# OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning

arXiv: https://arxiv.org/abs/2405.07233 · HTML: https://mlsanity.com/paper/2405.07233/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 57 references that are in the map.
- First posted on arXiv 12 May 2024.

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks](https://mlsanity.com/paper/2108.00298/) (2021)
- [Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer](https://mlsanity.com/paper/2205.13947/) (2022)
- [Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders](https://mlsanity.com/paper/2305.18612/) (2023)
- [Competitive Physics Informed Networks](https://mlsanity.com/paper/2204.11144/) (2022)
- [RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting](https://mlsanity.com/paper/2106.06064/) (2021)
- [GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks](https://mlsanity.com/paper/2311.04245/) (2023)
- [Southern Ocean Dynamics Under Climate Change: New Knowledge Through Physics-Guided Machine Learning](https://mlsanity.com/paper/2310.13916/) (2023)
- [Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models](https://mlsanity.com/paper/2311.08421/) (2023)
- [Graph-Based Deep Learning for Sea Surface Temperature Forecasts](https://mlsanity.com/paper/2305.09468/) (2023)

## Built on by (most cited first, 5 of 5)

- [A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation](https://mlsanity.com/paper/2504.17200/) (2025)
- [CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective](https://mlsanity.com/paper/2504.14282/) (2025)
- [Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle](https://mlsanity.com/paper/2605.13021/) (2026)
- [Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting](https://mlsanity.com/paper/2503.21588/) (2025)
- [REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers](https://mlsanity.com/paper/2610.03888/) (2026)

## Abstract (arXiv)

Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem. Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and human activities. Besides, due to the high-cost data collection, the historical observations are severely sparse, leading to big challenge for precise reconstruction. In this work, we propose OxyGenerator, the first deep learning based model, to reconstruct the global ocean deoxygenation from 1920 to 2023. Specifically, to address the heterogeneity across large temporal and spatial scales, we propose zoning-varying graph message-passing to capture the complex oceanographic correlations between missing values and sparse observations. Additionally, to further calibrate the uncertainty, we incorporate inductive bias from dissolved oxygen (DO) variations and chemical effects. Compared with in-situ DO observations, OxyGenerator significantly outperforms CMIP6 numerical simulations, reducing MAPE by 38.77%, demonstrating a promising potential to understand the "breathless ocean" in data-driven manner.