ARCANE: An Operational Framework for Automatic Realtime ICME Detection in Solar Wind In Situ Data

Interplanetary Coronal Mass Ejections (ICMEs) are the primary drivers of space weather disturbances, necessitating accurate and timely detection to mitigate their impact. However, traditional identification methods often rely on post-event analysis, which limits their application in real-time forecasting scenarios.  

We introduce ARCANE, an operational, modular framework for the automatic, real-time detection of ICMEs in solar wind in situ data. ARCANE combines machine learning models with physics-based approaches, leveraging data from multiple spacecraft to enable early detection and enhance forecasting capabilities. The first prototype of the framework, trained on OMNI data, has been evaluated on real-time solar wind datasets, demonstrating its potential for operational use. 

This presentation outlines the methodology underlying ARCANE, highlights the challenges of adapting machine learning models for streaming data, and discusses the framework’s operational implementation at the Austrian Space Weather Office. Future development directions include enhancing real-time performance, integrating early predictions of key ICME parameters, and extending ARCANE's applicability to multi-spacecraft data for improved global space weather forecasting.