English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In many scenarios, it is necessary to monitor a complex system via atime-series of observations and determine when anomalous exogenous events haveoccurred so that relevant actions can be taken. Determining whether currentobservations are abnormal is challenging. It requires learning an extrapolativeprobabilistic model of the dynamics from historical data, and using a limitednumber of current observations to make a classification. We leverage recentadvances in long-term probabilistic forecasting, namely {\em Deep ProbabilisticKoopman}, to build a general method for classifying anomalies inmulti-dimensional time-series data. We also show how to utilize models withdomain knowledge of the dynamics to reduce type I and type II error. Wedemonstrate our proposed method on the important real-world task of globalatmospheric pollution monitoring, integrating it with NASA's Global EarthSystem Model. The system successfully detects localized anomalies in airquality due to events such as COVID-19 lockdowns and wildfires.

Koopman-theoretic Approach for Identification of Exogenous Anomalies in Nonstationary Time-series Data