, Ruediger Lang","doi":"10.5194/egusphere-2024-2365","DOIUrl":null,"url":null,"abstract":"<strong>Abstract.</strong> Carbon dioxide (CO<sub>2</sub>) and methane (CH<sub>4</sub>) are the most important anthropogenic greenhouse gases and the main drivers of climate change. Monitoring their concentrations from space helps to detect and quantify anthropogenic emissions, supporting the mitigation efforts urgently needed to meet the primary objective of the United Nations Framework Convention on Climate Change (UNFCCC) Paris Agreement to limit the global average temperature increase to well below 2 °C above pre-industrial levels. In addition, satellite observations can be used to quantify natural sources and sinks improving our understanding of the carbon cycle. Advancing these goals is the motivation for the European Copernicus CO<sub>2</sub> monitoring mission CO2M. The necessary accuracy and precision requirements for the measured quantities XCO2 and XCH4 (the column-averaged dry-air mixing ratios of CO<sub>2</sub> and CH<sub>4</sub>) are demanding. According to the CO2M mission requirements, the spatial and temporal variability of the systematic errors of XCO2 and XCH4 shall not exceed 0.5 ppm and 5 ppb, respectively. The stochastic errors due to instrument noise shall not exceed 0.7 ppm for XCO2 and 10 ppb for XCH4. Conventional so-called full-physics algorithms for retrieving XCO2 and/or XCH4 from satellite-based measurements of reflected solar radiation are typically computationally intensive and still usually require empirical bias corrections based on supervised machine learning methods. Here we present the retrieval algorithm NRG-CO2M (Neural networks for Remote sensing of Greenhouse gases from CO2M), which derives XCO2 and XCH4 from CO2M radiance measurements with minimal computational effort using artificial neural networks (ANNs). Since CO2M will not be launched until 2026, our study is based on simulated measurements over land surfaces from a comprehensive observing system simulation experiment (OSSE). We employ a hybrid learning approach that combines advantages of simulation-based and measurement-based training data to ensure coverage of a wide range of XCO2 and XCH4 values making the training data also representative of future concentrations. The algorithm's postprocessing is designed to achieve a high data yield of about 80 % of all cloud-free soundings. The spatio-temporal systematic errors of XCO2 and XCH4 amount 0.44 ppm and 2.45 ppb, respectively. The average single sounding precision is 0.41 ppm for XCO2 and 2.74 ppb for XCH4. Therefore, the presented retrieval method has the potential to meet the demanding CO2M mission requirements for XCO2 and XCH4.","PeriodicalId":8619,"journal":{"name":"Atmospheric Measurement Techniques","volume":"181 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atmospheric Measurement Techniques","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.5194/egusphere-2024-2365","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Abstract. Carbon dioxide (CO2) and methane (CH4) are the most important anthropogenic greenhouse gases and the main drivers of climate change. Monitoring their concentrations from space helps to detect and quantify anthropogenic emissions, supporting the mitigation efforts urgently needed to meet the primary objective of the United Nations Framework Convention on Climate Change (UNFCCC) Paris Agreement to limit the global average temperature increase to well below 2 °C above pre-industrial levels. In addition, satellite observations can be used to quantify natural sources and sinks improving our understanding of the carbon cycle. Advancing these goals is the motivation for the European Copernicus CO2 monitoring mission CO2M. The necessary accuracy and precision requirements for the measured quantities XCO2 and XCH4 (the column-averaged dry-air mixing ratios of CO2 and CH4) are demanding. According to the CO2M mission requirements, the spatial and temporal variability of the systematic errors of XCO2 and XCH4 shall not exceed 0.5 ppm and 5 ppb, respectively. The stochastic errors due to instrument noise shall not exceed 0.7 ppm for XCO2 and 10 ppb for XCH4. Conventional so-called full-physics algorithms for retrieving XCO2 and/or XCH4 from satellite-based measurements of reflected solar radiation are typically computationally intensive and still usually require empirical bias corrections based on supervised machine learning methods. Here we present the retrieval algorithm NRG-CO2M (Neural networks for Remote sensing of Greenhouse gases from CO2M), which derives XCO2 and XCH4 from CO2M radiance measurements with minimal computational effort using artificial neural networks (ANNs). Since CO2M will not be launched until 2026, our study is based on simulated measurements over land surfaces from a comprehensive observing system simulation experiment (OSSE). We employ a hybrid learning approach that combines advantages of simulation-based and measurement-based training data to ensure coverage of a wide range of XCO2 and XCH4 values making the training data also representative of future concentrations. The algorithm's postprocessing is designed to achieve a high data yield of about 80 % of all cloud-free soundings. The spatio-temporal systematic errors of XCO2 and XCH4 amount 0.44 ppm and 2.45 ppb, respectively. The average single sounding precision is 0.41 ppm for XCO2 and 2.74 ppb for XCH4. Therefore, the presented retrieval method has the potential to meet the demanding CO2M mission requirements for XCO2 and XCH4.
利用人工神经网络从欧洲哥白尼 CO2M 卫星任务中检索大气中二氧化碳和甲烷的浓度
摘要二氧化碳(CO2)和甲烷(CH4)是最重要的人为温室气体,也是气候变化的主要驱动因素。从太空监测这两种气体的浓度有助于探测和量化人为排放,从而为实现《联合国气候变化框架公约》(UNFCCC)《巴黎协定》的首要目标--将全球平均气温升幅限制在远低于工业化前水平 2 ℃--所急需的减缓努力提供支持。此外,卫星观测还可用于量化自然源和汇,从而增进我们对碳循环的了解。推进这些目标是欧洲哥白尼二氧化碳监测任务 CO2M 的动机。测量量 XCO2 和 XCH4(二氧化碳和甲烷的柱平均干空气混合比)所需的准确度和精确度要求很高。根据 CO2M 任务要求,XCO2 和 XCH4 系统误差的空间和时间变化分别不得超过 0.5 ppm 和 5 ppb。仪器噪声造成的随机误差,XCO2 不应超过 0.7 ppm,XCH4 不应超过 10 ppb。从基于卫星的反射太阳辐射测量中检索 XCO2 和/或 XCH4 的传统所谓全物理算法通常需要大量计算,而且通常仍需要基于监督机器学习方法的经验偏差修正。在此,我们介绍检索算法 NRG-CO2M(从 CO2M 遥感温室气体的神经网络),该算法利用人工神经网络(ANN),以最小的计算量从 CO2M 辐射测量值推导出 XCO2 和 XCH4。由于 CO2M 要到 2026 年才会发射,我们的研究基于综合观测系统模拟实验(OSSE)对陆地表面的模拟测量。我们采用了一种混合学习方法,该方法结合了基于模拟和基于测量的训练数据的优势,以确保涵盖广泛的 XCO2 和 XCH4 值,从而使训练数据也能代表未来的浓度。该算法的后处理旨在获得约 80% 的无云探测数据。XCO2 和 XCH4 的时空系统误差分别为 0.44 ppm 和 2.45 ppb。XCO2 和 XCH4 的平均单次探测精度分别为 0.41 ppm 和 2.74 ppb。因此,提出的检索方法有可能满足 CO2M 任务对 XCO2 和 XCH4 的苛刻要求。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Atmospheric Measurement Techniques
Atmospheric Measurement Techniques METEOROLOGY & ATMOSPHERIC SCIENCES-
CiteScore
7.10
自引率
18.40%
发文量
331
审稿时长
3 months
期刊介绍: Atmospheric Measurement Techniques (AMT) is an international scientific journal dedicated to the publication and discussion of advances in remote sensing, in-situ and laboratory measurement techniques for the constituents and properties of the Earth’s atmosphere. The main subject areas comprise the development, intercomparison and validation of measurement instruments and techniques of data processing and information retrieval for gases, aerosols, and clouds. The manuscript types considered for peer-reviewed publication are research articles, review articles, and commentaries.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信