Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework

Aircraft trajectory prediction is challenging because of the flight process with uncertain kinematic motion and varying dynamics, which is characterized by intricate temporal dependencies of the flight surveillance data. To address these challenges, this study proposes a novel hybrid prediction fram...

Full description

Saved in:
Bibliographic Details
Main Authors: Fan Li, Xuezhi Xu, Rihan Wang, Mingyuan Ma, Zijing Dong
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713534016946176
author Fan Li
Xuezhi Xu
Rihan Wang
Mingyuan Ma
Zijing Dong
author_facet Fan Li
Xuezhi Xu
Rihan Wang
Mingyuan Ma
Zijing Dong
author_sort Fan Li
collection DOAJ
description Aircraft trajectory prediction is challenging because of the flight process with uncertain kinematic motion and varying dynamics, which is characterized by intricate temporal dependencies of the flight surveillance data. To address these challenges, this study proposes a novel hybrid prediction framework, the IMM-Informer, which integrates an interacting multiple model (IMM) approach with the deep learning-based Informer model. The IMM processes flight tracking with multiple typical motion models to produce the initial state predictions. Within the Informer framework, the encoder captures the temporal features with the ProbSparse self-attention mechanism, and the decoder generates trajectory deviation predictions. A final fusion combines the IMM estimators with Informer correction outputs and leverages their respective strengths to achieve accurate and robust predictions. The experiments are conducted using real flight surveillance data received from automatic dependent surveillance-broadcast (ADS-B) sensors to validate the effectiveness of the proposed method. The results demonstrate that the IMM-Informer framework has notable prediction error reductions and significantly outperforms the prediction accuracies of the standalone sequence prediction network models.
format Article
id doaj-art-4ee91efa81074930922e95b1a0b292b1
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4ee91efa81074930922e95b1a0b292b12025-08-20T03:13:57ZengMDPI AGSensors1424-82202025-04-01258253110.3390/s25082531Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer FrameworkFan Li0Xuezhi Xu1Rihan Wang2Mingyuan Ma3Zijing Dong4CAAC Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Flight University of China, Guanghan 618307, ChinaCAAC Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Flight University of China, Guanghan 618307, ChinaCAAC Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Flight University of China, Guanghan 618307, ChinaCollege of Air Traffic Management, Civil Aviation Flight University of China, Guanghan 618307, ChinaSchool of Mathematics, Sichuan University, Chengdu 610065, ChinaAircraft trajectory prediction is challenging because of the flight process with uncertain kinematic motion and varying dynamics, which is characterized by intricate temporal dependencies of the flight surveillance data. To address these challenges, this study proposes a novel hybrid prediction framework, the IMM-Informer, which integrates an interacting multiple model (IMM) approach with the deep learning-based Informer model. The IMM processes flight tracking with multiple typical motion models to produce the initial state predictions. Within the Informer framework, the encoder captures the temporal features with the ProbSparse self-attention mechanism, and the decoder generates trajectory deviation predictions. A final fusion combines the IMM estimators with Informer correction outputs and leverages their respective strengths to achieve accurate and robust predictions. The experiments are conducted using real flight surveillance data received from automatic dependent surveillance-broadcast (ADS-B) sensors to validate the effectiveness of the proposed method. The results demonstrate that the IMM-Informer framework has notable prediction error reductions and significantly outperforms the prediction accuracies of the standalone sequence prediction network models.https://www.mdpi.com/1424-8220/25/8/2531flight trajectoryADS-B datahybrid predictioninteracting multiple modelInformer
spellingShingle Fan Li
Xuezhi Xu
Rihan Wang
Mingyuan Ma
Zijing Dong
Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
Sensors
flight trajectory
ADS-B data
hybrid prediction
interacting multiple model
Informer
title Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
title_full Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
title_fullStr Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
title_full_unstemmed Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
title_short Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework
title_sort flight trajectory prediction based on automatic dependent surveillance broadcast data fusion with interacting multiple model and informer framework
topic flight trajectory
ADS-B data
hybrid prediction
interacting multiple model
Informer
url https://www.mdpi.com/1424-8220/25/8/2531
work_keys_str_mv AT fanli flighttrajectorypredictionbasedonautomaticdependentsurveillancebroadcastdatafusionwithinteractingmultiplemodelandinformerframework
AT xuezhixu flighttrajectorypredictionbasedonautomaticdependentsurveillancebroadcastdatafusionwithinteractingmultiplemodelandinformerframework
AT rihanwang flighttrajectorypredictionbasedonautomaticdependentsurveillancebroadcastdatafusionwithinteractingmultiplemodelandinformerframework
AT mingyuanma flighttrajectorypredictionbasedonautomaticdependentsurveillancebroadcastdatafusionwithinteractingmultiplemodelandinformerframework
AT zijingdong flighttrajectorypredictionbasedonautomaticdependentsurveillancebroadcastdatafusionwithinteractingmultiplemodelandinformerframework