Research map / Probabilistic and scientific modeling / Dynamical systems
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation
Yuan Gao, Hao Wu, Fan Xu, Yanfei Xiang, Ruijian Gou, Ruiqi Shu, Qingsong Wen, Xian Wu, Kun Wang, Xiaomeng Huang
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 |
|---|---|---|---|
| subtract climatological mean from periodic input variables (ablation) | NeuralOM · Salinity (23 layers) | ACC: 0.1066 -> 0.6412 | Improved |
| subtract climatological mean from periodic input variables (ablation) | NeuralOM · Sea surface height | RMSE: 0.2427 -> 0.1375 | Improved |
| add progressive residual correction instead of a single model (ablation) | NeuralOM · GLORYS12 simulation | RMSE: 0.6692 -> 0.6009 | Improved |
| add physics-inspired edge interactions (PEI) (ablation) | NeuralOM · GLORYS12 simulation | ACC: 0.5166 -> 0.6058 | Improved |
| add sum aggregation path in multi-scale adaptive node aggregation (ablation) | NeuralOM · GLORYS12 simulation | RMSE: 0.7037 -> 0.6009 | Improved |
| add mean aggregation path in multi-scale adaptive node aggregation (ablation) | NeuralOM · GLORYS12 simulation | RMSE: 0.6978 -> 0.6009 | Improved |
| use NeuralOM instead of WenHai at 60-day lead | ocean simulation · GLORYS12 60-day | normalized RMSE: 0.8091 -> 0.7014 | Improved |
| use NeuralOM with forecast atmospheric forcing | ocean forecasting · GLORYS12 35-day | RMSE: 1.30 -> 0.68 vs FourCastNet | Improved |
| apply atmospheric foundation model (CirT) to ocean simulation | CirT · GLORYS12 60-day | ACC: 0.0081 ACC | Hurt |
Closest papers by meaning
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting (NeurIPS 2026 · similarity 0.87)
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution (NeurIPS 2025 · similarity 0.86)
- Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting (NeurIPS 2026 · similarity 0.86)
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs (ICLR 2024 · similarity 0.86)
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.85)
- Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates (ICML 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.
