In recent years, the cross research involving intelligent technology and the aviation industry has received continuous attention. The United States and Europe have respectively proposed NextGen, and SESAR related air traffic control research plans. China has also proposed the concept of smart civil aviation and its specific implementation roadmap. As a key technology based on trajectory-based operation (TBO), flight trajectory prediction has received widespread attention from academic and industrial circles at home and abroad. It is an important foundation for existing air traffic management and also the core support for future air traffic operations.
In response to the insufficient performance of existing methods in feature mining and maneuvering stages, the research team of Yi Lin, an associate research fellow at the College of Computer Science, Sichuan University (School of Software, School of Intelligent Science and Technology),introduced time-frequency analysis method into flight trajectory prediction research for the first time.
“---Modern data-driven methods are typically formulated as a time series forecasting task and fail to retain high accuracy. Meantime, as the primary modeling method for time series forecasting, frequency-domain analysis is underutilized in the flight trajectory prediction task. In this work, an innovative wavelet transform-based framework is proposed to perform time-frequency analysis of flight patterns to support trajectory forecasting. An encoder-decoder neural architecture is developed to estimate wavelet components, focusing on the effective modeling of global flight trends and local motion details. A real-world dataset is constructed to validate the proposed approach, and the experimental results demonstrate that the proposed framework exhibits higher accuracy than other comparative baselines, obtaining improved prediction performance in terms of four measurements, especially in the climb and descent phase with maneuver control. Most importantly, the time-frequency analysis is confirmed to be effective to achieve the flight trajectory prediction task.” (Abstract)
This achievement was published in Nature Communications under the title 'Flight Trajectory Prediction Enabled by Time-Frequency Wavelet Transform'. The entire work was independently completed by the College of Computer Science, Sichuan University. Yi Lin is the only corresponding author of this article, and Zheng Zhang, a Class 2021 master program student, is the first author.This work was supported by the National Natural Science Foundation of China (NSFC) under grants No. 62001315, and U20A20161, and by the Open Fund of Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Administration of China (CAAC) under Grant No. FZ2021KF04, also by the Fundamental Research Funds for the Central Universities under Grant No. 2021SCU12050.
https://www.nature.com/articles/s41467-023-40903-9
