Global Cross-Time Attention Fusion for Enhanced Solar Flare Prediction from Multivariate Time Series

2025-11-16

AI Summary

Addressing the class imbalance in multivariate time-series classification caused by the rarity of intense solar flares and their skewed temporal feature distribution, this paper proposes a Transformer-based global cross-temporal attention fusion architecture. The core innovation is a learnable global attention token that dynamically aggregates discriminative patterns from non-consecutive critical time points via cross-attention, explicitly modeling long-range temporal dependencies and salient physical features. A lightweight dynamic temporal summarization module is further integrated to mitigate class imbalance effects. Evaluated on a standard solar observation dataset, the model achieves significant improvements in F1-score and recall for intense flares (≥M5.0), demonstrating the effectiveness and generalizability of the global-token-guided attention mechanism for space weather forecasting.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Multivariate time series classification is increasingly investigated in space weather research as a means to predict intense solar flare events, which can cause widespread disruptions across modern technological systems. Magnetic field measurements of solar active regions are converted into structured multivariate time series, enabling predictive modeling across segmented observation windows. However, the inherently imbalanced nature of solar flare occurrences, where intense flares are rare compared to minor flare events, presents a significant barrier to effective learning. To address this challenge, we propose a novel Global Cross-Time Attention Fusion (GCTAF) architecture, a transformer-based model to enhance long-range temporal modeling. Unlike traditional self-attention mechanisms that rely solely on local interactions within time series, GCTAF injects a set of learnable cross-attentive global tokens that summarize salient temporal patterns across the entire sequence. These tokens are refined through cross-attention with the input sequence and fused back into the temporal representation, enabling the model to identify globally significant, non-contiguous time points that are critical for flare prediction. This mechanism functions as a dynamic attention-driven temporal summarizer that augments the model's capacity to capture discriminative flare-related dynamics. We evaluate our approach on the benchmark solar flare dataset and show that GCTAF effectively detects intense flares and improves predictive performance, demonstrating that refining transformer-based architectures presents a high-potential alternative for solar flare prediction tasks.

Problem

• Addressing imbalanced solar flare data for improved prediction accuracy
• Enhancing long-range temporal modeling in multivariate solar time series
• Identifying globally significant non-contiguous time points for flare detection

Innovation

• Transformer model with global cross-time attention fusion
• Learnable tokens summarizing non-contiguous temporal patterns
• Dynamic attention-driven temporal summarizer for flare prediction