OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
Authors: Bin Lu, Ze Zhao, Luyu Han, Xiaoying Gan, Yuntao Zhou, Lei Zhou, Luoyi Fu, Xinbing Wang, Chenghu Zhou, Jing Zhang
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 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. |
| Researcher Affiliation | Academia | 1Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China 2School of Oceanography, Shanghai Jiao Tong University, Shanghai, China 3Department of Computer Science, Shanghai Jiao Tong University, Shanghai, China 4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China. |
| Pseudocode | Yes | Algorithm 1 Optimization algorithm of OXYGENERATOR |
| Open Source Code | No | The paper does not provide an explicit statement or link for open-source code for the methodology described. |
| Open Datasets | Yes | We collect over 6 billion historical observation records from 1920 to 2023 of dissolved oxygen and relevant environmental factors, including temperature, salinity, nitrates, phosphates, silicates, and chlorophyll, from multiple public databases (Table 4 and Figure 9 in Appendix). |
| Dataset Splits | Yes | Therefore, we treat the deoxygenation reconstruction as a regression task independent of current-time observations and perform 4-fold cross testing of the collected data. For each fold, we randomly choose 25% observation data as the test data and the rest as training and validation. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | LOXYGENERATOR = Lr + λ(RN + RP ), where λ is the ratio coefficient of two losses. |