Optimizing Contrail Detection: A Deep Learning Approach with EfficientNet-b4 Encoding

TL;DR

This paper introduces a deep learning method using EfficientNet-b4 for precise contrail detection in satellite images, incorporating misalignment correction and pseudo-labeling to support sustainable aviation efforts.

Contribution

It presents a novel deep learning framework that improves contrail segmentation accuracy by integrating misalignment correction, soft labeling, and pseudo-labeling techniques.

Findings

Enhanced contrail detection accuracy in satellite imagery.

Effective handling of atmospheric variability and misalignment issues.

Potential to support environmental impact assessment in aviation.

Abstract

In the pursuit of environmental sustainability, the aviation industry faces the challenge of minimizing its ecological footprint. Among the key solutions is contrail avoidance, targeting the linear ice-crystal clouds produced by aircraft exhaust. These contrails exacerbate global warming by trapping atmospheric heat, necessitating precise segmentation and comprehensive analysis of contrail images to gauge their environmental impact. However, this segmentation task is complex due to the varying appearances of contrails under different atmospheric conditions and potential misalignment issues in predictive modeling. This paper presents an innovative deep-learning approach utilizing the efficient net-b4 encoder for feature extraction, seamlessly integrating misalignment correction, soft labeling, and pseudo-labeling techniques to enhance the accuracy and efficiency of contrail detection in satellite imagery. The proposed methodology aims to redefine contrail image analysis and contribute to the objectives of sustainable aviation by providing a robust framework for precise contrail detection and analysis in satellite imagery, thus aiding in the mitigation of aviation's environmental impact.