REAL-TIME ANORMALY DETECTION OF RIVER WATER LEVEL OBSERVATION BASED ON PROBABILITY DISTRIBUTION OF WATER LEVEL ESTIMATION ERROR

Abstract

 Real-time observation data of the river water level includes various anomalies. Such anomalies may cause fatal errors in judgments on disaster prevention activity and flood forecasting systems, but real-time anomaly detection has not been sufficiently implemented. In this study, we developed the model to detect anomalies in real-time for river water level data sent from observation stations every 10 minutes. By using machine learning, the water level at the current time of the objective observation station was estimated from the neighboring water level and rainfall. Then the anomaly score was calculated from the degree of deviation between the estimated water level and actual observation. Furthermore, the model was combined with the rule-based anomaly detection model. The proposed method was verified using actual observation data, and better performance was confirmed compared to the existing method.