1. Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold
- Author
-
Ale, Tolulope, Schlegel, Nicole-Jeanne, and Janeja, Vandana P.
- Subjects
Computer Science - Machine Learning ,Computer Science - Information Retrieval - 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 the Variational Autoencoder (VAE) integrated with dynamic thresholding and correlation-based 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., Comment: This work was presented at the 2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024, 07-12 July 2024, Athens, Greece
- Published
- 2024