基于资源一号高光谱影像的养殖海域富营养化反演

doi:10.13474/j.cnki.11-2246.2026.0613

测绘通报 ›› 2026, Vol. 0 ›› Issue (6): 84-91.doi: 10.13474/j.cnki.11-2246.2026.0613

• 学术研究 • 上一篇

基于资源一号高光谱影像的养殖海域富营养化反演

陈红梅¹, 陈家钰^2,3, 陈芸芝^2,3, 罗冬莲¹, 游远新¹, 许春晓¹, 张伟铃¹

1. 福建省水产研究所, 福建厦门 361013;
2. 福州大学空间数据挖掘与信息共享教育部重点实验室, 福建福州 350108;
3. 卫星空间信息技术综合应用国家地方联合工程研究中心, 福建福州 350108

收稿日期:2025-10-22 发布日期:2026-07-09
通讯作者: 罗冬莲。E-mail:295807046@qq.com
作者简介:陈红梅(1979—),女,硕士,助理研究员,主要研究方向为海洋遥感、地理信息系统和调查规划。E-mail:563898690@qq.com
基金资助:
国家重点研发计划(2024YFD2400300);福建省省属公益类科研院所基本科研专项(2023R1012005);福建省海洋服务与渔业高质量发展专项资金(FJHY-YYKJ-2024-1-14;FJHY-YYKJ-2024-1-18-2)

Inversion of eutrophication in aquaculture areas based on ZY-1 hyperspectral imagery

CHEN Hongmei¹, CHEN Jiayu^2,3, CHEN Yunzhi^2,3, LUO Donglian¹, YOU Yuanxin¹, XU Chunxiao¹, ZHANG Weiling¹

1. Fisheries Research Institute of Fujian, Xiamen 361013, China;
2. Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350108, China;
3. National and Local Joint Engineering Research Center for Comprehensive Application of Satellite and Spatial Information Technology, Fuzhou 350108, China

Received:2025-10-22 Published:2026-07-09

摘要/Abstract

摘要： [目的] 构建基于资源一号高光谱影像的养殖海域富营养化反演模型,能够为海洋渔业管理、海洋环境保护提供科学参考。[方法]本文以福建省诏安湾和东山湾为研究区域,基于实测光谱反射率、实测水质数据及资源一号高光谱影像,筛选出与化学需氧量(COD)、活性磷酸盐(DIP)及无机氮(DIN)对数相关性最高的4个波段组合作为特征波段,构建CatBoost、随机森林及多元线性回归3个模型;进行精度评价,确定最优模型,进而反演富营养化状况,并进行时空特征分析。[结果]CatBoost模型展现出更高的反演精度,COD、DIP、DIN的决定系数R²分别为0.80、0.71、0.88。[结论]诏安湾富营养化指数季节变化明显,秋季部分区域富营养化指数较高,春季和冬季较低。东山湾水质总体优于诏安湾,不同时期绝大部分区域富营养化指数较低,水质状况较好。

关键词: 富营养化, 水产养殖, 资源一号, CatBoost, 随机森林

Abstract: [Purposes]A nutrient enrichment inversion model for aquaculture sea areas based on ZY-1 hyperspectral images is constructed to provide scientific reference for marine fishery management and marine environmental protection.[Methods]Using Zhao'an Bay and Dongshan Bay in Fujian province as research areas,we select 4 spectral bands with the strongest correlation to the logarithm of COD,DIP,and DIN based on measured spectral reflectance,water quality data,and ZY-1 hyperspectral imagery.Three models (CatBoost,random forest,and multiple linear regression) are developed.After precision evaluation,the optimal model is identified to assess eutrophication status and conduct spatiotemporal feature analysis.[Findings]Results show that the CatBoost model demonstrated higher inversion accuracy.The R² values for COD,DIP,and DIN are 0.80,0.71,and 0.88,respectively.[Conclusions]The inversion results reveal significant seasonal variations in Zhaoan Bay's eutrophication index,showing higher levels in some areas during autumn and lower levels in spring and winter.Dongshan Bay exhibit better overall water quality than Zha'an Bay,with most regions maintaining low eutrophication indices across different periods,indicating relatively good water conditions.

Key words: eutrophication, aquaculture, ZY-1 satellite, CatBoost, random forest

中图分类号:

P237

陈红梅, 陈家钰, 陈芸芝, 罗冬莲, 游远新, 许春晓, 张伟铃. 基于资源一号高光谱影像的养殖海域富营养化反演[J]. 测绘通报, 2026, 0(6): 84-91.

CHEN Hongmei, CHEN Jiayu, CHEN Yunzhi, LUO Donglian, YOU Yuanxin, XU Chunxiao, ZHANG Weiling. Inversion of eutrophication in aquaculture areas based on ZY-1 hyperspectral imagery[J]. Bulletin of Surveying and Mapping, 2026, 0(6): 84-91.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://tb.chinasmp.com/CN/10.13474/j.cnki.11-2246.2026.0613

http://tb.chinasmp.com/CN/Y2026/V0/I6/84

参考文献

[1] 张宏建,王冰,周健,等.基于BP神经网络的内陆河流水质遥感反演[J].华中师范大学学报(自然科学版),2022,56(2):333-341.
[2] MIRZAEI R,SAKIZADEH M.Comparison of interpolation methods for the estimation of groundwater contamination in Andimeshk-Shush Plain,Southwest of Iran[J].Environmental Science and Pollution Research,2016,23(3):2758-2769.
[3] YANG Haibo,DU Yao,ZHAO Hongling,et al.Water quality chl-a inversion based on spatio-temporal fusion and convolutional neural network[J].Remote Sensing,2022,14(5):1267.
[4] 王波,黄津辉,郭宏伟,等.基于遥感的内陆水体水质监测研究进展[J].水资源保护,2022,38(3):117-124.
[5] 周艺,周伟奇,王世新,等.遥感技术在内陆水体水质监测中的应用[J].水科学进展,2004,15(3):312-317.
[6] YU Yan,CHEN Shengbo,QIN Wenhan,et al.A semi-empirical chlorophyll-a retrieval algorithm considering the effects of Sun glint,bottom reflectance,and non-algal particles in the optically shallow water zones of Sanya Bay using SPOT6 data[J].Remote Sensing,2020,12(17):2765.
[7] 陈保锋,陈芸芝,陈红梅.基于Sentinel-2的福建典型沿海养殖区化学需氧量反演[J].测绘通报,2025(4):75-81.
[8] LU Qikai,SI Wei,WEI Lifei,et al.Retrieval of water quality from UAV-borne hyperspectral imagery:a comparative study of machine learning algorithms[J].Remote Sensing,2021,13(19):3928.
[9] SONG Wei,YINGLAN A,WANG Yuntao,et al.Study on remote sensing inversion and temporal-spatial variation of Hulun Lake water quality based on machine learning[J].Journal of Contaminant Hydrology,2024,260:104282.
[10] CHEN Baofeng,CHEN Yunzhi,CHEN Hongmei.An interpretable CatBoost model guided by spectral morphological features for the inversion of coastal water quality parameters[J].Water,2024,16(24):3615.
[11] CAO Jiaju,WEN Xingping,LUO Dayou,et al.Study on water quality inversion model of Dianchi Lake based on Landsat 8 data[J].Journal of Spectroscopy,2022,2022(1):3341713.
[12] YAO Yanjuan,ZHU Li,WU Chuanqing,et al.Water quality remote sensing monitoring research in China based on the HJ-1 satellite data[C]//Proceedings of 2010 IEEE International Geoscience and Remote Sensing Symposium.Honolulu:IEEE,2010:620-623.
[13] 陈红梅.基于Sentinel-2 MSI的养殖海湾富营养化反演研究[J].渔业研究,2024,46(6):653-663.
[14] 徐汉超,邰贺,杨静.基于资源一号数据的棋盘山水库水质信息提取[J].海洋测绘,2022,42(1):64-68.
[15] 邹景忠,董丽萍,秦保平.渤海湾富营养化和赤潮问题的初步探讨[J].海洋环境科学,1983,2(2):41-54.
[16] 刘瑶,李俊生,肖晨超,等.资源一号02D高光谱影像内陆水体叶绿素a浓度反演[J].遥感学报,2022,26(1):168-178.
[17] 唐军武,田国良,汪小勇,等.水体光谱测量与分析Ⅰ:水面以上测量法[J].遥感学报,2004,8(1):37-44.
[18] 卜博,张方方,李俊生,等.基于GF6-WFV数据的中国东部典型湖库叶绿素a浓度反演[J].遥感技术与应用,2024,39(1):170-184.
[19] OSTROUMOVA L,GUSEV G,VOROBEV A,et al.CatBoost:unbiased boosting with categorical features[C]//Proceedings of 2017 Neural Information Processing Systems.Moscow:[s.n.],2017.
[20] HUANG Guomin,WU Lifeng,MA Xin,et al.Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions[J].Journal of Hydrology,2019,574:1029-1041.
[21] 陈点点,陈芸芝,冯险峰,等.基于超参数优化CatBoost算法的河流悬浮物浓度遥感反演[J].地球信息科学学报,2022,24(4):780-791.
[22] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[23] 杨庆振,郭敏,范新成.基于随机森林算法的高光谱遥感作物分类[J].测绘与空间地理信息,2023,46(4):149-151.
[24] 方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.
[25] 卢雪梅,苏华.基于OLCI数据的福建近海悬浮物浓度遥感反演[J].环境科学学报,2020,40(8):2819-2827.
[26] 曾伟生,唐守正.非线性模型对数回归的偏差校正及与加权回归的对比分析[J].林业科学研究,2011,24(2):137-143.
[27] YANG Zhiming,REITER M,MUNYEI N.Estimation of chlorophyll-a concentrations in diverse water bodies using ratio-based NIR/Red indices[J].Remote Sensing Applications:Society and Environment,2017,6:52-58.
[28] ESCOTO J E,BLANCO A C,ARGAMOSA R J,et al.Pasig River water quality estimation using an empirical ordinary least squares regression model of Sentinel-2 satellite images[J].The International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2021,XLVI-4/W6-2021:161-168.
[29] ELSAYED S,GAD M,FAROUK M,et al.Using optimized two and three-band spectral indices and multivariate models to assess some water quality indicators of qaroun lake in Egypt[J].Sustainability,2021,13(18):10408.
[30] MISHRA S,MISHRA D R.Normalized difference chlorophyll index:a novel model for remote estimation of chlorophyll-a concentration in turbid productive waters[J].Remote Sensing of Environment,2012,117:394-406.
[31] 刘阁.适用于不同光学特征二类水体的叶绿素a浓度遥感估算方法研究[D].南京:南京师范大学,2016.

基于资源一号高光谱影像的养殖海域富营养化反演

Inversion of eutrophication in aquaculture areas based on ZY-1 hyperspectral imagery

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王昊辉, 马丁, 邓宏烨, 刘一航, 王振坤, 朱维, 王伟玺. 三维可视性对城市住宅价格的影响研究[J]. 测绘通报, 2026, 0(3): 150-155.
[2]	王青青, 张中流, 卢刚. 卫星反演测深在库容监测中的应用[J]. 测绘通报, 2026, 0(2): 7-11.
[3]	杨新茹, 王勇, 车向红, 姜驰, 孙擎, 刘纪平. 融合光学-雷达-物候特征的烟草种植区识别方法研究——以云南宣威为例[J]. 测绘通报, 2026, 0(1): 25-31.
[4]	谷钰泽, 邓孺孺, 李嘉怡, 郭昱, 华振群, 旷志渊, 黄迪. 北江流域叶绿素a浓度反演及富营养化评价[J]. 测绘通报, 2025, 0(6): 24-29,72.
[5]	张云菲, 钟天宇. 耦合多层次格网特征的轨迹数据提取路网方法[J]. 测绘通报, 2025, 0(6): 109-114.
[6]	郑超, 童旭东, 祝善友, 张丽娟, 殷凌锋, 林佳余. 基于多源影像数据与Otsu-RF方法的太湖蓝藻水华识别及监测[J]. 测绘通报, 2025, 0(5): 1-7.
[7]	张富杰, 王留召, 钟若飞, 许梦兵, 靳欢欢. 基于车载激光点云的路灯提取方法[J]. 测绘通报, 2025, 0(3): 46-51.
[8]	蒋铭, 张福浩, 赵习枝, 欧尔格力, 于浩. 基于多源地理数据的长时序贫困度估算——以孟加拉国为例[J]. 测绘通报, 2025, 0(3): 99-104.
[9]	徐鹏宇, 王勇, 王红雪, 高翔. SHAP解释下随机森林预测的越江盾构隧道病害发展分析[J]. 测绘通报, 2025, 0(3): 117-121.
[10]	李升海, 张俊, 唐海林. 基于改进SVM算法的Sentinel-2A MSI遥感影像水体提取[J]. 测绘通报, 2025, 0(2): 53-57,76.
[11]	李昂, 张学东, 马悦, 杨振, 李林阳. 基于手机端GNSS和音频信号的室内/室外导航场景感知模型构建与优化方法[J]. 测绘通报, 2025, 0(2): 101-107.
[12]	徐晨, 鲍帅, 刘猛猛. 祁连山脉东段未来滑坡易发性监测评价[J]. 测绘通报, 2025, 0(11): 62-69.
[13]	童皓东, 周钰炜, 沈永明. 多源时序遥感影像与GEE支持下的潮沟提取方法[J]. 测绘通报, 2025, 0(10): 43-49.
[14]	张戴新月, 刘扬, 高思岩. 基于多特征组合的建筑垃圾分类方法[J]. 测绘通报, 2024, 0(6): 59-64.
[15]	王金迪, 钱建国, 邱银国, 王志勇, 刘傅彰, 刘佳鑫. 富营养化湖泊水环境监测模拟平台研发与应用[J]. 测绘通报, 2024, 0(6): 120-126.