Adaptive Anomaly Detection in Chaotic Time Series with a Spatially Aware Echo State Network
This work addresses anomaly detection in high-dimensional chaotic systems like climate models, offering a domain-specific incremental improvement for environmental monitoring.
The authors developed an automated anomaly detection method for chaotic time series, specifically targeting turbulent ocean simulations, by extending Echo State Networks with spatially aware input maps and loss functions, achieving detection of subtle bimodality in the Kuroshio ocean current that is not easily visible.
This work builds an automated anomaly detection method for chaotic time series, and more concretely for turbulent, high-dimensional, ocean simulations. We solve this task by extending the Echo State Network by spatially aware input maps, such as convolutions, gradients, cosine transforms, et cetera, as well as a spatially aware loss function. The spatial ESN is used to create predictions which reduce the detection problem to thresholding of the prediction error. We benchmark our detection framework on different tasks of increasing difficulty to show the generality of the framework before applying it to raw climate model output in the region of the Japanese ocean current Kuroshio, which exhibits a bimodality that is not easily detected by the naked eye. The code is available as an open source Python package, Torsk, available at https://github.com/nmheim/torsk, where we also provide supplementary material and programs that reproduce the results shown in this paper.