AeroTSBoost: Temporal-Statistical Boosting for Real-World UAV Telemetry Anomaly Mining
2026-05-25 • Computational Engineering, Finance, and Science
Computational Engineering, Finance, and Science
AI summaryⓘ
The authors developed AeroTSBoost, a method to find unusual events in drone flight data, which is hard because problems happen rarely and the data is messy. Their approach looks at windows of flight data and creates detailed summaries that capture changes and patterns over time, then uses a machine learning model to detect anomalies. Tested on two different drone datasets, AeroTSBoost outperformed other common methods, showing better accuracy in spotting faults. This suggests their way of summarizing and analyzing flight logs is effective for finding rare drone issues.
Unmanned Aerial Vehicle (UAV)Anomaly DetectionTelemetryTime Series AnalysisLightGBMBoostingAUPRC (Area Under Precision-Recall Curve)Multivariate DataCyber-Physical SystemsFeature Engineering
Authors
Junhao Wei, Haochen Li, Yanxiao Li, Yifu Zhao, Dexing Yao, Baili Lu, Xudong Ye, Sio-Kei Im, Yapeng Wang, Xu Yang
Abstract
Mining anomalies from unmanned aerial vehicle (UAV) state-estimation logs is challenging because failures are sparse, temporally structured, and distributed across heterogeneous PX4 telemetry streams with variable sensor availability and missing values. We present AeroTSBoost, a temporal-statistical boosting framework for real-world UAV telemetry anomaly mining. AeroTSBoost aligns multivariate flight logs, converts each window into deterministic descriptors that capture distributional shifts, quantile structure, endpoint drift, local dynamics, and lag correlation, and trains a class-balanced LightGBM detector. On UAV-SEAD, AeroTSBoost achieves the strongest AUPRC among evaluated classical, supervised tabular, neural reconstruction, recurrent, Granger-causality-based, and frequency-domain baselines. Across five seeds, it reaches $0.7516\pm0.0043$ AUPRC and $0.5342\pm0.0108$ threshold-swept event F1, improving AUPRC by 5.79 absolute points over the strongest non-AeroTSBoost baseline. Under purged chronological and leave-log-out protocols, it remains the best AUPRC method, reaching $0.6066\pm0.0193$ and $0.6388\pm0.0315$, respectively. On related ALFA fixed-wing UAV fault logs, AeroTSBoost reaches $0.9259\pm0.0076$ leave-sequence-out AUPRC, ahead of RandomForest ($0.8835\pm0.0797$) and moments-only ($0.8700\pm0.0481$). These results show that deterministic temporal-statistical representations remain highly competitive for sparse anomaly mining in operational cyber-physical telemetry.