融合ICESat⁃2和GEDI的多源遥感冠层高度估测  

Estimation of Canopy Height is Conducted by Integrating Multisource Remote Sensing Data from ICESat-2 and GEDI

作　　者：梁华君 别强 石莹 邓心茹 李欣璋 LIANG Huajun;BIE Qiang;SHI Ying;DENG Xinru;LI Xinzhang(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China;Post-doctorate Workstation,Sanhe Digital Surverying and Geographic Information Technology Company,Tianshui 741000,China)

机构地区：[1]兰州交通大学测绘与地理信息学院,甘肃兰州730070 [2]地理国情监测技术应用国家地方联合工程研究中心,甘肃兰州730070 [3]三和数码博士后科研工作站,甘肃天水741000

出　　处：《遥感技术与应用》2025年第1期202-214,共13页Remote Sensing Technology and Application

基　　金：国家自然科学基金青年科学基金项目“基于遥感和WRF模式的干旱区绿洲冷岛效应研究”(42101096);自然资源部城市国土资源监测与仿真重点实验室“基于多源数据的生态系统碳汇价值评估技术研究”(KF-20230801)共同资助。

摘　　要：新一代星载激光雷达冰、云和陆地高程卫星二代(ICESat-2)和全球生态系统动力学调查(GEDI)在森林冠层高度估算中具有独特的优势。融合两种激光雷达数据不仅能够增加冠层高度反演的样本量,还能实现不同数据之间的空间互补。首先采用随机森林—递归特征消除法(RFRFE)筛选光子特征参数,结合逐步线性回归(SLR)、随机森林(RF)、轻量级梯度提升机(LightGBM)、随机森林逐步线性回归(RF-SLR)、粒子群优化随机森林(PSO-RF)5种融合模型进行适用性分析,选择最优模型构建点尺度冠层高度数据集,并联合多源遥感影像反演祁连山国家公园冠层高度图。最后使用GEDI脚点足迹和样地调查数据将反演结果与现有冠层高度产品进行对比。结果表明:①粒子群优化随机森林(PSO-RF)模型的融合效果最好(R^(2)=0.71;RMSE=3.15 m;MAE=2.66 m)。②基于PSO-RF融合的点尺度冠层高度集的反演模型精度最高(R^(2)=0.56;RMSE=3.02 m;MAE=2.38 m)。③与现有冠层高度产品相比,反演结果的精度较高(基于GEDI脚点足迹:R^(2)=0.43;RMSE=4.50 m;MAE=3.59 m),与样地调查数据相比,反演结果的误差较小(R^(2)=0.36;RMSE=3.15 m;MAE=2.56 m)。研究结果可反映祁连山国家公园植被空间分布格局,为森林资源管理、碳汇计算和生态资源保护提供科学依据。The next-generation satellite LiDAR systems,including the Ice,Cloud,and land Elevation Satel⁃lite-2(ICESat-2)and the Global Ecosystem Dynamics Investigation(GEDI),offer unique advantages in esti⁃mating forest canopy height.The fusion of these two LiDAR datasets not only increases the sample size for can⁃opy height retrieval but also allows for spatial complementarity between different datasets.First,the Random Forest-Recursive Feature Elimination(RF-RFE)method was used to select photon feature parameters.Subse⁃quently,five fusion models—Stepwise Linear Regression(SLR),Random Forest(RF),Light Gradient Boosting Machine(LightGBM),Random Forest with Stepwise Linear Regression(RF-SLR),and Particle Swarm Optimization Random Forest(PSO-RF)—were analyzed for their applicability.The optimal model was selected to construct a point-scale canopy height dataset,which was then combined with multi-source remote sensing imagery to map the canopy height in Qilian Mountain National Park.Finally,the retrieval results were compared with existing canopy height products using GEDI footprint data and field survey data.The results showed that:(1)the Particle Swarm Optimization Random Forest(PSO-RF)model provided the best fusion performance(R^(2)=0.71;RMSE=3.15 m;MAE=2.66 m);(2)the retrieval model based on PSO-RF fu⁃sion of point-scale canopy height data achieved the highest accuracy(R^(2)=0.56;RMSE=3.02 m;MAE=2.38 m);(3)compared to existing canopy height products,the retrieval results demonstrated higher accuracy(based on GEDI footprint data:R^(2)=0.43;RMSE=4.50 m;MAE=3.59 m),and the errors were smaller when compared to field survey data(R^(2)=0.36;RMSE=3.15 m;MAE=2.56 m).The findings reflect the spatial distribution pattern of vegetation in Qilian Mountain National Park and provide scientific support for for⁃est resource management,carbon sequestration estimation,and ecological resource conservation.

关 键 词：ICESat⁃2 GEDI 数据融合 冠层高度反演 粒子群优化的随机森林 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置] S771.8[自动化与计算机技术—控制科学与工程]