| 12 Jan 2026
An Adaptive Segmentation Approach for Contrail Detection in Meteosat Second Generation Satellite Imagery
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.
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:
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
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