Improving orbit prediction accuracy through supervised machine learning

Peng, Hao; Bai, Xiaoli

doi:10.1016/j.asr.2018.03.001

Cited by 67 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the measurements were uniform, so results demonstrated an improvement in the orbit prediction accuracy. SVM has been widely used to predict orbit errors as in [13,14], improving the orbit prediction accuracy learning from historical prediction errors.…”

Section: Subjectmentioning

confidence: 99%

Satellite Orbit Prediction Using Big Data and Soft Computing Techniques to Avoid Space Collisions

et al. 2021

View full text Add to dashboard Cite

The number of satellites and debris in space is dangerously increasing through the years. For that reason, it is mandatory to design techniques to approach the position of a given object at a given time. In this paper, we present a system to do so based on a database of satellite positions according to their coordinates (x,y,z) for one month. We have paid special emphasis on the preliminary stage of data arrangement, since if we do not have consistent data, the results we will obtain will be useless, so the first stage of this work is a full study of the information gathered locating the missing gaps of data and covering them with a prediction. With that information, we are able to calculate an orbit error which will estimate the position of a satellite in time, even when the information is not accurate, by means of prediction of the satellite’s position. The comparison of two satellites over 26 days will serve to highlight the importance of the accuracy in the data, provoking in some cases an estimated error of 4% if the data are not well measured.

show abstract

Section: Subjectmentioning

confidence: 99%

Satellite Orbit Prediction Using Big Data and Soft Computing Techniques to Avoid Space Collisions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Some of those works are focused on improving orbit determination by the implementation of ML. In Peng and Bai (2018a), support vector machine is used for reducing the positional error of satellites after orbit determination and orbit propagation processes. In Peng and Bai (2018b), they continued with this line of research, switching from SVM to artificial neural networks (ANN).…”

Section: Artificial Intelligence In Space Safetymentioning

confidence: 99%

AI and Space Safety: Collision Risk Assessment

Sánchez

Vasile

Minisci

2020

Handbook of Space Security

View full text Add to dashboard Cite

The New Space environment will introduce notorious changes in the space environment during the next decades with the irruption of mega-constellation, the boost of small satellites, and the generalization of low-thrust engines. Current safety strategies and collision avoidance procedures will no longer be capable to deal with the increase on conjunction alerts. Artificial intelligence appears to be the best strategy to cope with this new situation, thanks to its ability to perform faster than physical models and make decisions based on a wider range of parameters than human operators. This results in better performances when more data are available, as the situations will present on the coming years.

show abstract

“…Peng et al [15] concentrated on the lack of area-tomass ratio of a resident space object in most space catalogs and proposed an improved method of satellite orbital prediction. They used Random Forest (RF) to learn the connection between the consistency error and area-to-mass ratio, and Support Vector Machine (SVM) to learn the errors of orbital prediction [16] [17]. However, their work is just based on their simulation environment and did not apply TLE data or any other actual on-orbit data.…”

Section: Introductionmentioning

confidence: 99%

Correction of Atmospheric Model Through Data Mining With Historical Data of Two-Line Element

Bai

Liao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The existing atmospheric mass density models (AMDM) would produce considerable errors in orbital prediction for Low Earth Orbit (LEO) satellites. In order to reduce these errors and correct the AMDM, this paper presents methods based on data mining with historical data of two-line element (TLE). Starting from a typical LEO satellite, TIANHUI, two orbital dynamical models are firstly proposed as the simulation environment to generate training data. The historical TLE data are regarded as actual space environment and used to generate application data. Secondly, three data mining methods, Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine (SVM), are combined with the training data to investigate their feasibility in recovering the known deviation of AMDM under simulation environment. Training results show that RF displays the best performance and achieves the accuracy of 99.99%, while the other two methods only achieve 86.83% and 71.90% respectively. Thirdly, under the actual space environment, this paper uses new training and application data to research the ability of the three methods in recovering the unknown deviation of the AMDM and improve the accuracy of orbital prediction. Numerical results are evidential to the accuracy of the proposed methods based on data mining. It is concluded that the capabilities of the data mining for correction for the atmospheric model are very promising, with great potential to advance practical applications on on-orbit propagation.

show abstract

Improving orbit prediction accuracy through supervised machine learning

Cited by 67 publications

References 10 publications

Satellite Orbit Prediction Using Big Data and Soft Computing Techniques to Avoid Space Collisions

Satellite Orbit Prediction Using Big Data and Soft Computing Techniques to Avoid Space Collisions

AI and Space Safety: Collision Risk Assessment

Correction of Atmospheric Model Through Data Mining With Historical Data of Two-Line Element

Contact Info

Product

Resources

About