本文排版定稿已在中国知网网络首发,如需阅读全文请打开知网首页,并搜索该论文题目即可查看。
基于ICESat–2/ATLAS与地统计学的森林生物量空间异质性分析
Spatial Heterogeneity Analysis of Forest Biomass Based on Spaceborne LiDAR ICESat–2/ATLAS and Geostatistics
-
摘要: 以ICESat–2/ATLAS数据为数据源,结合54块实测样地,构建机器学习模型并对光斑足迹的地上生物量进行预测,采用Moran's I和半变异函数对反演的森林AGB空间自相关和异质性进行研究。结果表明:梯度提升回归树(GBRT)模型具有较好的预测精度(R2=0.90,RMSE=11.08 t/hm2);香格里拉市森林生物量的最佳拟合半变异函数模型为指数模型(C0=0.12,C0 + C=0.87,A0=10200 m);与普通克里格相比,序贯高斯条件模拟得到的AGB空间分布图具有较好的一致性(r=0.59**,d=0.70)。AGB的空间分异能够被地形因子解释,在解释力方面,海拔最大,坡向次之,坡度最小;基于星载激光雷达ICESat–2/ATLAS数据的森林AGB反演精度较高(Pp=81.43%),为地统计分析提供了可靠的数据源。因此,基于星载激光雷达与地统计学相结合的方法,能较好地实现森林AGB的空间异质性分析。Abstract: Using ICESat–2/ATLAS data as data source, combined with 54 measured plots, a machine learning model was built and the AGB of the spot footprint was predicted. Moran's I and semi-variance function were used to study the spatial autocorrelation and heterogeneity of inverse forest AGB. The results showed that the Gradient Boost Regression Tree (GBRT) model had a great prediction accuracy (R2=0.90, RMSE=11.08 t/hm2). The best-fitting semi-variogram function model of forest biomass was exponential model in Shangri-La (C0=0.12, C0 + C=0.87, A0=10200 m). Compared with ordinary Kriging, the spatial distribution of AGB obtained by the Sequential Gaussian Conditional Simulation had better consistency (r=0.59**, d=0.70). The spatial differentiation of AGB could be explained by topographic factors. In terms of explanatory power, elevation was the largest, slope was the second, and slope was the least. The inversion accuracy of forest AGB based on spaceborne LiDAR ICESat-2/ATLAS data was high (Pp=81.43%), which provided a reliable data source for geostatistical analysis. Therefore, the method based on spaceborne LiDAR and geostatistics can greatly analyze the spatial heterogeneity of forest AGB.