Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold
Year: 2024
Type: article
Abstract: We introduce an anomaly detection method for multivariate time series data with the aim of identifying critical periods and features influencing extreme climate events like snowmelt in the Arctic. This method leverages Variational Autoencoder (VAE) integrated with dynamic thresholding and correlationbased feature clustering. This framework enhances the VAE’s ability to identify localized dependencies and learn the temporal relationships in climate data, thereby improving the detection of anomalies as demonstrated by its higher F1-score on benchmark datasets. The study’s main contributions include the development of a robust anomaly detection method, improving feature representation within VAEs through clustering, and creating a dynamic threshold algorithm for localized anomaly detection. This method offers explainability of climate anomalies across different regions.
DOI: 10.13016/m2cngr-xnfl
Authors: Ale, Tolulope, Janeja, Vandana, Schlegel, Nicole-Jeanne
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Climate action
Open Access status: green
OpenAlex ID: W6903709037
FWCI:
Cites:
Cited by:
Related to: