CIPHER: Scalable Time Series Analysis for Physical Sciences with Application to Solar Wind Phenomena

TL;DR

CIPHER is a scalable framework that combines symbolic compression, clustering, and human validation to efficiently label complex physical science time series, demonstrated on solar wind data.

Contribution

It introduces a novel pipeline integrating symbolic approximation, clustering, and expert validation for large-scale time series labeling in physics.

Findings

Successfully classifies solar wind phenomena like CMEs and stream regions.

Demonstrates scalable, systematic labeling with minimal expert effort.

Provides a reproducible framework applicable to physical sciences data.

Abstract

Labeling or classifying time series is a persistent challenge in the physical sciences, where expert annotations are scarce, costly, and often inconsistent. Yet robust labeling is essential to enable machine learning models for understanding, prediction, and forecasting. We present the \textit{Clustering and Indexation Pipeline with Human Evaluation for Recognition} (CIPHER), a framework designed to accelerate large-scale labeling of complex time series in physics. CIPHER integrates \textit{indexable Symbolic Aggregate approXimation} (iSAX) for interpretable compression and indexing, density-based clustering (HDBSCAN) to group recurring phenomena, and a human-in-the-loop step for efficient expert validation. Representative samples are labeled by domain scientists, and these annotations are propagated across clusters to yield systematic, scalable classifications. We evaluate CIPHER on the task of classifying solar wind phenomena in OMNI data, a central challenge in space weather research, showing that the framework recovers meaningful phenomena such as coronal mass ejections and stream interaction regions. Beyond this case study, CIPHER highlights a general strategy for combining symbolic representations, unsupervised learning, and expert knowledge to address label scarcity in time series across the physical sciences. The code and configuration files used in this study are publicly available to support reproducibility.