Contrail altitude estimation using GOES-16 ABI data and deep learning

<p>The climate impact of persistent aircraft contrails is currently estimated to be comparable to that due to aviation-emitted CO<span class="inline-formula"><sub>2</sub></span>. A potential near-term and low-cost mitigation option is contrail avoidance, which...

Full description

Saved in:
Bibliographic Details
Main Authors: V. R. Meijer, S. D. Eastham, I. A. Waitz, S. R. H. Barrett
Format: Article
Language:English
Published: Copernicus Publications 2024-10-01
Series:Atmospheric Measurement Techniques
Online Access:https://amt.copernicus.org/articles/17/6145/2024/amt-17-6145-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209993996894208
author V. R. Meijer
V. R. Meijer
S. D. Eastham
S. D. Eastham
S. D. Eastham
I. A. Waitz
S. R. H. Barrett
S. R. H. Barrett
author_facet V. R. Meijer
V. R. Meijer
S. D. Eastham
S. D. Eastham
S. D. Eastham
I. A. Waitz
S. R. H. Barrett
S. R. H. Barrett
author_sort V. R. Meijer
collection DOAJ
description <p>The climate impact of persistent aircraft contrails is currently estimated to be comparable to that due to aviation-emitted CO<span class="inline-formula"><sub>2</sub></span>. A potential near-term and low-cost mitigation option is contrail avoidance, which involves rerouting aircraft around ice-supersaturated regions, preventing the formation of persistent contrails. Current forecasting methods for these regions of ice supersaturation have been found to be inaccurate when compared to in situ measurements. Further assessment and improvements of the quality of these predictions can be realized by comparison with observations of persistent contrails, such as those found in satellite imagery. In order to further enable comparison between these observations and contrail predictions, we develop a deep learning algorithm to estimate contrail altitudes based on GOES-16 Advanced Baseline Imager (ABI) infrared imagery. This algorithm is trained using a dataset of 3267 contrails found within Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP) data and achieves a root mean square error (RMSE) of 570 m. The altitude estimation algorithm outputs probability distributions for the contrail top altitude in order to represent predictive uncertainty. The 95 % confidence intervals constructed using these distributions, which are shown to contain approximately 95 % of the contrail data points, are found to be 2.2 km thick on average. These intervals are found to be 34.1 % smaller than the 95 % confidence intervals constructed using flight altitude information alone, which are 3.3 km thick on average. Furthermore, we show that the contrail altitude estimates are consistent in time and, in combination with contrail detections, can be used to observe the persistence and three-dimensional (3D) evolution of contrail-forming regions from satellite images alone.</p>
format Article
id doaj-art-e009028e572446c184f2ab29d3e63a98
institution OA Journals
issn 1867-1381
1867-8548
language English
publishDate 2024-10-01
publisher Copernicus Publications
record_format Article
series Atmospheric Measurement Techniques
spelling doaj-art-e009028e572446c184f2ab29d3e63a982025-08-20T02:09:52ZengCopernicus PublicationsAtmospheric Measurement Techniques1867-13811867-85482024-10-011761456162Contrail altitude estimation using GOES-16 ABI data and deep learningV. R. Meijer0V. R. Meijer1S. D. Eastham2S. D. Eastham3S. D. Eastham4I. A. Waitz5S. R. H. Barrett6S. R. H. Barrett7Laboratory for Aviation and the Environment, Massachusetts Institute of Technology, Cambridge, MA, USAnow at: Faculty of Aerospace Engineering, Delft University of Technology, Delft, the NetherlandsLaboratory for Aviation and the Environment, Massachusetts Institute of Technology, Cambridge, MA, USAJoint Program on the Science and Policy of Global Change, Massachusetts Institute of Technology, Cambridge, MA, USAnow at: Brahmal Vasudevan Institute for Sustainable Aviation, Department of Aeronautics, Imperial College London, London, UKLaboratory for Aviation and the Environment, Massachusetts Institute of Technology, Cambridge, MA, USALaboratory for Aviation and the Environment, Massachusetts Institute of Technology, Cambridge, MA, USAnow at: Department of Engineering, University of Cambridge, Cambridge, UK<p>The climate impact of persistent aircraft contrails is currently estimated to be comparable to that due to aviation-emitted CO<span class="inline-formula"><sub>2</sub></span>. A potential near-term and low-cost mitigation option is contrail avoidance, which involves rerouting aircraft around ice-supersaturated regions, preventing the formation of persistent contrails. Current forecasting methods for these regions of ice supersaturation have been found to be inaccurate when compared to in situ measurements. Further assessment and improvements of the quality of these predictions can be realized by comparison with observations of persistent contrails, such as those found in satellite imagery. In order to further enable comparison between these observations and contrail predictions, we develop a deep learning algorithm to estimate contrail altitudes based on GOES-16 Advanced Baseline Imager (ABI) infrared imagery. This algorithm is trained using a dataset of 3267 contrails found within Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP) data and achieves a root mean square error (RMSE) of 570 m. The altitude estimation algorithm outputs probability distributions for the contrail top altitude in order to represent predictive uncertainty. The 95 % confidence intervals constructed using these distributions, which are shown to contain approximately 95 % of the contrail data points, are found to be 2.2 km thick on average. These intervals are found to be 34.1 % smaller than the 95 % confidence intervals constructed using flight altitude information alone, which are 3.3 km thick on average. Furthermore, we show that the contrail altitude estimates are consistent in time and, in combination with contrail detections, can be used to observe the persistence and three-dimensional (3D) evolution of contrail-forming regions from satellite images alone.</p>https://amt.copernicus.org/articles/17/6145/2024/amt-17-6145-2024.pdf
spellingShingle V. R. Meijer
V. R. Meijer
S. D. Eastham
S. D. Eastham
S. D. Eastham
I. A. Waitz
S. R. H. Barrett
S. R. H. Barrett
Contrail altitude estimation using GOES-16 ABI data and deep learning
Atmospheric Measurement Techniques
title Contrail altitude estimation using GOES-16 ABI data and deep learning
title_full Contrail altitude estimation using GOES-16 ABI data and deep learning
title_fullStr Contrail altitude estimation using GOES-16 ABI data and deep learning
title_full_unstemmed Contrail altitude estimation using GOES-16 ABI data and deep learning
title_short Contrail altitude estimation using GOES-16 ABI data and deep learning
title_sort contrail altitude estimation using goes 16 abi data and deep learning
url https://amt.copernicus.org/articles/17/6145/2024/amt-17-6145-2024.pdf
work_keys_str_mv AT vrmeijer contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT vrmeijer contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT sdeastham contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT sdeastham contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT sdeastham contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT iawaitz contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT srhbarrett contrailaltitudeestimationusinggoes16abidataanddeeplearning
AT srhbarrett contrailaltitudeestimationusinggoes16abidataanddeeplearning