# VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations

arXiv: https://arxiv.org/abs/2509.21477 · HTML: https://mlsanity.com/paper/2509.21477/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 66 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Convolutional Neural Operators for robust and accurate learning of PDEs](https://mlsanity.com/paper/2302.01178/) (2023)
- [UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks](https://mlsanity.com/paper/2105.00956/) (2021)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Solving High-Dimensional PDEs with Latent Spectral Models](https://mlsanity.com/paper/2301.12664/) (2023)
- [Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs](https://mlsanity.com/paper/2011.00844/) (2020)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction](https://mlsanity.com/paper/2305.11421/) (2023)
- [Learning to Prompt with Text Only Supervision for Vision-Language Models](https://mlsanity.com/paper/2401.02418/) (2024)
- [Image-Adaptive GAN based Reconstruction](https://mlsanity.com/paper/1906.05284/) (2019)
- [OneForecast: A Universal Framework for Global and Regional Weather Forecasting](https://mlsanity.com/paper/2502.00338/) (2025)
- [What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use](https://mlsanity.com/paper/2409.08775/) (2024)
- [SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2211.12509/) (2022)
- [Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model](https://mlsanity.com/paper/2312.08403/) (2023)
- [NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation](https://mlsanity.com/paper/2505.21020/) (2025)
- [Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias](https://mlsanity.com/paper/2505.19038/) (2025)
- [Advanced Long-term Earth System Forecasting](https://mlsanity.com/paper/2505.19432/) (2025)
- [DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting](https://mlsanity.com/paper/2403.02914/) (2024)

## Abstract (arXiv)

Reconstructing subsurface ocean dynamics, such as vertical velocity fields, from incomplete surface observations poses a critical challenge in Earth science, a field long hampered by the lack of standardized, analysis-ready benchmarks. To systematically address this issue and catalyze research, we first build and release KD48, a high-resolution ocean dynamics benchmark derived from petascale simulations and curated with expert-driven denoising. Building on this benchmark, we introduce VISION, a novel reconstruction paradigm based on Dynamic Prompting designed to tackle the core problem of missing data in real-world observations. The essence of VISION lies in its ability to generate a visual prompt on-the-fly from any available subset of observations, which encodes both data availability and the ocean's physical state. More importantly, we design a State-conditioned Prompting module that efficiently injects this prompt into a universal backbone, endowed with geometry- and scale-aware operators, to guide its adaptive adjustment of computational strategies. This mechanism enables VISION to precisely handle the challenges posed by varying input combinations. Extensive experiments on the KD48 benchmark demonstrate that VISION not only substantially outperforms state-of-the-art models but also exhibits strong generalization under extreme data missing scenarios. By providing a high-quality benchmark and a robust model, our work establishes a solid infrastructure for ocean science research under data uncertainty. Our codes are available at: https://github.com/YuanGao-YG/VISION.