Speaker
Description
In the evolving landscape of 21st-century space science, forecasting space weather events such as solar flares and Coronal Mass Ejections (CMEs) is crucial yet challenging. Solar flares are intense bursts of radiation caused by the release of magnetic energy in active regions and are often accompanied by CMEs. These events can significantly impact Earth's space environment, causing disruptions in radio communication, satellite operations, and power grids. The potential for lasting damage to the worldwide economic system from such events is enormous unless early warnings, which can mitigate their effects, can be derived from solar weather data. Monitoring the temporal evolution of active regions and providing early warnings of solar flares is essential to mitigate these risks. Deep learning techniques have demonstrated significant success in detecting and predicting time-dependent events. By leveraging spatial data through convolution operations with temporal correlations, we introduce 3D Temporal Convolutional Networks (3TCNs) to efficiently analyse active region patches over time, leveraging spatial and temporal correlations. Additionally, we introduce separate predictor modules based on flare classification to enhance the performance of our EoFTCNets (Eye-on-Flare Temporal Convolutional Networks), a unified framework that enables continuous forecasting of solar flares through high-cadence (12-minute) magnetogram analysis, predicting activity up to 24 hours ahead. Our results show that the proposed architecture matches or exceeds state-of-the-art performance, achieving 99.20% accuracy for X-class, 97.50% for M-class, and 95.80% for C-class flares for a 24-hour solar flare forecasting. Furthermore, the model is computationally efficient, consuming approximately 1.55 watts on Intel Movidius Myriad X, making it well-suited for onboard deployment and real-time space weather monitoring.
