Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Penelitian Sains
Hamdi Akhsan
Program Studi Magister Pendidikan Fisika, FKIP, Universitas Sriwijaya, Palembang, Indonesia
Chemistry Mathematics Physics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
AI Methods For Satellite Clock Bias Prediction: A Systematic Literature Review of Techniques, Performance and Future Directions Putri Anisah; Hamdi Akhsan; Arqharana Tiara Ayu
Jurnal Penelitian Sains Vol 28, No 2 (2026)
Publisher : Faculty of Mathtmatics and Natural Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56064/jps.v28i2.1367

Abstract

The accuracy of the Global Navigation Satellite System (GNSS) relies heavily on the precision of the atomic clocks onboard the satellites. Satellite Clock Bias (SCB) is a dominant source of error that limits the accuracy of Positioning, Velocity, and Timing (PVT), especially in Precise Point Positioning (PPP) and Real-Time Kinematic (RTK) applications. This study presents a comprehensive Systematic Literature Review (SLR) using the PRISMA 2020 protocol with searches conducted across four databases (IEEE Xplore, ScienceDirect, Springer, Google Scholar) for the period 2017–2025. Out of 512 identified articles, 22 peer-reviewed studies with verified DOIs met the inclusion criteria. LSTM is the dominant architecture (55% of studies), followed by hybrid CNN-LSTM/BiGRU-Attention approaches (41%) and BPNN (27%). AI methods achieved an accuracy improvement of 40–93% compared to classical methods for 1–6 hour predictions, with the best accuracy of 0.078 ns using BWO-CNN-BiGRU-Attention [5]. Passive Hydrogen Maser (PHM) showed 47% better predictability compared to Rubidium [16]. As many as 77% of studies were published from 2023–2025. Major challenges include overfitting, cross-constellation generalization, and explainability. Recommendations include Physics-Informed Neural Networks (PINNs), Explainable AI (XAI), and standardized benchmarking.
Co-Authors Arqharana Tiara Ayu Putri Anisah