Visualization and Prediction of Aircraft trajectory using ADS-B

Kanneganti, Sai Teja; Chilson, Phillip B.; Huck, Robert C.

doi:10.1109/naecon.2018.8556782

Cited by 10 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data received from the PingStation are used to view air traffic in a web browser, which updates air traffic on the map every two seconds. A more detailed discussion can be found in Kanneganti et al [45]. An example of how flight tracks are displayed through the software is given in Figure 10.…”

Section: Supporting Components Of the 3d Mesonetmentioning

confidence: 99%

Moving towards a Network of Autonomous UAS Atmospheric Profiling Stations for Observations in the Earth’s Lower Atmosphere: The 3D Mesonet Concept

Chilson

Bell

Brewster

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

The deployment of small unmanned aircraft systems (UAS) to collect routine in situ vertical profiles of the thermodynamic and kinematic state of the atmosphere in conjunction with other weather observations could significantly improve weather forecasting skill and resolution. High-resolution vertical measurements of pressure, temperature, humidity, wind speed and wind direction are critical to the understanding of atmospheric boundary layer processes integral to air–surface (land, ocean and sea ice) exchanges of energy, momentum, and moisture; how these are affected by climate variability; and how they impact weather forecasts and air quality simulations. We explore the potential value of collecting coordinated atmospheric profiles at fixed surface observing sites at designated times using instrumented UAS. We refer to such a network of autonomous weather UAS designed for atmospheric profiling and capable of operating in most weather conditions as a 3D Mesonet. We outline some of the fundamental and high-impact science questions and sampling needs driving the development of the 3D Mesonet and offer an overview of the general concept of operations. Preliminary measurements from profiling UAS are presented and we discuss how measurements from an operational network could be realized to better characterize the atmospheric boundary layer, improve weather forecasts, and help to identify threats of severe weather.

show abstract

Section: Supporting Components Of the 3d Mesonetmentioning

confidence: 99%

Moving towards a Network of Autonomous UAS Atmospheric Profiling Stations for Observations in the Earth’s Lower Atmosphere: The 3D Mesonet Concept

Chilson

Bell

Brewster

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In theory, given enough examples and relevant features, these methods can learn the underlying laws, routes and maneuvers that govern aircraft movement rather than having to manually integrate them. While relatively simple models such as regression ones can be used to predict trajectories [19], [20], the models that have caught the most interest are those based on neural networks. The flexibility and capability of neural networks to approximate arbitrary functions and exploiting low-level features make them ideal for a context where the output may be influenced by complex, conditional non-linear combinations of the input.…”

Section: Related Workmentioning

confidence: 99%

Neural Networks for Aircraft Trajectory Prediction: Answering Open Questions About Their Performance

Ayala

Vidal

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The increase in air traffic in the recent years has motivated the development of technologies to monitor air space and warn about possible collisions by predicting the trajectories that will be followed by aircraft. In this field, neural networks have become prominent thanks to their potential to learn to predict maneuvers without providing aspects that are difficult to model such as atmospheric conditions, or detailed aircraft parameters. A variety of models have been proposed; however, these are often tested in very limited setups, leaving many unanswered questions about how they perform in certain conditions, or whether or not their accuracy can be improved by training models for specific trajectories, using additional features, predicting more distant points directly, etc. This may be problematic for researchers or developers of these systems, who have no way of knowing what strategies will yield the best results. We have identified ten open research questions that have not been answered through in-depth testing. This motivated us to carry out a novel experimental study that performs aircraft trajectory prediction with several dozens configuration variants to answer the aforementioned questions by means of a much more complete evaluation. Some of the conclusions of our study stand in contrast with some popular practices in the state of the art, which casts some doubts on the simplicity of their application; for example, differential features are crucial for proper performance but are not mentioned by most studies, while complex, more elaborate models may lead to worse results than simple ones. Other important insights include the benefit from specialized models in more challenging scenarios, the influence of the known trajectory length in said scenarios, the step degradation of predictions when predicting further into the future, or the detrimental effect of adding additional features. These insights should help guide future research about the application of neural networks when it comes to aircraft trajectory prediction and their eventual inclusion in final systems.

show abstract

“…This primarily includes regression models [20], neural networks [21], [22], and hybrid models [23], [24], [25]. Kanneganti et al [26] utilized aircraft direction and velocity data to construct a simple regression prediction model that accurately forecasted aircraft positions. However, when it comes to trajectory prediction, the paths of moving targets often exhibit nonlinearity, especially when dealing with small civilian UAVs.…”

Section: Related Workmentioning

confidence: 99%

SVM-BTS Based Trajectory Identification and Prediction Method for Civil Rotorcraft UAVs

Jiao,

Bao,

Bai

et al. 2023

IEEE Access

View full text Add to dashboard Cite

To address the issue of low predictive accuracy in complex trajectory forecasting for civilian rotorcraft unmanned aerial vehicles (UAVs), this paper presents a method that utilizes the SVM-BTS technique for recognizing and predicting these intricate trajectories. Initially, the Support Vector Machine-Binary Tree Support Vector Machine model (SVM-BTS) is employed to segmentally recognize the complex trajectories of civilian UAVs. Based on this identification, five distinct flight states are identified: vertical, pitch, transverse, roll, and transitional. To assess the predictive performance of these states, a combination of Sliding Window Polynomial Least Squares, Unscented Kalman Filtering, and Long Short-Term Memory neural network methods is utilized. Consequently, the most suitable prediction algorithm is determined for each flight state. Experimental results demonstrate that this method accurately predicts complex flight trajectories for civilian rotorcraft UAVs, enhancing the precision and efficiency of UAV flight prediction.

show abstract

Visualization and Prediction of Aircraft trajectory using ADS-B

Cited by 10 publications

References 1 publication

Moving towards a Network of Autonomous UAS Atmospheric Profiling Stations for Observations in the Earth’s Lower Atmosphere: The 3D Mesonet Concept

Moving towards a Network of Autonomous UAS Atmospheric Profiling Stations for Observations in the Earth’s Lower Atmosphere: The 3D Mesonet Concept

Neural Networks for Aircraft Trajectory Prediction: Answering Open Questions About Their Performance

SVM-BTS Based Trajectory Identification and Prediction Method for Civil Rotorcraft UAVs

Contact Info

Product

Resources

About