基于人工智能与大数据的双碳大气环境信息化应用进展与展望

doi:10.11871/jfdc.issn.2096-742X.2023.03.001

数据与计算发展前沿 ›› 2023, Vol. 5 ›› Issue (3): 2-12.

CSTR: 32002.14.jfdc.CN10-1649/TP.2023.03.001

doi: 10.11871/jfdc.issn.2096-742X.2023.03.001

• 专刊：“人工智能&大数据”科研范式变革专刊（下） • 上一篇下一篇

基于人工智能与大数据的双碳大气环境信息化应用进展与展望

朱明明^1,^2#(),曹无敌^1#(),吴林^1,^*(),王自溪^1,²,廖琦³,张思^1,²,唐晓¹,李杰¹,王婧⁴,王彦棡⁴,王自发^1,^2,^5,^*()

1.中国科学院大气物理研究所，北京 100029
2.中国科学院大学，北京 100049
3.成都信息工程大学，四川成都 610225
4.中国科学院计算机网络信息中心，北京 100083
5.中国科学院城市环境研究所，福建厦门 361021

收稿日期:2023-05-10 出版日期:2023-06-20 发布日期:2023-06-21
通讯作者: *吴林（E-mail: wlin@mail.iap.ac.cn）；王自发（E-mail: zifawang@mail.iap.ac.cn）
作者简介:朱明明，中国科学院大气物理研究所，博士研究生，主要研究方向为基于人工智能的大气系统模式数据融合及应用。
本文主要承担工作为数值模式分析科研范式与人工智能及大数据科研范式下的双碳大气环境研究分析。
ZHU Mingming is a Ph.D. student at the Institute of Atmo-spheric Physics, Chinese Academy of Sciences. His main research interests include AI-based model-data fusion with atmos-pheric systems and its applications.
In this paper, he is mainly responsible for the research and analysis of dual carbon atmospheric environment based on research paradigms of numerical model analysis and artificial intelligence and big data.
E-mail: zhumingming@mail.iap.ac.cn|曹无敌，中国科学院大气物理研究所，硕士，科研助理，主要研究方向为城市碳反演与清单大数据技术。
本文主要承担工作为大数据背景下的碳反演与清单信息化编制以及信息化平台架构研究。
CAO Wudi is a research assistant at the Institute of Atmospheric Physics, Chinese Academy of Scie-nces. His main research interests include urban carbon inversion and big data technology for carbon inventory compilation.
In this paper, he is mainly responsible for the research on in-version and informatization compilation of carbon inventory and architecture of the informatization platform under the back-ground of big data.
E-mail: wd.cao@outlook.com|吴林，中国科学院大气物理研究所，正研级高工，博士生导师，碳中和研究中心副主任，主要研究方向为大气污染资料同化、碳反演、人工智能与大数据在双碳大气环境中的应用等。
本文主要承担工作为数值模式分析科研范式与人工智能及大数据科研范式下双碳大气环境研究进展总结与展望等。
WU Lin, professor, doctoral supervisor, and deputy director of the Carbon Neutrality Research Center, Institute of Atmos-pheric Physics, Chinese Academy of Sciences. His research interests include air pollution data assimilation, carbon inver-sion, applications of artificial intelligence, and big data in dual carbon atmospheric environment.
In this paper, he is mainly responsible for the research pro-gress summary and prospects of dual carbon atmospheric environment based on research paradigms of numerical model analysis and artificial intelligence and big data.
E-mail: wlin@mail.iap.ac.cn|王自发，中国科学院大气物理研究所，研究员，博士生导师，大气边界层物理和大气化学国家重点实验室主任，主要研究方向为大气污染输送和沉降、大气化学模式研发、空气质量预报理论与方法。
本文主要承担工作为数值模式分析科研范式与人工智能及大数据科研范式下大气环境模式研究发展总结与展望。
WANG Zifa, professor, doctoral supervisor, and Director of the State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences. His research interests include atmospheric pollution transport and sedimentation, atmospheric chemical model development, and air quality forecasting theory and method.
In this paper, he is mainly responsible for the research deve-lopment summary and prospects of atmospheric environment simulations based on research paradigms of numerical model analysis and artificial intelligence and big data.
E-mail: zifawang@mail.iap.ac.cn
#共同第一作者：朱明明（E-mail: zhumingming@mail.iap.ac.cn）；曹无敌（E-mail: wd.cao@outlook.com）
基金资助:
中国科学院网信专项应用示范项目(CAS-WX2021SF-0107);中国气象局气象软科学重大项目(2022-ZDAXM06);内蒙古自治区科技重大专项项目(2020ZD0013-03);中国科学院B类百人计划项目

The Development and Prospects of Informatization Applications in Dual-Carbon Atmospheric Environment Based on Artificial Intelligence and Big Data

ZHU Mingming^1,^2#(),CAO Wudi^1#(),WU Lin^1,^*(),WANG Zixi^1,²,LIAO Qi³,ZHANG Si^1,²,TANG Xiao¹,LI Jie¹,WANG Jing⁴,WANG Yangang⁴,WANG Zifa^1,^2,^5,^*()

1. Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Chengdu University of Information Technology, Chengdu, Sichuan 610225, China
4. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
5. Institute of Urban Environment, Chinese Academy of Sciences, Xiamen, Fujian 361021, China

Received:2023-05-10 Online:2023-06-20 Published:2023-06-21

摘要/Abstract

摘要：

【目的】 二氧化碳与大气污染物化石燃料排放同源，在碳达峰碳中和的双碳进程中应协同治理，改善双碳大气环境。大气环境信息化应用主要基于大气化学传输数值模式展开，而双碳大气环境信息化应用还处于起步阶段。近年来，人工智能与大数据技术在双碳大气环境上的应用愈加广泛，蕴育科研范式从数值模式向与人工智能、大数据深度融合变革，因而亟需梳理当前进展并展望未来发展方向与路径。【方法】 通过调研领域工作，勾勒基于人工智能与大数据的双碳大气环境信息化应用的研究路径和发展方向。【结果】 双碳大气环境信息化应用应以人工智能、大数据科技创新实现对大气化学传输模式的融合替代，形成应用体系，实现更高精度、更快速度的数字化治理。【局限】 本文提出的概念与设计，有待于未来的实施与验证。【结论】 人工智能与大数据技术的应用，带来双碳大气环境科研范式变革机遇，同时也提出了挑战。协同推进算法突破与信息化系统研制，有助于实现这一科研范式变革。

关键词: 双碳大气环境, 大气化学传输模式, 人工智能与大数据, 人工智能与数值模式融合, 科研范式转变

Abstract:

[Objective] Emissions of carbon dioxide and air pollutants caused by fossil fuel usage are from similar activities, and thus need synergic governance in the process of “carbon-peak and carbon-neutrality” for a better “dual-carbon” atmospheric environment. Informatization applications in atmospheric environment are principally based on numerical chemistry transport models, whereas in dual-carbon atmospheric environment, such applications are still in their infancy stage. Recently, artificial intelligence and big data techniques have gained increasing popularity in dual-carbon atmospheric environment, which fosters the paradigm shift from numerical model-based research to deep fusion with artificial intelligence and big data techniques. Therefore, there is an urgent need to examine current developments and outline directions and pathways for future research. [Methods] This paper presents a brief review and prospects on the developments, directions, and pathways towards the future informatization applications based on artificial intelligence and big data techniques in dual-carbon atmospheric environment. [Results] It is shown that innovations with artificial intelligence and big data techniques are needed to fusion with or substitute the atmospheric chemistry transport models by emulations and corrections. Systematic applications based on the resulting hybrid models should be put forward so that digital governance of the dual-carbon atmospheric environment could be conducted in finer resolution and higher speed. [Limitations] Our proposed concept and design are to be verified by future implementations and experimentations. [Conclusions] The applications of artificial intelligence and big data techniques enable opportunities for a paradigm shift in dual-carbon atmospheric environment and in the meantime bring challenges. Joint efforts in algorithmic breakthroughs and information system development would help to realize this paradigm shift.

Key words: dual-carbon atmospheric environment, atmospheric chemistry transport model, artificial intelligence and big data, hybridization between artificial intelligence and numerical model, paradigm shift

朱明明, 曹无敌, 吴林, 王自溪, 廖琦, 张思, 唐晓, 李杰, 王婧, 王彦棡, 王自发. 基于人工智能与大数据的双碳大气环境信息化应用进展与展望[J]. 数据与计算发展前沿, 2023, 5(3): 2-12.

ZHU Mingming, CAO Wudi, WU Lin, WANG Zixi, LIAO Qi, ZHANG Si, TANG Xiao, LI Jie, WANG Jing, WANG Yangang, WANG Zifa. The Development and Prospects of Informatization Applications in Dual-Carbon Atmospheric Environment Based on Artificial Intelligence and Big Data[J]. Frontiers of Data and Computing, 2023, 5(3): 2-12, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.03.001.

图/表 2

参考文献 37

[1]	习近平在第七十五届联合国大会一般性辩论上发表重要讲话[N]. 人民日报, 2020-09-23(001).
[2]	郑逸璇, 宋晓晖, 周佳, 等. 减污降碳协同增效的关键路径与政策研究[J]. 中国环境管理, 2021, 13(05):45-51.
[3]	Hasselmann K. Stochastic climate models part I[J]. The-ory. Tellus, 1976, 28(6): 473-485.
[4]	Manabe S, Stouffer R J. Century-scale effects of increased atmospheric CO₂ on the oceanatmosphere system[J]. Nature, 1993. 364(6434): 215-218. doi: 10.1038/364215a0
[5]	Byun Q W, Ching J K. Science algorithms of the EPA Models-3 Community Multiscale Air Quality (CMAQ) modeling system[R]. USA, Environmental Protection Agency, 1999.
[6]	Grell G A, Peckham S E, Schmitz R, et al. Fully coup-led “online” chemistry within the WRF model[J]. Atmos-pheric Environmesnt, 2005, 39:6957-6975.
[7]	Wang Z, Maeda T, Hayashi M, et al. A nested air quality prediction modeling system for urban and regional sca-les: application for highozone episode in Taiwan[J]. Water, Air, and Soil Pollution, 2001, 130:391-396. doi: 10.1023/A:1013833217916
[8]	王自发, 魏颖, 陈学舜, 等. 一个适用于地球系统模式(CAS-ESM)的在线气溶胶与大气化学分量模式(IAP-AACM)的发展与评估[J]. 气候与环境研究, 2020, 25(1): 1-1.
[9]	刘丽, 王体健, 王勤耕. 区域复杂地形大气污染扩散的模拟研究[J]. 高原气象, 2008(5):1074-1082.
[10]	吴剑斌, 王茜, 伏晴艳. 2013年12月上海市PM_2.5重污染过程数值模拟研究[J]. 环境科学学报, 2016, 36(6): 2152-2159.
[11]	皮冬勤, 陈焕盛, 魏巍, 等. 京津冀一次重污染过程的成因和来源[J]. 中国环境科学, 2019, 39(5):1899-1908.
[12]	Candiani G, Carnevale C, Finzi G, et al. A comparison of reanalysis techniques: Ap-plying optimal interpolation and Ensemble Kalman Filtering to improve air quality monitoring at mesoscale[J]. Sci. Total Environ., 458: 7-14.
[13]	Wu L, Mallet V, Bocquet M, et al. A comparison study of data assimilation algorithms for ozone forecasts[J]. Journal of Geophysical Research: Atmospheres, 2008, 113(D20).
[14]	朱江, 唐晓, 王自发, 吴林. 大气污染资料同化与应用综述[J]. 大气科学, 2018, 42(3):607-620.
[15]	王自发. 区域大气污染预报预警与应急控制[C]// 中华环保联合会(All-China Environment Federation)、联合国环境规划署第十届环境与发展论坛论文集.中华环保联合会(All-China Environment Federation)、联合国环境规划署, 2014:7.
[16]	Tang X., Zhu J., Wang Z. F., et al. Inversion of CO emissions over Beijing and its surrounding areas with ensemble Kalman filter[J]. Atmospheric Environment, 2013, 81: 676-686. doi: 10.1016/j.atmosenv.2013.08.051
[17]	Wu L, Broquet G, Ciais P, et al. What would dense atmo-spheric observation networks bring to the quantification of city CO₂ emissions?[J]. Atmospheric Chemistry and Physics, 2016, 16(12): 7743-7771.
[18]	Wang H, Sui W, Tang X, et al. Simulation-based Design of Regional Emission Control Experiments with Simult-aneous Pollution of O₃ and PM_2.5 in Jinan, China[J]. Aerosol and Air Quality Research, 2019, 19(11): 2543-2556. doi: 10.4209/aaqr.2019.03.0125
[19]	Bai L, Wang J, Ma X, et al. Air Pollution Forecasts: An Overview[J]. Int J Environ Res Public Health, 2018, 15 (4):780. doi: 10.3390/ijerph15040780
[20]	Baklanov A, Zhang Y. Advances in air quality modeling and forecasting[J]. Global Transitions: 2020, 2:261-270.
[21]	唐孝炎, 张远航, 邵敏. 大气环境化学-第2版[M]. 北京: 高等教育出版社, 2006:8-9.
[22]	Reichstein M., et al. Deep learning and process under-standing for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204. doi: 10.1038/s41586-019-0912-1
[23]	Ghahramani Z. Probabilistic machine learning and artif-icial intelligence[J]. Nature, 2015, 521: 452-459. doi: 10.1038/nature14541
[24]	Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521:436-444. doi: 10.1038/nature14539
[25]	Bengio Y, Courville A, Vincent P. Representation lear-ning: A review and new perspectives[J]. IEEE transa-ctions on pattern analysis and machine intelligence, 2013, 35(8): 1798-1828.
[26]	Liao Q, Zhu M, Wu L, et al. Deep learning for air quality forecasts: a review[J]. Current Pollution Reports, 2020, 6(4): 399-409. doi: 10.1007/s40726-020-00159-z
[27]	Wang Z, Li J, Wu L, et al. Deep learning-based gas-phase chemical kinetics kernel emulator: Application in a global air quality simulation case[J]. Frontiers in Environmental Science, 2022, 10: 955980. doi: 10.3389/fenvs.2022.955980
[28]	Li X, Peng L, Yao X, et al. Long short-term memory neural network for air pollutant concentration predictions: method development and evalua-tion[J]. Environ Pollut, 2017, 231:997-1004. doi: 10.1016/j.envpol.2017.08.114
[29]	Sayeed A, Lops Y, Choi Y, et al. Bias correcting and ex-tending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks[J]. Atmospheric Environment, 2021, 253:118376. doi: 10.1016/j.atmosenv.2021.118376
[30]	He T L, Jones D, Miyazaki K, et al. Inverse modelling of Chinese NO_x emissions using deep learning: integrating in situ observations with a satellite-based chemical reana-lysis[J]. Atmospheric Chemistry and Physics, 2022, 22 (21): 14059-14074.
[31]	Huang L, Liu S, Yang Z, et al. Exploring deep learning for air pollutant emission estimation[J]. Geoscientific Model Development, 2021, 14(7): 4641-4654. doi: 10.5194/gmd-14-4641-2021
[32]	Brandt M, Tucker C J, Kariryaa A, et al. An unexpectedly large count of trees in the West African Sahara and Sahel[J]. Nature, 2020, 587(7832): 78-82. doi: 10.1038/s41586-020-2824-5
[33]	Dumont Le Brazidec J, Vanderbecken P, Farchi A, et al. Segmentation of XCO₂ images with deep learning: application to synthetic plumes from cities and power plants[J]. Geoscientific Model Development Discussions, [preprint], in review, 2022.
[34]	江峰琴. 美国环境空气质量监测数据管理经验及启示[J]. 环境与发展, 2015(3):40-43.
[35]	Rémy S, Kipling Z, Flemming J, et al. Description and evaluation of the tropospheric aerosol scheme in the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecasting System (IFS-AER, cycle 45R1)[J]. Geoscientific Model Development, 2019, 12(11): 4627-4659. doi: 10.5194/gmd-12-4627-2019
[36]	Bao Y, Wu L, Jiang C, et al. A Cloud-Based Information System of Emission Inventory Compilation for Digital Governance of Urban Air Pollution and Carbon Man-agement[C]// 2021 IEEE 7th International Conference on Control Science and Systems Engineering (ICCSSE), IEEE, 2021: 273-277.
[37]	Ren X, Zhao Y, Wu L, et al. Towards efficient digital governance of city air pollution using technique of big atmospheric environmental data[C]// IOP Conference Series: Earth and Environmental Science, IOP Publishing, 2020, 502(1): 012031.

基于人工智能与大数据的双碳大气环境信息化应用进展与展望

The Development and Prospects of Informatization Applications in Dual-Carbon Atmospheric Environment Based on Artificial Intelligence and Big Data

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 2

参考文献 37

相关文章 0

编辑推荐

Metrics

本文评价