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    

红树林三维结构和生物量的激光点云反演

谢雨桐1, 黄友菊2, 田义超1,3,4,5*, 韩广萍3, 张强1, 陶进1, 杜金泽1, 彭子杰1
  

  1. 1.北部湾大学海洋学院，资源与环境学院，广西 钦州 535011；

    2.自然资源部热带海洋生态系统与生物资源重点实验室,自然资源部第四海洋研究所,广西 北海 536015；


    3.广西壮族自治区自然资源遥感院，广西 南宁 530023；


    4.广西平陆运河与北部湾沿岸生态系统观测研究站，广西北部湾海洋环境变化与灾害重点实验室，广西 钦州 535011；

    5.北部湾大学北部湾海洋地理信息资源开发利用重点实验室，广西 钦州 535011；

    6.北部湾大学北部湾海洋发展研究中心，广西 钦州 535011；


  • 收稿日期:2025-09-01 修回日期:2025-10-22 接受日期:2025-11-12
  • 通讯作者: 田义超
  • 基金资助:
    中国国家自然科学基金委员会(Grant No.42261024); 广西八桂青年拔尖人才(八桂青年学者); 广西林业厅项目(Guilin scientific research [2022] no. 4); 广西高校人文社会科学重点研究基地“北部湾海洋发展研究中心”(Grant No. BHZKY2202); 广西高校人文社科重大项目(Grant JDZD202214); 北部湾大学高层次人才引进项目(Grant No.2019KYQD28); 广西研究生教育创新计划项目(YCSW2025623); 北部湾大学海洋科学一流学科项目(DRB003); 自然资源部热带海洋生态系统与生物资源重点实验室(2023ZD06)

Laser point cloud inversion of three-dimensional structure and biomass of mangroves

XIE Yutong1, HUANGYouju2, TIAN Yichao1,3,4,5*, HAN Guangping3, ZHANG Qiang1, TAO Jin1, DU Jinze1, PENG Zijie1   

  1. 1.College of Marine Sciences and College of Resources and Environment, Beibu Gulf University, Qinzhou, Guangxi 535011;

    2.Key Laboratory of Tropical Marine Ecosystems and Biological Resources, Ministry of Natural Resources, Fourth Institute of Oceanography, Ministry of Natural Resources, Beihai, Guangxi 536015;

    3.Guangxi Zhuang Autonomous Region Remote Sensing Institute of Natural Resources, Nanning, Guangxi 530023;

    4.Pinglu Canal and Coastal Ecosystem Observation and Research Station of the Beibu Gulf, Key Laboratory of Marine Environmental Changes and Disasters of the Beibu Gulf, Qinzhou, Guangxi 535011;

    5.Key Laboratory of Marine Geographic Information Resource Development and Utilization of the Beibu Gulf, Beibu Gulf University, Qinzhou, Guangxi 535011;

    6.Beibu Gulf University Beibu Gulf Marine Development Research Center, Qinzhou, Guangxi 535011)



  • Received:2025-09-01 Revised:2025-10-22 Accepted:2025-11-12
  • Supported by:
    the National Natural Science Foundation of China(Grant No.42261024); Guangxi Bagui Young Scholar.,Guangxi Forestry Science and Technology Promotion demonstration project(Guilin scientific research [2022] no. 4); Key Research Base of Humanities and Social Sciences in Guangxi Universities"Beibu Gulf Ocean Development Research Center"(Grant No. BHZKY2202); major projects of key research bases for humanities and social sciences in Guangxi universities(Grant JDZD202214); igh-level talent introduction project of Beibu Gulf University(Grant No.2019KYQD28); Innovation Project of Guangxi Graduate Education(YCSW2025623); Marine Science First-Class Subject, Beibu Gulf University(DRB003); Key Laboratory of Tropical Marine Ecosystems and Biological Resources, Ministry of Natural Resources(2023ZD06)

PDF (PC)

赞

摘要： 快速、准确地获取红树林三维结构参数是估算其地上生物量（Above Ground Biomass, AGB，AGB）的关键。虽然已有不少研究结合光谱数据估算红树林AGB，但利用自动机器学习（AutoML）进行模型优选并分析特征可解释性的研究仍较少。本文基于异速生长方程，利用高分辨率无人机激光点云数据提取红树林的三维结构信息，结合国产高分二号卫星影像光谱特征，以中国广西北部湾钦江入海口处的红树林为研究区域，基于点云的三维结构分析揭示了该区域红树林的冠层形态特征并以此为基础，使用AutoML Flaml框架构建了红树林AGB反演模型。结果表明：Flaml框架优选的LightGBM算法模型性能良好（训练集精度0.98，测试集精度0.84，测试集标准差11.32）；激光点云提取的结构参数（如高度统计量）以及蓝光波段、NPCI等光谱特征对AGB反演贡献显著，整体研究区红树林面积减少约50.59%，生物量损失约49.36%，但平均密度有所提高。本研究验证了激光点云结合AutoML在高效反演红树林三维结构及生物量方面的可行性与优势，为研究区红树林生态系统评估提供了重要的数据支撑和方法参考。

Abstract: Rapid and accurate acquisition of three-dimensional structural parameters of mangroves is crucial for estimating their aboveground biomass (AGB). Although many studies have combined spectral data to estimate mangrove AGB, research using automatic machine learning (AutoML) for model selection and analysis of feature interpretability is still limited. Based on allometric growth equations, this study extracted three-dimensional structural information of mangroves from high-resolution unmanned aerial vehicle (UAV) LiDAR point cloud data and combined spectral features from domestic GF-2 satellite imagery. The study area was the mangrove forest at the estuary of the Qinzhou River in Beibu Gulf, Guangxi, China. The three-dimensional structure analysis based on point cloud revealed the canopy morphology characteristics of the mangrove forest in this area. On this basis, an AGB inversion model for mangroves was constructed using the AutoML Flaml framework. The results showed that the LightGBM algorithm model selected by the Flaml framework performed well (training set accuracy 0.98, test set accuracy 0.84, test set standard deviation 11.32). Structural parameters extracted from LiDAR point cloud (such as height statistics) and spectral features such as blue band and NPCI significantly contributed to AGB inversion. The overall mangrove area in the study area decreased by approximately 50.59%, and the biomass loss was about 49.36%, but the average density increased. This study verified the feasibility and advantages of combining LiDAR point cloud and AutoML in efficiently inverting the three-dimensional structure and biomass of mangroves, providing important data support and methodological references for the assessment of the mangrove ecosystem in the study area.

Key words: Mangrove AGB, LiDAR point cloud, domestic GF-2 satellite, automatic machine learning, Guangxi, China Mangrove AGB, LiDAR point cloud, domestic GF-2 satellite, automatic machine learning, Guangxi, China