Research map / Video / Video segmentation and tracking
Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images
Shunya Nagashima, Komei Sugiura
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LT-SSM (ablation) | Deep SWM · FlareBench | GMGS: 0.330 -> 0.582 | Improved |
| add DCSM (ablation) | Deep SWM · FlareBench | GMGS: 0.342 -> 0.582 | Improved |
| add ST-SSM (ablation) | Deep SWM · FlareBench | GMGS: 0.371 -> 0.582 | Improved |
| add the full SSE (DCSM and ST-SSM) (ablation) | Deep SWM · FlareBench | GMGS: 0.494 -> 0.582 | Improved |
| add DCSM to LT-SSM and ST-SSM (ablation) | Deep SWM · FlareBench | BSS>=M: 0.320 -> 0.334 | Hurt |
| use Sparse MAE instead of MAE with mask ratio 0.75 (ablation) | Deep SWM · FlareBench | GMGS: 0.286 -> 0.582 | Improved |
| use Sparse MAE instead of MAE with mask ratio 0.5 (ablation) | Deep SWM · FlareBench | GMGS: 0.420 -> 0.582 | Improved |
| use Sparse MAE instead of MAE with mask ratio 0.5 (ablation) | Deep SWM · FlareBench | pretraining MSE: 5.887 -> 2.461 | Improved |
| use S5 instead of attention (ablation) | Deep SWM · FlareBench | GMGS: 0.311 -> 0.582 | Improved |
| use S5 instead of Mamba (ablation) | Deep SWM · FlareBench | GMGS: 0.364 -> 0.582 | Improved |
| use S5 instead of attention (ablation) | Deep SWM · FlareBench | BSS>=M: 0.753 -> 0.334 | Hurt |
| use Deep SWM instead of CNN-LSTM | CNN-LSTM · FlareBench | GMGS: 0.315 -> 0.582 | Improved |
Closest papers by meaning
- SG-PALM: a Fast Physically Interpretable Tensor Graphical Model (ICML 2021 · similarity 0.84)
- Beyond 3 Million Tokens: A Multi-Modal Foundation Model for Full-Resolution Heliophysics (NeurIPS 2026 · similarity 0.83)
- SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting (NeurIPS 2024 · similarity 0.82)
- FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering (NeurIPS 2025 · similarity 0.82)
- FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views (CVPR 2025 · similarity 0.81)
- Language-Guided One-Step Diffusion Model for Nighttime Flare Removal (CVPR 2026 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
