In this study, we build multiple data sets based on magnetograms provided by the Solar Dynamics Observatory (SDO)/SHARP, SDO/Helioseismic and Magnetic Imager, and the Full-disk vector Magnetograph (FMG) on board the Advanced Space-based Solar Observatory (ASO-S) for ≥M-class flare prediction within 24 hr. We compare the performance of four models for flare forecasting, including a convolutional neural network (CNN), CNN-BiLSTM, vision transformer (ViT), and MViT. We study the impact of magnetograms with single, multiple, and mixed active regions (ARs) on model performance. Furthermore, we investigate the generalization capability of the models by using multisource data collected within the same period, as well as single-source data gathered across different periods. This is the first time that we utilize ASO-S/FMG data for flare forecasting. Finally, we fairly compare the forecasting performance of the MViT model with that of NASA/CCMC under the same prediction time and AR number. The main results are as follows. (1) Transformer-based models outperform CNN-based models, while spatiotemporal models significantly surpass nonspatiotemporal models. (2) The inclusion of a magnetogram with multiple ARs diminishes the forecasting performance of the models, whereas the use of magnetogram data with a single AR for flare prediction yields superior results compared to data with multiple ARs. (3) The MViT model reaches a true skill score of 0.707 when utilizing the FMG data with a single AR, achieving exceptional performance for solar flare forecasting. (4) The MViT model demonstrates better generalization ability across both single-source data and multisource data. (5) The MViT model demonstrates a performance comparable to current state-of-the-art methods (i.e., NASA/CCMC) in flare prediction.
1 April 2024 in Research in Astronomy and Astrophysics
The Solar Polar-orbit Observatory (SPO), proposed by Chinese scientists, is designed to observe the solar polar regions in an unprecedented way with a spacecraft traveling in a large solar inclination angle and a small ellipticity. However, one of the most significant challenges lies in ultra-long-distance data transmission, particularly for the Magnetic and Helioseismic Imager (MHI), which is the most important payload and generates the largest volume of data in SPO. In this paper, we propose a tailored lossless data compression method based on the measurement mode and characteristics of MHI data. The background out of the solar disk is removed to decrease the pixel number of an image under compression. Multiple predictive coding methods are combined to eliminate the redundancy utilizing the correlation (space, spectrum, and polarization) in data set, improving the compression ratio. Experimental results demonstrate that our method achieves an average compression ratio of 3.67. The compression time is also less than the general observation period. The method exhibits strong feasibility and can be easily adapted to MHI.
1 April 2026 in Research in Astronomy and Astrophysics
The Vision-Language Models (VLMs) have achieved breakthrough progress in general knowledge domains, yet adaptation to specialized scientific fields remains challenging due to multimodal representation shifts and the limited integration of domain-specific knowledge. To address the limitations of general-purpose VLMs when applied to solar physics image recognition, analysis, and reasoning, we propose the first vision–language model specifically designed for solar physics, referred to as JinWu Vision–Language (JW-VL). The model integrates multi-wavelength observational data from both space-based and ground-based telescopes, encompassing representative spectral bands spanning the photosphere, chromosphere, and corona. Built upon a cross-modal alignment knowledge distillation framework, JW-VL learns a joint visual–semantic embedding that enables end-to-end modeling from raw solar observational data to downstream tasks, including solar image recognition, solar activity analysis via image-based question answering, and optical character recognition (OCR), while also supporting the construction of a multi-band, cross-instrument solar image benchmark dataset. Furthermore, as a demonstration of interdisciplinary applicability, we developed a “Daily Solar Activity Reports” agent comprising core modules for solar activity level assessment, significant active region characterization, magnetic field complexity analysis, potential space weather impact assessment, and recommended observational focus activate regions. By enabling multimodal reasoning over multi-band solar observational data, JW-VL bridges raw observations and diverse downstream tasks, and provides a reusable methodological framework for vision–language modeling in solar physics.
28 July 2026 in Research in Astronomy and Astrophysics
We present the first deployment of an end-to-end autonomous control system driven by a large language model (LLM) on an operational solar telescope—the Solar Full-disk Multi-layer Magnetograph, named JW-ASTClaw. This system employs a multi-agent framework adopting a decoupled three-layer architecture (perception–decision–execution) interconnected through the Model Context Protocol, which addresses real-time adaptive scheduling under complex environmental conditions while achieving high portability: the perception and decision logic are reused unchanged across instruments, requiring only telescope-specific command interfaces to be adapted. Three perception agents—data-quality-agent, cloud-analyzer-agent, and flare-detector-agent—encode senior observer expertise, including wind jitter detection via limb-ring standard deviation, projected-circle zonal cloud analysis, and multi-band active region identification, as LLM-callable rules, while a central reasoning engine performs multi-source fusion and conflict resolution. The system supports graceful degradation from cloud LLM to local inference and finally to rule-based fallback, designed for remote field stations with unstable connectivity. Cross-season validation on archival data demonstrates 100% cloud detection with zero false positives across 10 distinct observation dates, with active-region counts and positions closely matching the NOAA Solar Region Summary (SRS) reports (102 versus 100 across 10 separate validation dates). These capabilities significantly improve scientific-intent-driven observation accessibility, enable rapid flare response for space weather monitoring, enhance data usability under adverse conditions, and increase observability during partially cloudy periods. This work represents the first concrete engineering step toward the embodied intelligent solar telescope concept, providing a validated foundation for the transition from automated scheduling to AI-driven autonomous observation.