Detection of wave buoy rough data errors using the local outlier factor

Sea states are usually obtained using wave buoys. Wave recording using these wave buoys is usually associated with some errors. So before extracting any information from this data it is necessary to identify and remove or correct them. The aim of this paper is identifying the errors in wave records of buoys using local outlier factor (LOF) method. LOF is a powefull method to identify anomalies in the data in machine learning which is used in many practical applications. In this paper the daily wave data of Asalouye of Boushehr Province in persian Gulf recorded by PMO buoy in the period 17/02/92 to 01/05/92 was analysed for errors using this method. The results show that LOF is an efficient method to detect errors in wave data loggers.