Abstract
Existing dynamic graph embedding-based outlier detection methods mainly focus on the evolution of graphs and ignore the similarities among them. To overcome this limitation for the effective detection of abnormal climatic events from meteorological time series, we proposed a dynamic graph embedding model based on graph proximity, called DynGPE. Climatic events are represented as a graph where each vertex indicates meteorological data and each edge indicates a spurious relationship between two meteorological time series that are not causally related. The graph proximity is described as the distance between two graphs. DynGPE can cluster similar climatic events in the embedding space. Abnormal climatic events are distant from most of the other events and can be detected using outlier detection methods. We conducted experiments by applying three outlier detection methods (i.e., isolation forest, local outlier factor, and box plot) to real meteorological data. The results showed that DynGPE achieves better results than the baseline by 44.3% on average in terms of the F-measure. Isolation forest provides the best performance and stability. It achieved higher results than the local outlier factor and box plot methods, namely, by 15.4% and 78.9% on average, respectively.
Highlights
Meteorological time series are part of climatic data and they have been extensively researched in many fields, including environmental science and computer engineering [1,2,3]
Dynamic graph embedding for outlier detection on multiple meteorological time series The remainder of this paper is organized as follows
DynGPE achieves the best result for each city because graph convolutional neural (GCN) and dynagraph2vecAE only capture information from a single graph; dyngraph2vecRNN only captures the temporal information of the dynamic graph but ignores the similarities of the graph
Summary
Meteorological time series are part of climatic data and they have been extensively researched in many fields, including environmental science and computer engineering [1,2,3]. Existing methods are mainly based on statistical indices [6] and machine learning algorithms, such as similarity-based methods [7] and density-based clustering methods [8] These methods ignore the relationships among the time series, making it difficult to understand the causes of outliers. Dynamic graph embedding for outlier detection on multiple meteorological time series. This cannot explain the external factors affecting outliers To solve this problem, we propose a method to discover the spurious relationship between two correlated time series that are not causally related, such that a dynamic graph can be constructed for detecting outliers. We used dynamic graph embedding, which uses a non-linear function to learn representation vectors of climatic events. Dynamic graph embedding for outlier detection on multiple meteorological time series The remainder of this paper is organized as follows.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
