Elastic Maps now supports the Machine Learning Anomalies Layer

Elastic Maps' 8.1.0 release now supports a Machine Learning Anomalies Layer, allowing users to view geographical anomalies detected by ML jobs directly on maps. This feature is particularly useful for analyzing data like the General Transit Feed Specification (GTFS) from San Antonio, TX, which includes real-time vehicle position updates. Users can create anomaly detection jobs in Kibana with the lat_long function to identify unusual geographic locations for vehicles, which may signal issues or delays. Once the job results are available, users can visualize them on Elastic Maps by adding an ML Anomalies layer that displays actual, typical, and actual-to-typical positions, color-coded by anomaly severity. Additionally, users can filter anomalies by time frame or severity score, facilitating a focused analysis of significant deviations from typical vehicle patterns. The integration also allows seamless navigation from the Anomaly Explorer view in Elastic Machine Learning to Elastic Maps, enhancing the user's ability to analyze and investigate anomalies in detail.