An Adaptive Segmentation Approach for Contrail Detection in Meteosat Second Generation Satellite Imagery

Santos Gabriel, Vanessa; Bugliaro, Luca; Piontek, Dennis; Ries, Sabrina; Voigt, Christiane

doi:10.5194/egusphere-2025-6275

Preprints

https://doi.org/10.5194/egusphere-2025-6275

Preprints

12 Jan 2026

| 12 Jan 2026

An Adaptive Segmentation Approach for Contrail Detection in Meteosat Second Generation Satellite Imagery

Vanessa Santos Gabriel, Luca Bugliaro, Dennis Piontek, Sabrina Ries, and Christiane Voigt

Abstract. Line-shaped ice clouds known as contrails are produced by aircraft and play a notable role in aviation's contribution to climate change. One promising and cost-effective approach to mitigating this impact is the operational avoidance of contrail formation. To enable the design and evaluation of such mitigation strategies, reliable automated detection of contrails using spaceborne geostationary sensors is essential. In this work, we present a contrail detection algorithm named COCOS (Contrail Confidence Score) for the Meteosat Second Generation (MSG) satellite. Contrail detection with MSG is challenging due to its moderate spatial resolution of 3 km at nadir. COCOS uses a combination of image processing techniques to identify lineshaped contrails. An adaptive thresholding technique as well as a new object separation method and advanced false alarm reduction procedures are implemented. Furthermore, instead of returning just a binary contrail mask as a result, COCOS returns a confidence score to indicate the degree of certainty of each contrail identification. COCOS is evaluated based on a human-labeled dataset. It comprises 140 images of 256 × 256 pixels from 2013 2024, about 60 % of which contain contrails according to human labelers, covering the entire MSG disk with a higher concentration over Europe and the North Atlantic flight corridor. COCOS outperforms the other known contrail detection algorithms in the literature for MSG. At similar recalls (the fraction of true positives correctly identified) it achieves precisions (the fraction of positive predictions that are correct) more than three times higher (0.65 for recall 0.25 and 0.3 for recall 0.5) than other MSG-based contrail detection algorithms, providing a significant improvement in contrail detection for MSG.

Received: 16 Dec 2025 – Discussion started: 12 Jan 2026

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.

Download & links

Preprint (PDF, 1892 KB)

Notice on discussion status
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
Preprint (1892 KB)

Download & links

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Journal article(s) based on this preprint

22 May 2026

An adaptive segmentation approach for contrail detection in meteosat second generation satellite imagery

Vanessa Santos Gabriel, Luca Bugliaro, Dennis Piontek, Sabrina Ries, and Christiane Voigt

Atmos. Meas. Tech., 19, 3271–3289, https://doi.org/10.5194/amt-19-3271-2026,https://doi.org/10.5194/amt-19-3271-2026, 2026

Short summary

Vanessa Santos Gabriel, Luca Bugliaro, Dennis Piontek, Sabrina Ries, and Christiane Voigt

Interactive discussion

Status: closed

RC1:
'Comment on egusphere-2025-6275', Anonymous Referee #1, 13 Jan 2026
This paper introduces a new computer-vision method (COCOS) to automatically recognize contrails in satellite images captured by the MSG SEVIRI instrument. In contrast to many recently introduced methods for the detection of contrails in images, it does not explicitly consist of neural networks. This approach is motivated by the idea that it leads to an interpretable, adaptable detection algorithm that can be adjusted to new satellite instruments in the near-future. The improvement in performance, as evaluated using a dataset consisting of manually annotated satellite images, is considerable when compared to previous methods for contrail detection in MSG SEVIRI images
The paper is certainly within the scope of AMT, it is very well-written and it was an enjoyable read: I have only few line-by-line comments, which are given in a separate section below. I do have some more general comments. Once these are considered by the authors, I think the paper is ready to be published.
My first comment concerns section 2.4 “Contrail Ground Truth” which describes the dataset of annotated MSG images used for developing and evaluating the detection algorithm. After reading this section, I still have many remaining questions:
Broadly speaking, how were labelers instructed to identify contrails? Was this in any way similar to the instructions used by (Meijer et al., 2022) and (Ng et al., 2024)?

How were scenes selected for labeling, and what is the resulting spatio-temporal distribution of annotated scenes?

What information (other than the image itself) was presented to the labelers? For example, both previously mentioned annotated datasets provided labelers with a sequence of images leading up to the relevant image.

For my second comment, I refer to a passage from the introduction:
By avoiding machine learning methods, the authors aim to facilitate the future adaptation of COCOS to the Meteosat Third Generation satellite. Furthermore, we gain a deeper understanding of the factors affecting contrail detection—such as why a contrail is detected or missed, which spectral channels contribute most, and which contrail characteristics are most informative, thereby strengthening the use of COCOS for assessing temporal and spatial contrail distributions, evaluating the effectiveness of mitigation strategies (such as flight rerouting), and improving the representation of aviation-induced clouds in climate models and contrail models.
I find the above motivation to avoid a machine-learning based approach sensible. However, I think that the terminology “avoiding machine learning methods” should be modified slightly, as the COCOS algorithm introduced in the paper still relies on the output of another machine learning approach: CiPS. Secondly, I think that the paper’s contribution to a “Deeper understanding of the factors affecting contrail detection” could be expanded. Although the analysis of the algorithm’s performance (and its dependency on background/contrail properties) is clear, I would be very interested in learning what parts of /tests within the algorithm contribute mostly to the improvement in performance compared to previous MSG SEVIRI algorithms. For example, suppose the CiPS output is a very important input to COCOS: this knowledge could be used in the design of new contrail detection approaches.
Line-by-line comments
Line 26, it may of interest to the authors to also cite (Sonabend-W et al., 2025)

Line 87, “This also ensures that contrail detection remains independent of the time of the day” Would it perhaps be better to state this as “remains possible throughout the day”, since variations in scene properties may still occur throughout the day which could possibly affect contrail detection performance?

Line 89: there seems to be a “8” missing here

Line 116: Missing a space between “contrails” and “(“

Line 222: Note that “gaussian weighted” is spelled differently here than for example line 220

Line 415: Seems like there is an additional space at the start of this sentence.

Figure 8: I would strongly consider replacing the pie charts with other means of visualization. For example, the distribution of “linearity” and “ice optical thickness” could be visualized with CDFs/PDFs.

References
Meijer, V.R., Kulik, L., Eastham, S.D., Allroggen, F., Speth, R.L., Karaman, S., Barrett, S.R.H., 2022. Contrail coverage over the United States before and during the COVID-19 pandemic. Environ. Res. Lett. 17, 034039. https://doi.org/10.1088/1748-9326/ac26f0
Ng, J.Y.-H., McCloskey, K., Cui, J., Meijer, V.R., Brand, E., Sarna, A., Goyal, N., Van Arsdale, C., Geraedts, S., 2024. Contrail Detection on GOES-16 ABI With the OpenContrails Dataset. IEEE Trans. Geosci. Remote Sens. 62, 1–14. https://doi.org/10.1109/TGRS.2023.3345226
Sonabend-W, A., Geraedts, S., Goyal, N., Ng, J.Y.-H., Van Arsdale, C., McCloskey, K., 2025. Observing long-lived longwave contrail forcing. EGUsphere 1–25. https://doi.org/10.5194/egusphere-2025-3739
Citation: https://doi.org/10.5194/egusphere-2025-6275-RC1
- AC1: 'Reply on RC1', Vanessa Santos Gabriel, 17 Apr 2026
  
  We thank Anonymous Referee #1 for their review and time invested in providing feedback. We have carefully considered all point raised and incorporated them in our revised manuscript. Please find attached our point-by-point responses.
  
  Citation: https://doi.org/10.5194/egusphere-2025-6275-AC1
RC2:
'Comment on egusphere-2025-6275', Andrew Heymsfield, 05 Apr 2026

I read carefully through this interesting article. I have some suggestions.
1. Contrails form at temperatures below about -40C, unless there are some extenuating circumstances. "Hole Punch Clouds". I suggest using temperature as another way of checking your results.
2. It would be interesting to use ERA5 relative humidity/temperature data to see how well those fit with your analysis
3. EarthCare lidar data will be helpful in the future to further quantify how well your method fits the observations. You did use the CALIOP data in quantifying your results and the EarthCare lidar data can be used in the future.

Citation: https://doi.org/10.5194/egusphere-2025-6275-RC2
- AC2: 'Reply on RC2', Vanessa Santos Gabriel, 17 Apr 2026
  
  We thank Andrew Heymsfield for his comprehensive review of our manuscript. We have carefully considered all points raised and revised our manuscript. Please find attached our point-by-point responses.
  
  Citation: https://doi.org/10.5194/egusphere-2025-6275-AC2

Interactive discussion

Status: closed

RC1:
'Comment on egusphere-2025-6275', Anonymous Referee #1, 13 Jan 2026
This paper introduces a new computer-vision method (COCOS) to automatically recognize contrails in satellite images captured by the MSG SEVIRI instrument. In contrast to many recently introduced methods for the detection of contrails in images, it does not explicitly consist of neural networks. This approach is motivated by the idea that it leads to an interpretable, adaptable detection algorithm that can be adjusted to new satellite instruments in the near-future. The improvement in performance, as evaluated using a dataset consisting of manually annotated satellite images, is considerable when compared to previous methods for contrail detection in MSG SEVIRI images
The paper is certainly within the scope of AMT, it is very well-written and it was an enjoyable read: I have only few line-by-line comments, which are given in a separate section below. I do have some more general comments. Once these are considered by the authors, I think the paper is ready to be published.
My first comment concerns section 2.4 “Contrail Ground Truth” which describes the dataset of annotated MSG images used for developing and evaluating the detection algorithm. After reading this section, I still have many remaining questions:
Broadly speaking, how were labelers instructed to identify contrails? Was this in any way similar to the instructions used by (Meijer et al., 2022) and (Ng et al., 2024)?

How were scenes selected for labeling, and what is the resulting spatio-temporal distribution of annotated scenes?

What information (other than the image itself) was presented to the labelers? For example, both previously mentioned annotated datasets provided labelers with a sequence of images leading up to the relevant image.

For my second comment, I refer to a passage from the introduction:
By avoiding machine learning methods, the authors aim to facilitate the future adaptation of COCOS to the Meteosat Third Generation satellite. Furthermore, we gain a deeper understanding of the factors affecting contrail detection—such as why a contrail is detected or missed, which spectral channels contribute most, and which contrail characteristics are most informative, thereby strengthening the use of COCOS for assessing temporal and spatial contrail distributions, evaluating the effectiveness of mitigation strategies (such as flight rerouting), and improving the representation of aviation-induced clouds in climate models and contrail models.
I find the above motivation to avoid a machine-learning based approach sensible. However, I think that the terminology “avoiding machine learning methods” should be modified slightly, as the COCOS algorithm introduced in the paper still relies on the output of another machine learning approach: CiPS. Secondly, I think that the paper’s contribution to a “Deeper understanding of the factors affecting contrail detection” could be expanded. Although the analysis of the algorithm’s performance (and its dependency on background/contrail properties) is clear, I would be very interested in learning what parts of /tests within the algorithm contribute mostly to the improvement in performance compared to previous MSG SEVIRI algorithms. For example, suppose the CiPS output is a very important input to COCOS: this knowledge could be used in the design of new contrail detection approaches.
Line-by-line comments
Line 26, it may of interest to the authors to also cite (Sonabend-W et al., 2025)

Line 87, “This also ensures that contrail detection remains independent of the time of the day” Would it perhaps be better to state this as “remains possible throughout the day”, since variations in scene properties may still occur throughout the day which could possibly affect contrail detection performance?

Line 89: there seems to be a “8” missing here

Line 116: Missing a space between “contrails” and “(“

Line 222: Note that “gaussian weighted” is spelled differently here than for example line 220

Line 415: Seems like there is an additional space at the start of this sentence.

Figure 8: I would strongly consider replacing the pie charts with other means of visualization. For example, the distribution of “linearity” and “ice optical thickness” could be visualized with CDFs/PDFs.

References
Meijer, V.R., Kulik, L., Eastham, S.D., Allroggen, F., Speth, R.L., Karaman, S., Barrett, S.R.H., 2022. Contrail coverage over the United States before and during the COVID-19 pandemic. Environ. Res. Lett. 17, 034039. https://doi.org/10.1088/1748-9326/ac26f0
Ng, J.Y.-H., McCloskey, K., Cui, J., Meijer, V.R., Brand, E., Sarna, A., Goyal, N., Van Arsdale, C., Geraedts, S., 2024. Contrail Detection on GOES-16 ABI With the OpenContrails Dataset. IEEE Trans. Geosci. Remote Sens. 62, 1–14. https://doi.org/10.1109/TGRS.2023.3345226
Sonabend-W, A., Geraedts, S., Goyal, N., Ng, J.Y.-H., Van Arsdale, C., McCloskey, K., 2025. Observing long-lived longwave contrail forcing. EGUsphere 1–25. https://doi.org/10.5194/egusphere-2025-3739
Citation: https://doi.org/10.5194/egusphere-2025-6275-RC1
- AC1: 'Reply on RC1', Vanessa Santos Gabriel, 17 Apr 2026
  
  We thank Anonymous Referee #1 for their review and time invested in providing feedback. We have carefully considered all point raised and incorporated them in our revised manuscript. Please find attached our point-by-point responses.
  
  Citation: https://doi.org/10.5194/egusphere-2025-6275-AC1
RC2:
'Comment on egusphere-2025-6275', Andrew Heymsfield, 05 Apr 2026

I read carefully through this interesting article. I have some suggestions.
1. Contrails form at temperatures below about -40C, unless there are some extenuating circumstances. "Hole Punch Clouds". I suggest using temperature as another way of checking your results.
2. It would be interesting to use ERA5 relative humidity/temperature data to see how well those fit with your analysis
3. EarthCare lidar data will be helpful in the future to further quantify how well your method fits the observations. You did use the CALIOP data in quantifying your results and the EarthCare lidar data can be used in the future.

Citation: https://doi.org/10.5194/egusphere-2025-6275-RC2
- AC2: 'Reply on RC2', Vanessa Santos Gabriel, 17 Apr 2026
  
  We thank Andrew Heymsfield for his comprehensive review of our manuscript. We have carefully considered all points raised and revised our manuscript. Please find attached our point-by-point responses.
  
  Citation: https://doi.org/10.5194/egusphere-2025-6275-AC2

Peer review completion

AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload

AR by Vanessa Santos Gabriel on behalf of the Authors (17 Apr 2026) Author's response Author's tracked changes Manuscript

ED: Referee Nomination & Report Request started (17 Apr 2026) by Andrew Sayer

RR by Anonymous Referee #2 (11 May 2026)

ED: Publish subject to technical corrections (11 May 2026) by Andrew Sayer

Dear authors,

Thank you for your revised submission. Based upon the evaluation of one of the initial referees, and my own review, I am happy to accept this version of the study for publication in AMT. Please note this note from the production office and make edits if necessary when uploading your final files:

"Your figures 1, 3, 5 contain maps. To clarify whether a copyright statement or a credit must be given in the map itself or in the caption, we differentiate between (a) maps entirely created by you, (b) maps created by you but based on layers reused from other originators, or (c) maps simply reused from other originators.

An example for (a) is a digital elevation model (DEM) purely based on measurement points collected by you and derived by using a software product. If you use an existing map layer from another originator as a basis for significantly enriching the map with your own content, this would be an example for case (b). Case (c) could be a pure reproduction of Google Maps where your own contribution is rather small (e.g. a city map where you only added a few marks for your study locations).

If the map was entirely created by you (case a), there is no need to change the caption or map. Please simply inform us.

To the contrary, if your map follows cases (b) or (c), please let us know whether the map is distributed under public domain. If yes, please do not include a copyright statement (copyright is waived) but consider adding a credit to the map or caption.

However, if your map follows cases (b) or (c) and is not distributed under public domain, please include at least a credit or even a copyright statement, if this is required by the map provider, in the map itself or in the caption.

For further information please see our website: https://publications.copernicus.org/for_authors/manuscript_preparation.html#mapsaerials
"

Best wishes,

Andrew

Hide

AR by Vanessa Santos Gabriel on behalf of the Authors (13 May 2026) Manuscript

Journal article(s) based on this preprint

22 May 2026

An adaptive segmentation approach for contrail detection in meteosat second generation satellite imagery

Vanessa Santos Gabriel, Luca Bugliaro, Dennis Piontek, Sabrina Ries, and Christiane Voigt

Atmos. Meas. Tech., 19, 3271–3289, https://doi.org/10.5194/amt-19-3271-2026,https://doi.org/10.5194/amt-19-3271-2026, 2026

Short summary

Vanessa Santos Gabriel, Luca Bugliaro, Dennis Piontek, Sabrina Ries, and Christiane Voigt

Viewed

Total article views: 2,752 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
1,559	1,095	98	2,752	94	102

HTML: 1,559
PDF: 1,095
XML: 98
Total: 2,752
BibTeX: 94
EndNote: 102

Views and downloads (calculated since 12 Jan 2026)

Month	HTML	PDF	XML	Total
Jan 2026	757	386	54	1,197
Feb 2026	255	292	13	560
Mar 2026	395	321	16	732
Apr 2026	131	68	12	211
May 2026	21	28	3	52

Cumulative views and downloads (calculated since 12 Jan 2026)

Month	HTML	PDF	XML	Total
Jan 2026	757	386	54	1,197
Feb 2026	255	292	13	560
Mar 2026	395	321	16	732
Apr 2026	131	68	12	211
May 2026	21	28	3	52

Viewed (geographical distribution)

Total article views: 2,717 (including HTML, PDF, and XML) Thereof 2,717 with geography defined and 0 with unknown origin.

Country	#	Views	%

Latest update: 23 May 2026

Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Preprint (1892 KB)
Metadata XML

Short summary

We present a new contrail detection algorithm for the geostationary Meteosat satellite, which outperforms other algorithms for this satellite. Contrails influence the climate but are hard to identify in geostationary satellite imagery with moderate spatial resolution. With this study, we enable the design and evaluation of contrail mitigation strategies, contributing to ongoing efforts in understanding, monitoring, and reducing the climate impact of aviation-induced cirrus.


Total:	0
HTML:	0
PDF:	0
XML:	0

An Adaptive Segmentation Approach for Contrail Detection in Meteosat Second Generation Satellite Imagery

Journal article(s) based on this preprint

Interactive discussion

Interactive discussion

Peer review completion

Suggestions for revision or reasons for rejection

Journal article(s) based on this preprint

Viewed

Viewed (geographical distribution)