Scholarlink

<p>The prediction of sea surface partial pressure of carbon dioxide (<i>p</i>CO<sub>2</sub>) in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change. We applied the Spatiotemporal Convolutional Long Short-Term Memory (ST-ConvLSTM) model, integrating key environmental factors including sea surface temperature (SST), sea surface salinity (SSS), and chlorophyll <i>a</i> (Chl <i>a</i>), to predict and analyze sea surface <i>p</i>CO<sub>2</sub> in the South China Sea. The model demonstrated high accuracy in short-term predictions (1 month), with a mean absolute error (MAE) of 0.394, a root mean square error (RMSE) of 0.659, and a coefficient of determination (<i>R</i><sup>2</sup>) of 0.998. For long-term predictions (12 months), the model maintained its predictive capability, with an MAE of 0.667, RMSE of 1.255, and <i>R</i><sup>2</sup> of 0.994. Feature importance analysis revealed that sea surface <i>p</i>CO<sub>2</sub> and SST were the main drivers of the model’s predictions, whereas Chl <i>a</i> and SSS had relatively minor impacts. The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean, where it successfully captured the spatiotemporal variation in <i>p</i>CO<sub>2</sub> with small prediction errors. The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface <i>p</i>CO<sub>2</sub> in the South China Sea, offering new insights into global carbon cycling and climate change. This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of sea surface pCO2 in the South China Sea using Spatiotemporal Convolutional LSTM model

  • 期刊论文

  • 发表日期：

    2025年8月26日

查看全文
  • Shuang Li,
  • Yu Gao,
  • Jiannan Gao,
  • Yaqi Zhao,
  • Peng Hao,
  • Jinbao Song,
  • Chengcheng Yu

摘要

The prediction of sea surface partial pressure of carbon dioxide (pCO2) in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change. We applied the Spatiotemporal Convolutional Long Short-Term Memory (ST-ConvLSTM) model, integrating key environmental factors including sea surface temperature (SST), sea surface salinity (SSS), and chlorophyll a (Chl a), to predict and analyze sea surface pCO2 in the South China Sea. The model demonstrated high accuracy in short-term predictions (1 month), with a mean absolute error (MAE) of 0.394, a root mean square error (RMSE) of 0.659, and a coefficient of determination (R2) of 0.998. For long-term predictions (12 months), the model maintained its predictive capability, with an MAE of 0.667, RMSE of 1.255, and R2 of 0.994. Feature importance analysis revealed that sea surface pCO2 and SST were the main drivers of the model’s predictions, whereas Chl a and SSS had relatively minor impacts. The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean, where it successfully captured the spatiotemporal variation in pCO2 with small prediction errors. The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface pCO2 in the South China Sea, offering new insights into global carbon cycling and climate change. This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.