Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes

The “top-down” global stocktake (GST) requires the processing of vast volumes of hyperspectral data to derive emission information, placing greater demands on data processing efficiency. Deep learning, leveraging its strengths in the automated and rapid analysis of image datasets, holds significant...

Full description

Saved in:
Bibliographic Details
Main Authors: Erchang Sun, Shichao Wu, Xianhua Wang, Hanhan Ye, Hailiang Shi, Yuan An, Chao Li
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1167
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769683289374720
author Erchang Sun
Shichao Wu
Xianhua Wang
Hanhan Ye
Hailiang Shi
Yuan An
Chao Li
author_facet Erchang Sun
Shichao Wu
Xianhua Wang
Hanhan Ye
Hailiang Shi
Yuan An
Chao Li
author_sort Erchang Sun
collection DOAJ
description The “top-down” global stocktake (GST) requires the processing of vast volumes of hyperspectral data to derive emission information, placing greater demands on data processing efficiency. Deep learning, leveraging its strengths in the automated and rapid analysis of image datasets, holds significant potential to enhance the efficiency and effectiveness of data processing in the GST. This paper develops a method for detecting carbon dioxide (CO<sub>2</sub>) emission hotspots using a convolutional neural network (CNN) with short-lived and co-emitted nitrogen dioxide (NO<sub>2</sub>) as a proxy. To address the data gaps in model parameter training, we constructed a dataset comprising over 210,000 samples of NO<sub>2</sub> plumes and emissions based on atmospheric dispersion models. The trained model performed well on the test set, with most samples achieving an identification accuracy above 80% and more than half exceeding 94%. The trained model was also applied to the NO<sub>2</sub> column data from the TROPOspheric Monitoring Instrument (TROPOMI) for hotspot detection, and the detections were compared with the MEIC inventory. The results demonstrate that in high-emission areas, the proposed method successfully identifies emission hotspots with an average accuracy of over 80%, showing a high degree of consistency with the emission inventory. In areas with multiple observations from TROPOMI, we observed a high degree of consistency between high NO<sub>2</sub> emission areas and high CO<sub>2</sub> emission areas from the Global Open-Source Data Inventory for Anthropogenic CO<sub>2</sub> (ODIAC), indicating that high NO<sub>2</sub> emission hotspots can also indicate CO<sub>2</sub> emission hotspots. In the future, as hyperspectral and high spatial resolution remote sensing data for CO<sub>2</sub> and NO<sub>2</sub> continue to grow, our methods will play an increasingly important role in global data preprocessing and global emission estimation.
format Article
id doaj-art-e842aefcc63d4f069c526ea7c56176d6
institution DOAJ
issn 2072-4292
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e842aefcc63d4f069c526ea7c56176d62025-08-20T03:03:20ZengMDPI AGRemote Sensing2072-42922025-03-01177116710.3390/rs17071167Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> PlumesErchang Sun0Shichao Wu1Xianhua Wang2Hanhan Ye3Hailiang Shi4Yuan An5Chao Li6Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAnhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAnhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAnhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAnhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAnhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaScience Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, ChinaThe “top-down” global stocktake (GST) requires the processing of vast volumes of hyperspectral data to derive emission information, placing greater demands on data processing efficiency. Deep learning, leveraging its strengths in the automated and rapid analysis of image datasets, holds significant potential to enhance the efficiency and effectiveness of data processing in the GST. This paper develops a method for detecting carbon dioxide (CO<sub>2</sub>) emission hotspots using a convolutional neural network (CNN) with short-lived and co-emitted nitrogen dioxide (NO<sub>2</sub>) as a proxy. To address the data gaps in model parameter training, we constructed a dataset comprising over 210,000 samples of NO<sub>2</sub> plumes and emissions based on atmospheric dispersion models. The trained model performed well on the test set, with most samples achieving an identification accuracy above 80% and more than half exceeding 94%. The trained model was also applied to the NO<sub>2</sub> column data from the TROPOspheric Monitoring Instrument (TROPOMI) for hotspot detection, and the detections were compared with the MEIC inventory. The results demonstrate that in high-emission areas, the proposed method successfully identifies emission hotspots with an average accuracy of over 80%, showing a high degree of consistency with the emission inventory. In areas with multiple observations from TROPOMI, we observed a high degree of consistency between high NO<sub>2</sub> emission areas and high CO<sub>2</sub> emission areas from the Global Open-Source Data Inventory for Anthropogenic CO<sub>2</sub> (ODIAC), indicating that high NO<sub>2</sub> emission hotspots can also indicate CO<sub>2</sub> emission hotspots. In the future, as hyperspectral and high spatial resolution remote sensing data for CO<sub>2</sub> and NO<sub>2</sub> continue to grow, our methods will play an increasingly important role in global data preprocessing and global emission estimation.https://www.mdpi.com/2072-4292/17/7/1167CO<sub>2</sub> hotspotsNO<sub>2</sub> plumesglobal stocktakeCNNdeep learning
spellingShingle Erchang Sun
Shichao Wu
Xianhua Wang
Hanhan Ye
Hailiang Shi
Yuan An
Chao Li
Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
Remote Sensing
CO<sub>2</sub> hotspots
NO<sub>2</sub> plumes
global stocktake
CNN
deep learning
title Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
title_full Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
title_fullStr Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
title_full_unstemmed Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
title_short Deep Learning Methods for Inferring Industrial CO<sub>2</sub> Hotspots from Co-Emitted NO<sub>2</sub> Plumes
title_sort deep learning methods for inferring industrial co sub 2 sub hotspots from co emitted no sub 2 sub plumes
topic CO<sub>2</sub> hotspots
NO<sub>2</sub> plumes
global stocktake
CNN
deep learning
url https://www.mdpi.com/2072-4292/17/7/1167
work_keys_str_mv AT erchangsun deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT shichaowu deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT xianhuawang deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT hanhanye deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT hailiangshi deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT yuanan deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes
AT chaoli deeplearningmethodsforinferringindustrialcosub2subhotspotsfromcoemittednosub2subplumes