A. Aswini and Prof. S. Varadarajan

DOI: https://doi.org/10.5281/zenodo.23191863

Ground monitoring becomes more useful when aircraft state, communication condition, time, and location are interpreted together rather than as independent streams. This paper presents an integrated ground-monitoring workflow that combines historical flight-telemetry visualization with a causal multi-horizon machine-learning pipeline for predicting future wireless-link change. The main prediction target is future change in signal-to-interference-plus-noise ratio (ΔSINR) at horizons of 1, 2, 5, 10, 15, 20, and 30 s. The quantitative study uses three physical flight records drawn from two public AERPAW measurement sources: two Ericsson 5G NSA traces at yaw orientations of 45° and 315°, and one Lake Wheeler Android-based 4G LTE/5G NR trace. The records contain LTE/NR radio indicators, throughput, position, altitude, cell information, and motion/orientation fields, with 2376 raw observations across the three physical flights. The processing uses a causal 1-s grid, flight-isolated temporal features, chronological evaluation with a horizon-sized purge, training only mutual-information feature selection, and a persistence baseline. Three classical regressors—HistGradientBoosting (HGB), Random Forest, and Extra Trees—are evaluated. An engineering link-quality index (LQI) in the range 0–100 summarizes 12 available cellular and throughput indicators. At the predeclared 30-s operating point, HGB obtains a ΔSINR MAE of 3.110 dB versus 3.669 dB for persistence, a 15.23% reduction. A separate NASA Tail-654 ground-monitoring implementation replays a historical MATLAB flight record, presents map-based trajectory and primary telemetry, and applies phase-aware statistical anomaly monitoring using robust envelopes, eight-second persistence, and recovery hysteresis. The NASA component is kept experimentally separate from the wireless-link prediction metrics. The resulting system connects telemetry observability with forward-looking communication-state information while preserving a strict separation between information available at prediction time and future observations.

UAV telemetry, ground monitoring console, causal machine learning, link-quality prediction, SINR prediction, 5G, LTE, link quality index, anomaly detection, aerial communications.

This paper presents a ground-monitoring workflow that connects aircraft telemetry replay, causal temporal processing, future cellular-link prediction, an engineering LQI, and operator-facing monitoring outputs. The main quantitative experiment uses two public AERPAW measurement sources and three independent physical flight traces. At the selected 30-s operating point, HGB achieves 3.110 dB MAE versus 3.669 dB for persistence. The separate NASA Tail-654 console adds map-based replay, primary aircraft telemetry, phase-aware statistical monitoring, eight-second persistence, and recovery hysteresis without mixing aircraft-state anomaly monitoring with wireless-link prediction metrics. The resulting system is a practical ground-monitoring prototype with clear separation between the predictive communication experiment and the aircraft telemetry observability branch.

[1] H. S. Júnior, M. A. Santos, T. F. Lúcio, and G. V. Raffo, “Developing an Integrated Ground Station for UAV Operations: Telemetry and Mission Planning,” in Proc. 2025 Brazilian Conference on Robotics (CROS), 2025, pp. 1–6, doi: 10.1109/CROS66186.2025.11066147.
[2] C. Liu, B. Shangguan, P. Yue, and M. Zhang, “Towards an Integrated Service Platform in Remote Sensing Satellite Ground Station for Telemetry, Operational Control, and Data Application,” in Proc. 10th Int. Conf. Agro-Geoinformatics, 2022, pp. 1–6, doi: 10.1109/Agro Geoinformatics 55649 .2022.9859217.
[3] G. Cerar, H. Yetgin, M. Mohorčič, and C. Fortuna, “Machine Learning for Wireless Link Quality Estimation: A Survey,” IEEE Communications Surveys & Tutorials, vol. 23,no. 2, pp. 696–728, 2021, doi:10.1109/COMST.2021 .3053615.
[4] I. J. Kim and S. Lee, “Development of Telemetry Data Processing Program,” in Proc. 2013 Int. Conf. ICT Convergence (ICTC), 2013, pp. 468–473, doi: 10.1109/ICTC.2013.6675398.
[5] L. Segal, “Development of a Command and Telemetry Processing Interface to be Independent of Ground Control Systems,” in Proc. AUTOTESTCON, 2011, doi: 10.1109/AUTEST.2011.6058770.
[6] M. A. Alqodah and M. M. Matalgah, “Ground-Based Aircraft Recorders: Requirements, Challenges, Implementations, and Future Perspectives,” IEEE Communications Magazine, vol. 63, no. 3, pp. 62–68, 2025, doi: 10.1109/MCOM.001.2300779.
[7] A. H. Fahim Raouf, D. Lee, M. Rahman, et al., “Curated wireless datasets for aerial network research,” npj Wireless Technology, vol. 2, Art. no. 41, 2026, doi: 10.1038/s44459-026-00050-1.
[8] S. Singh, A. Gürses, O. Ozdemir, R. Asokan, M. L. Sichitiu, I. Guvenc, R. Dutta, and M. Mushi, “Modeling and Analysis of Air-to-Ground Cellular KPIs in a 5G Testbed using Android Smartphones,” in Proc. IEEE Aerospace Conference,2026, doi: 10.1109/AERO66936.2026.11520074.
[9] A. Festag, S. Udupa, L. Garcia, R. Wellens, M. Hecht, and P. Ulfig, “End-to-End Performance Measurements of Drone Communications in 5G Cellular Networks,” in Proc. 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall),2021,doi:10.1109/VTC2021-Fall 52928.2021.9625429.
[10] W. Khawaja, I. Guvenc, D. W. Matolak, U.-C. Fiebig, and N. Schneckenberger, “A Survey of Air-to-Ground Propagation Channel Modeling for Unmanned Aerial Vehicles,” IEEE Communications Surveys & Tutorials, vol. 21,no.3, pp. 2361–2391, 2019, doi: 10.1109/ COMST.2019.2915069.
[11] D. Mishra and E. Natalizio, “A survey on cellular-connected UAVs: Design challenges, enabling 5G/B5G innovations, and experimental advancements,” Computer Networks, vol. 182, Art. no. 107451, 2020, doi: 10.1016/j.comnet.2020.107451.
[12] A. Alzenad, A. El-Keyi, F. Lagum, and H. Yanikomeroglu, “UAV-Enabled Ultra-Reliable Low-Latency Communications for 6G: A Comprehensive Survey,” IEEE Access, vol. 9, pp. 137338–137352, 2021, doi: 10.1109/ACCESS.2021.3117902.
[13] Z. Li, M. Chen, G. Li, X. Lin, and Y. Liu, “Map-Driven mmWave Link Quality Prediction With Spatial-Temporal Mobility Awareness,” IEEE Transactions on Mobile Computing, vol. 23, no. 12, pp. 12161–12175, 2024, doi: 10.1109/TMC.2024.3406728.
[14] T. Nishio, K. Yamamoto, M. Morikura, and S. Itahara, “Online Trainable Wireless Link Quality Prediction System using Camera Imagery,” in Proc. IEEE Globecom Workshops, 2020, doi: 10.1109/ GCWkshps 50303.2020.9367396.
[15] M. L. Bote-Lorenzo, E. Gómez-Sánchez, C. Mediavilla-Pastor, and J. I. Asensio-Pérez, “Online machine learning algorithms to predict link quality in community wireless mesh networks,” Computer Networks, vol. 132, pp. 68–80, 2018, doi: 10.1016/j.comnet.2018.01.005.
[16] A. O. Hashesh, S. Hashima, R. M. Zaki, M. M. Fouda, K. Hatano, and A. S. T. Eldien, “AI-Enabled UAV Communications: Challenges and Future Directions,” IEEE Access, vol. 10, pp. 92048–92066, 2022, doi: 10.1109/ACCESS.2022.3202956.
[17] C. Xu and Y. Xie, “Conformal Prediction for Time Series,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 10, pp. 11575–11587, 2023, doi: 10.1109/TPAMI.2023.3272339.
[18] I. Panitsas and L. Tassiulas, “A Family of Open Time-Series Foundation Models for the Radio Access Network,” arXiv preprint arXiv:2604.04271, 2026.

A. Aswini and Prof. S. Varadarajan (2026). Ground Monitoring Console with Causal Link-Quality Prediction. International Journal of Engineering and Techniques, 12(5), 326–334. ISSN: 2395-1303. DOI: https://doi.org/10.5281/zenodo.23191863