Linear Contrails Detection, Tracking and Matching with Aircraft Using Geostationary Satellite and Air Traffic Data

Chevallier, Raymond; Shapiro, Marc; Engberg, Zebediah; Soler, Manuel; Delahaye, Daniel

doi:10.3390/aerospace10070578

Cited by 11 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning techniques like instance segmentation are explored for efficient detection. Integration of multiple observation methods and identification of contrail-producing aircraft contribute to advancing contrail research for climate validation and modeling improvement [ 21 ]. Recently, there has been a significant increase in research efforts to improve image segmentation methods by using deep learning techniques.…”

Section: Related Workmentioning

confidence: 99%

SegX-Net: A novel image segmentation approach for contrail detection using deep learning

Nobel,

Hossain,

Kabir

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Contrails are line-shaped clouds formed in the exhaust of aircraft engines that significantly contribute to global warming. This paper confidently proposes integrating advanced image segmentation techniques to identify and monitor aircraft contrails to address the challenges associated with climate change. We propose the SegX-Net architecture, a highly efficient and lightweight model that combines the DeepLabV3+, upgraded, and ResNet-101 architectures to achieve superior segmentation accuracy. We evaluated the performance of our model on a comprehensive dataset from Google research and rigorously measured its efficacy with metrics such as IoU, F1 score, Sensitivity and Dice Coefficient. Our results demonstrate that our enhancements have significantly improved the efficacy of the SegX-Net model, with an outstanding IoU score of 98.86% and an impressive F1 score of 99.47%. These results unequivocally demonstrate the potential of image segmentation methods to effectively address and mitigate the impact of air conflict on global warming. Using our proposed SegX-Net architecture, stakeholders in the aviation industry can confidently monitor and mitigate the impact of aircraft shrinkage on the environment, significantly contributing to the global fight against climate change.

show abstract

Section: Related Workmentioning

confidence: 99%

SegX-Net: A novel image segmentation approach for contrail detection using deep learning

Nobel,

Hossain,

Kabir

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Using the advected flightpaths to identify potential aircraft-modified clouds (e.g. Tesche et al 2016, Duda et al 2019, Marjani et al 2022, Chevallier et al 2023 avoids the requirement for tracking COs and potential selection biases associated with the filtering and tracking processes. Although the CNN produces a considerable number of false positives (figure 3(a)), these are significantly reduced over the ocean.…”

Section: Fleet-wide Contrailsmentioning

confidence: 99%

“…This typically limits insitu studies of contrails from specific aircraft to the first 10-15 min of their lifecycle, although some observations exist at longer timescales (Schumann et al 2017). Satellites have the capability to identify contrails over large regions (Mannstein et al 1999, Iwabuchi et al 2012, Duda et al 2013, Vázquez-Navarro et al 2015, but few studies track the evolution of contrails through their observable lifetime (Duda et al 2001, Haywood et al 2009, Vázquez-Navarro et al 2015, Chevallier et al 2023. Satellites cannot detect contrails throughout their whole lifetime (Gierens and Vázquez-Navarro 2018), but the observable lifetime can provide an approximate indication of the radiative impact of a contrail, all else being equal (Driver et al ).…”

Section: Introductionmentioning

confidence: 99%

Operational differences lead to longer lifetimes of satellite detectable contrails from more fuel efficient aircraft

Gryspeerdt,

Stettler,

Teoh

et al. 2024

Environ. Res. Lett.

View full text Add to dashboard Cite

Clouds produced by aircraft (known as contrails) contribute over half of the positive radiative forcing from aviation, but the size of this warming effect is highly uncertain. Their radiative effect is highly dependent on the microphysical properties and meteorological background state, varying strongly over the contrail lifecycle. In-situ observations have demonstrated an impact of aircraft and fuel type on contrail properties close to the aircraft, but there are few observational constraints at these longer timescales, despite these having a strong impact in high-resolution and global models. This work provides an observational quantification of these contrail controlling factors, matching air traffic data to satellite observations of contrails to isolate the role of the aircraft type in contrail properties and evolution. Investigating over 64 000 cases, a relationship between aircraft type and contrail formation is observed, with more efficient aircraft forming longer-lived satellite-detectable contrails more frequently, which could lead to a larger climate impact. This increase in contrail formation and lifetime is primarily driven by an increase in flight altitude. Business jets are also found to produce longer-lived satellite-detectable contrails despite their lower fuel flow, as they fly at higher altitudes. The increase in satellite-detected contrails behind more efficient aircraft suggests a trade-off between aircraft greenhouse gas emissions and the aviation climate impact through contrail production, due to differences in aircraft operation.

show abstract

“…Contrail formation and evolution can also be observed directly from ground and satellite imagery [19][20][21]. Recent advancements in machine learning have enabled contrails to be automatically detected from geostationary satellite imagery [22,23], enabling large-scale comparison with contrail predictions [24,25].…”

Section: Introductionmentioning

confidence: 99%

Feasibility of contrail avoidance in a commercial flight planning system: an operational analysis

Martin Frias,

Shapiro,

Engberg

et al. 2024

Environ. Res.: Infrastruct. Sustain.

Self Cite

View full text Add to dashboard Cite

Aircraft condensation trails, also known as contrails, contribute asubstantial portion of aviation’s overall climate footprint. Contrail impacts canbe reduced through smart flight planning that avoids contrail-forming regions ofthe atmosphere. While previous studies have explored the operational impactsof contrail avoidance in simulated environments, this paper aims to characterizethe feasibility and cost of contrail avoidance precisely within a commercial flightplanning system. This study leverages the commercial Flightkeys 5D (FK5D)algorithm, developed by Flightkeys GmbH, with a prototypical contrail forecastmodel based on the Contrail Cirrus Prediction (CoCiP) model to simulate contrailavoidance on 49,411 flights during the first two weeks of June 2023, and 35,429flights during the first two weeks of January 2024. The utilization of a commercialflight planning system enables high-accuracy estimates of additional cost andfuel investments by operators to achieve estimated reductions in contrail-energyforcing and overall flight Global Warming Potential (GWP). The results show thatnavigational contrail avoidance will require minimal additional cost (0.08%) andfuel (0.11%) investments to achieve notable reductions in contrail climate forcing(-73.0%). This simulation provides evidence that contrail mitigation entails verylow operational risks, even regarding fuel. This study aims to serve as an incentivefor operators and air traffic controllers to initiate contrail mitigation testing assoon as possible and begin reducing aviation’s non-CO2 emissions.

show abstract

Linear Contrails Detection, Tracking and Matching with Aircraft Using Geostationary Satellite and Air Traffic Data

Cited by 11 publications

References 27 publications

SegX-Net: A novel image segmentation approach for contrail detection using deep learning

SegX-Net: A novel image segmentation approach for contrail detection using deep learning

Operational differences lead to longer lifetimes of satellite detectable contrails from more fuel efficient aircraft

Feasibility of contrail avoidance in a commercial flight planning system: an operational analysis

Contact Info

Product

Resources

About