Research map / Probabilistic and scientific modeling / Molecules and proteins
The Seismic Wavefield Common Task Framework
Alexey Yermakov, Yue Zhao, Marine Denolle, Yiyu Ni, Philippe Martin Wyder, Judah Goldfeder, Stefano Riva, Jan P. Williams, David Zoro, Amy Sara Rude, Matteo Tomasetto, Joe Germany and 4 more
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 |
|---|---|---|---|
| use RNN models (LSTM, ODE-LSTM) rather than other model classes | forecasting/reconstruction baselines · Global wavefields and DAS CTF | AvgScore: LSTM 13.18 and ODE-LSTM 5.71 vs zeros 0.0 (global) | Improved |
| use statistical DMD methods versus RNNs for denoising | Higher Order DMD / Opt DMD · Global wavefields | AvgScore: Higher Order DMD 0.0, Opt DMD -25.76 vs LSTM 13.18 | Hurt |
| use time-series foundation models (Chronos, Moirai, Panda, TabPFN, LLMTime, Sundial) zero-shot | foundation models · Global wavefields | AvgScore: -100.0 for all six | Hurt |
| use Sundial foundation model for short-term forecasting | Sundial · DAS | E1/E7/E9: E1 49.57 (best) | Improved |
| RNNs on limited-data short-term forecast | LSTM / ODE-LSTM · Global wavefields | E7: LSTM -40.07, ODE-LSTM -67.04 | Hurt |
| multi-metric scoring instead of single score | CTF evaluation · Global wavefields and DAS | per-task scores: Top-average RNNs score poorly on E7 and E9 | Mixed |
Closest papers by meaning
- Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms (NeurIPS 2025 · similarity 0.87)
- A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations (ICLR 2025 · similarity 0.85)
- A Novel Diffusion Model for Pairwise Geoscience Data Generation with Unbalanced Training Dataset (AAAI 2025 · similarity 0.84)
- Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition (ICML 2025 · similarity 0.83)
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting (NeurIPS 2026 · similarity 0.83)
- SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey (NeurIPS 2024 · similarity 0.82)
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.
