Estimating Contrail Climate Effects from Satellite Data

Minnis, Patrick; Duda, David P.; Palikonda, Rabindra; Bedka, Sarah T.; Boeke, R.; Khlopenkov, K.; Chee, T.; Bedka, Kristopher

doi:10.2514/6.2011-3375

Cited by 4 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Geostationary Operational Environmental Satellite (GOES) Imager Detection Technique was used by Minnis et al (1998), for the detection of persistent contrails and cirrus. Some similar work using other data such as images from NOAA/AVHRR has been accomplished by DeGrand et al (2000), for the 1977-1979 time period and by Travis et al (2006-2002. Minnis et al (2011 used an automated contrail detection algorithm (CDA) using the Moderate Resolution Imaging Spectroradiometer (MODIS) data taken by Terra and Aqua over the United States during 2006-2008.…”

Section: Quantifying Radiative Forcing Efficienciesmentioning

confidence: 99%

Regional climate impact of aerosols emitted by transportation modes and potential effects of policies on demand and emissions

Hivin

Pfaender

Mavris

2015

Transportation Research Part D: Transport and Environment

View full text Add to dashboard Cite

Section: Quantifying Radiative Forcing Efficienciesmentioning

confidence: 99%

Regional climate impact of aerosols emitted by transportation modes and potential effects of policies on demand and emissions

Hivin

Pfaender

Mavris

2015

Transportation Research Part D: Transport and Environment

View full text Add to dashboard Cite

“…Detecting contrails in satellite images is a challenging task because they visually resemble natural cirrus clouds [9,25,23,29,28]. Contrail formations manifest as linear ice clouds that gradually change shape over time, making them difficult to differentiate from their natural cirrus counterparts.…”

Section: Background and Motivationmentioning

confidence: 99%

UPerNet with ConvNeXt for Semantic Segmentation

Wang

Jiang

2023

2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI)

View full text Add to dashboard Cite

Semantic segmentation is a critical tool in computer vision, applied in various domains like autonomous driving and medical imaging. This study focuses on aircraft contrail detection in global satellite images to improve contrail models and mitigate their impact on climate change.An innovative data preprocessing technique for NOAA GOES-16 satellite images is developed, using brightness temperature data from the infrared channel to create false-color images, enhancing model perception. To tackle class imbalance, the training dataset exclusively includes images with positive contrail labels.The model selection is based on the UPerNet architecture, implemented using the MMsegmentation library, with the integration of two ConvNeXt configurations for improved performance. Cross-entropy loss with positive class weights enhances contrail recognition. Fine-tuning employs the AdamW optimizer with a learning rate of 2.5 × 10 −4 .During inference, a multi-model prediction fusion strategy and a contrail determination threshold of 0.75 yield a binary prediction mask. RLE encoding is used for efficient prediction result organization.The approach achieves exceptional results, boasting a high Dice coefficient score, placing it in the top 5% of participating teams. This underscores the innovative nature of the segmentation model and its potential for enhanced contrail recognition in satellite imagery.For further exploration, the code and models are available on GitHub: https://github.com/biluko/2023GRIC.git.

show abstract

“…Condensation trails (also called contrails or vapor trails) are aircraft-generated cirrus clouds that often form in the absence of other cirrus clouds in ice-supersaturated conditions at temperatures less than -39 °C [22]. Since such conditions are relatively common in the upper troposphere, contrails can develop into relatively long-lived cirrus cloud [23].…”

Section: Direct and Diffused Beam Radiationmentioning

confidence: 99%