检索
E-mail
RSS

作者投稿 主编审稿 专家审稿 远程编辑

热带海洋学报

• • 上一篇    下一篇

基于机器学习算法的珠江口溶解氧快速预测预警

张现清1, 2，郭朴3，高广银4，杜佩佩4，唐德晶1, 2，李景超1，钟鸣华5，李彩1   

  1. 1. 热带海洋环境与岛礁生态全国重点实验室(中国科学院南海海洋研究所), 广东 广州 510301;

    2. 中国科学院大学, 北京 100049;

    3. 海洋环境工程中心(中国科学院南海海洋研究所), 广东 广州 510301;

    4. 广州市地质调查院(广州市海洋发展促进中心), 广东 广州 510440;

    5. 中国移动通信集团广东有限公司广州分公司, 广东 广州 510335



  • 收稿日期:2026-03-12 修回日期:2026-05-02 接受日期:2026-05-25
  • 通讯作者: 李彩
  • 基金资助:
    广东省基础与应用基础研究基金项目(2023A1515240073); 广州市南沙区科技规划项目(2022ZD001); 国家重点研发计划项目(2017YFC0506305)

Study on rapid prediction and early warning of dissolved oxygen based on machine learning algorithm in the Pearl River estuary 

ZHANG Xianqing1, 2, GUO Pu3, GAO Guangyin4, DU Peipei4, TANG Dejing1, 2, LI Jingchao1, ZHONG Minghua5, LI Cai1   

  1. 1. State Key Laboratory of Tropical Oceanography (South China Sea Institute of Oceanology, Chinese Academy of Sciences), Guangzhou 510301, China;

    2. University of Chinese Academy of Sciences, Beijing 100049, China;

    3. Marine Environmental Engineering Center (South China Sea Institute of Oceanology, Chinese Academy of Sciences), Guangzhou 510301, China;

    4. Guangzhou Geological Survey Institute, Guangzhou 510440, China;

    5. China Mobile Group Guangdong Co., Ltd. Guangzhou Branch, Guangzhou, 510335, China



  • Received:2026-03-12 Revised:2026-05-02 Accepted:2026-05-25
  • Supported by:
    Basic and Applied Basic Research Foundation of Guangdong Province(2023A1515240073); Science and Technology Planning Project of Guangzhou Nansha District, Guangzhou City China(2022ZD001); National Key Research and Development Program of China(2017YFC0506305)

PDF (PC)

赞

摘要： 溶解氧（Dissolved Oxygen, DO）含量的变化不仅影响海洋生物的生长发育与群落结构稳定，还调控着微量元素、有毒金属物质及营养物质的生物地球化学循环，而水体缺氧现象会严重威胁近岸海域生态系统健康与海洋资源的可持续利用。受全球气候变化加剧和人类活动强度持续提升的影响，珠江口海域缺氧现象日益显著，不仅损害海洋渔业资源，造成巨大的海洋经济损失，还破坏了海域生态环境平衡，基于DO预测预警结果开展该区域生态环境的管理与修复已迫在眉睫。为此，本文以长时间序列在线监测的水文、气象及水质参数与MIKE 3 FM数值模型模拟结果为基础，采用随机森林（Randon Forest, RF）、CatBoost两种高效机器学习算法，构建了珠江口未来24小时、48小时、72小时DO浓度快速预测模型。定量评价结果显示，所构建的两类预测模型均具备较高的预测精度：基于实时监测数据的预测模型在三种时间尺度下的R^2、RMSE 、MAPE依次为R2=0.965、0.921、0.889，RMSE=0.162、0.243、0.289 mg∙L-1，MAPE=1.8%、2.9%、3.5%；基于数值模拟结果的模型则依次为R2=0.965、0.921、0.889，RMSE=0.162、0.243、0.289 mg∙L-1，MAPE=1.8%、2.9%、3.5%。空间分布对比结果显示，两类预测模型均能准确表征研究区域内DO的空间分布状况，与实测结果、数值模拟结果的空间契合度较好。为清晰评估珠江口海域的水体缺氧状况，本研究依据溶解氧等级标准，并结合珠江口生态敏感性对模型预测结果进行了缺氧等级划分，研究结果可为区域水资源管理和生态保护提供可靠的科学支撑。

关键词: 溶解氧, 机器学习, 珠江口, 缺氧预警

Abstract: Dissolved oxygen (DO) is essential for the growth, development, and community structure stability of marine organisms, and plays a crucial role in regulating the biogeochemical cycles of trace elements, toxic metals, and nutrients. Hypoxia, defined as DO<2 mg∙L-1, threatens the health of coastal marine ecosystems and the sustainable utilization of marine resources. Due to intensifying global climate change and human activities, hypoxia in the Pearl River Estuary has become increasingly serious, resulting in substantial economic losses by damaging marine fishery resources and leading to the deterioration of key ecosystem characteristics that are vital for marine ecosystem sustainability. Accurate DO prediction is therefore essential for enhancing hypoxia prevention and management in the Pearl River Estuary. Based on time-series hydrometeorological and water quality parameters obtained from in situ measurements and numerical simulations, rapid prediction models for 24-hour-ahead, 48-hour-ahead, and 72-hour-ahead DO concentration were constructed using Randon Forest (RF), and CatBoost, respectively. These RF models demonstrated excellent performance, showing strong agreement with in situ measurements, with R2=0.965、0.921、0.889，RMSE=0.162、0.243、0.289 mg∙L-1，MAPE=1.8%、2.9%、3.5. And these CatBoost models also performed well, aligning closely with numerical simulations, with R2=0.965、0.921、0.889，RMSE=0.162、0.243、0.289 mg∙L-1，MAPE=1.8%、2.9%、3.5. To directly assess the hypoxia conditions, hypoxia levels were classified based on the model predictions, which could provide scientific support for water resource management and ecological protection in the Pearl River Estuary.

Key words: dissolved oxygen, machine learning, Pearl River Estuary, hypoxia