Automatic contrail detection using integrated satellite observation, meteorological indicators, and air traffic data in the United Kingdom

Aviation-induced contrails significantly contribute to climate change, yet current strategies for their real-time prediction and mitigation remain limited. This paper presents AI approaches for a contrail prediction framework that integrates meteorological data and Automatic Dependent Surveillance Broadcast (ADS-B) flight trajectories. We use meteorological and ADS-B flight data to identify contrail-prone areas, which are a foundation for model training and simulations. The Schmidt Appleman Criterion (SAC) model are applied to predict these areas and devise a strategy for detecting contrails. The models successfully identify contrails-prone zones and recommend feasible flight paths that optimise environmental and operational parameters while complying with the research framework. The proposed framework offers a promising avenue for mitigating the environmental impact of contrails in aviation, focusing on the United Kingdom (UK) airspace with potential adaptation for other regions to support global sustainable aviation practices.