Research map / Probabilistic and scientific modeling / Molecules and proteins
MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction
Shuo Tang, Jian Xu, Jiadong Zhang, Yi Chen, Qizhao Jin, Lingdong Shen, Chenglin Liu, Shiming Xiang
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 DTGF, TGS and TGCA modules with 185-level inputs | Qwen2.5-VL-7B baseline · MP-Bench | MC-main accuracy: 56.26 -> 72.37 | Improved |
| add the three modules | Qwen2.5-VL-7B baseline · MP-Bench | T/F accuracy: 68.33 -> 87.13 | Improved |
| add the three modules | LLaVA-NeXT-Video-7B baseline · MP-Bench | RSW accuracy: 45.22 -> 53.64 | Improved |
| add DTGF alone (ablation) | MMLM Qwen2.5-VL · MP-Bench (5k subset) | MC-main accuracy: 42.73 -> 53.28 | Improved |
| add DTGF alone (ablation) | MMLM Qwen2.5-VL · MP-Bench (5k subset) | T/F accuracy: 58.47 -> 57.23 | Hurt |
| add TGS alone (ablation) | MMLM Qwen2.5-VL · MP-Bench (5k subset) | T/F accuracy: 58.47 -> 54.81 | Hurt |
| add TGS alone (ablation) | MMLM Qwen2.5-VL · MP-Bench (5k subset) | MC-main accuracy: 42.73 -> 44.57 | No clear effect |
| add TGCA alone (ablation) | MMLM Qwen2.5-VL · MP-Bench (5k subset) | T/F accuracy: 58.47 -> 60.35 | Improved |
| add TGCA to DTGF+TGS (ablation) | DTGF+TGS · MP-Bench (5k subset) | T/F accuracy: 56.63 -> 79.21 | Improved |
| add TGS to DTGF+TGCA (full model) (ablation) | DTGF+TGCA · MP-Bench (5k subset) | MC-sub accuracy: 32.61 -> 47.37 | Improved |
| use 12h window instead of 1h (ablation) | MMLM · MP-Bench (5k subset) | MC-main accuracy: 54.29 -> 58.27 | Improved |
| use 12h window instead of 6h (ablation) | MMLM · MP-Bench (5k subset) | MC-main accuracy: 58.01 -> 58.27 | No clear effect |
Closest papers by meaning
- WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation (ICML 2026 · similarity 0.87)
- RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts (NeurIPS 2025 · similarity 0.86)
- Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models (NeurIPS 2024 · similarity 0.86)
- EWMoE: An Effective Model for Global Weather Forecasting with Mixture-of-Experts (AAAI 2025 · similarity 0.85)
- Integrating Multi-Source Data for Long Sequence Precipitation Forecasting (AAAI 2025 · similarity 0.85)
- HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting (ICLR 2025 · similarity 0.84)
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.
