Kalman Filter–Enhanced Threshold Framework for Strong Wind Anomaly Detection

The detection of strong wind anomalies is crucial for meteorological monitoring, environmental assessment, and mitigating wind-related risks. However, conventional threshold-based methods often lack robustness when processing noisy and unstable wind-speed data collected under dynamic outdoor conditions. To address this limitation, this study proposes an integrated real-time detection framework that combines Kalman Filter–based noise reduction, Beaufort Scale threshold classification, and statistical anomaly detection using the Interquartile Range (IQR). The Kalman Filter smooths wind-speed time series and suppresses random measurement noise, while the Beaufort Scale classifies strong wind events by intensity. Additionally, the IQR method identifies statistically significant sub-threshold anomalies that fixed thresholding alone may miss. We evaluated the proposed framework using a 14-day real-time wind-speed dataset collected outdoors. Experimental results show that the integrated approach improves signal stability and anomaly-detection performance compared with conventional threshold-only techniques. The IQR component reveals additional wind irregularities that remain undetected under fixed-threshold criteria. The main contribution of this work lies in the unified integration of dynamic Kalman-based filtering and distribution-driven anomaly analysis, enabling a more adaptive and interpretable characterization of wind-speed variability under real-world conditions. This framework provides a reliable foundation for real-time environmental monitoring and early warning applications.