多特征参数支持的红树林遥感信息提取——以广东省为例  

Remote sensing information extraction for mangrove forests based on multi-feature parameters:A case study of Guangdong Province

作　　者：王煜淼 李胜 东春宇 杨刚 WANG Yumiao;LI Sheng;DONG Chunyu;YANG Gang(Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources,Shenzhen 518000,China;Department of Geography and Spatial Information Techniques,Ningbo University,Ningbo 315211,China;Shenzhen Data Management Center of Planning and Natural Resource,Shenzhen 518000,China)

机构地区：[1]自然资源部城市国土资源监测与仿真重点实验室,深圳518000 [2]宁波大学地理空间信息技术系,宁波315211 [3]深圳市规划和自然资源数据管理中心,深圳518000

出　　处：《自然资源遥感》2024年第1期95-102,共8页Remote Sensing for Natural Resources

基　　金：自然资源部城市国土资源监测与仿真重点实验室开放课题“联合时序SAR与光学遥感数据的广东省红树林精准识别研究”(编号:KF-2021-06-089);宁波市重大科技攻关项目“海岸带碳库资源遥感调查与生态碳汇估算关键技术研发”(编号:20212ZDYF020049);浙江省自然科学基金探索青年项目“基于多源遥感时序数据的大区域农作物早期识别方法研究”(编号:LQ22D010007)共同资助。

摘　　要：准确的红树林分布信息对红树林保护和管理具有重要意义。尽管已有不少红树林遥感制图研究,但如何有效利用多源遥感特征来提高红树林制图精度仍有待探索。首先,利用多源遥感数据提取光谱、散射、纹理和地形等时序特征来设计15种特征组合;然后,利用随机森林模型分析不同特征组合在红树林识别中的精度,从而获得最优特征组合;最后,基于Google Earth Engine(GEE)平台获取2021年广东省10 m空间分辨率的红树林分布。结果显示,冬季光谱特征的重要性最高,特征类型越丰富对应制图精度越高,最优特征组合的总体精度为92.25%,Kappa系数为0.91。通过探究红树林识别中的最优特征组合,在多特征参数支持下实现广东省红树林信息提取,研究成果可为大范围红树林精准制图提供科学参考。Accurate mangrove forest distribution information is critical to the conservation and management of mangrove forests.Despite extensive studies on the remote sensing mapping of mangrove forests,it is necessary to improve their mapping accuracy by effectively utilizing multi-source remote sensing features.First,this study designed 15 feature associations using temporal features,including spectral,scattering,texture,and terrain features,which were extracted from multi-source remote sensing data.Then,using a random forest model,it analyzed the accuracy of different feature associations in mangrove forest identification,obtaining the optimal feature association.Finally,this study mapped the 10-m-resolution mangrove forest distribution of Guangdong Province in 2021 based on platform Google Earth Engine(GEE).The results show that spectral features in winter exhibited the highest importance,with richer feature types corresponding to higher mapping accuracy.The optimal feature association yielded overall accuracy of 92.25%and a Kappa value of 0.91.Overall,this study extracted information on mangrove forests in Guangdong based on multi-feature parameters and the optimal feature association.The results of this study will provide a scientific reference for accurate mapping of mangrove forests on a large scale.

关 键 词：红树林提取 多源遥感数据 GEE 机器学习 广东省 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]