Real-time and short-term anomaly detection for GWAC light curves

Due to the fast development and wide deployment of cloud computing and big data, applications in various industries have shown their unique advantages. Currently, many fields have gained great changes due to benefits brought by big data analysis. This paper accurately and quickly analyzes the data of Ground-based Wide-Angle Camera array (GWAC) based on Grubbs and detects anomaly astronomical events. In this paper, we improved ARIMA model with the dynamic and parallel processing. The model identifies anomaly events that occur in light curves obtained from GWAC as early as possible with high degree of confidence. A major advantage of improved ARIMA is that it can dynamically adjust its model parameters during the real-time processing of the time series data, and increase its efficiency through a multi-process parallel approach. We identify the anomaly points based on the Grubbs and improved ARIMA model. Experimental results with real survey data show that the improved ARIMA model can identify the anomaly points for all light curves. We also evaluate our model with simulated anomaly events of various types embedded in the real time series data. The improved ARIMA model is able to generate the early warning triggers for all of them. These results from the experiments demonstrate that the proposed improved ARIMA model is a promising method for real-time anomaly detection of short time-scale GWAC light curves.