Forest canopy height is an essential parameter in estimating forest aboveground biomass (AGB), growing stock volume (GSV), and carbon storage, and it can provide necessary information in forest management activities. Light direction and ranging (LiDAR) is widely used for estimating canopy height. Considering the high cost of acquiring LiDAR data over large areas, we took a two-stage up-scaling approach in estimating forest canopy height and aimed to develop a method for quantifying the uncertainty of the estimation result. Based on the generalized hierarchical model-based (GHMB) estimation framework, a new estimation framework named RK-GHMB that makes use of a geostatistical method (regression kriging, RK) was developed. In this framework, the wall-to-wall forest canopy height and corresponding uncertainty in map unit scale are generated. This study was carried out by integrating plot data, sampled airborne LiDAR data, and wall-to-wall Ziyuan-3 satellite (ZY3) stereo images. The result shows that RK-GHMB can obtain a similar estimation accuracy (r = 0.92, MAE = 1.50 m) to GHMB (r = 0.92, MAE = 1.52 m) with plot-based reference data. For LiDAR-based reference data, the accuracy of RK-GHMB (r = 0.78, MAE = 1.75 m) is higher than that of GHMB (r = 0.75, MAE = 1.85 m). The uncertainties for all map units range from 1.54 to 3.60 m for the RK-GHMB results. The values change between 1.84 and 3.60 m for GHMB. This study demonstrates that this two-stage up-scaling approach can be used to monitor forest canopy height. The proposed RK-GHMB approach considers the spatial autocorrelation of neighboring data in the second modeling stage and can achieve a higher accuracy.

Kernel clustering of categorical data is a useful tool to process the separable datasets and has been employed in many disciplines. Despite recent efforts, existing methods for kernel clustering remain a significant challenge due to the assumption of feature independence and equal weights. In this study, we propose a self-expressive kernel subspace clustering algorithm for categorical data (SKSCC) using the self-expressive kernel density estimation (SKDE) scheme, as well as a new feature-weighted non-linear similarity measurement. In the SKSCC algorithm, we propose an effective non-linear optimization method to solve the clustering algorithm’s objective function, which not only considers the relationship between attributes in a non-linear space but also assigns a weight to each attribute in the algorithm to measure the degree of correlation. A series of experiments on some widely used synthetic and real-world datasets demonstrated the better effectiveness and efficiency of the proposed algorithm compared with other state-of-the-art methods, in terms of non-linear relationship exploration among attributes.

Synthetic aperture radar (SAR) features have 2 been demonstrated that they have the potentiality to improve 3 forest above ground biomass (AGB) estimation accuracy, 4 especially including polarimetric information. Genetic 5 algorithms (GAs) have been successfully implemented in optimal 6 feature identification, while support vector regression (SVR) has 7 great robustness in parameter estimation. The use of combined 8 GAs and SVR can improve the accuracy of forest AGB 9 estimation through simultaneously identifying the optimal SAR 10 features and selecting the SVR model parameters. In this paper, 11 14 SAR polarimetric features were extracted from C-band and 12 L-band full-polarization SAR images and worked as input SAR 13 features, respectively. C-band data was acquired on GaoFen-3 14 mission, we also call it GF-3 image. L-band data was ALOS-2 15 PALSAR-2 data. Both feature subsets from GF-3 and ALOS-2 16 PALSAR-2 and SVR hyper parameters used in the forest AGB 17 estimation were optimized by a GA processing, where 8 different 18 settings of 3 kinds of parameters, as 512 kind of different 19 combinations were applied for SVR hyper parameters searching 20 field. The results of GA-SVR performance using the two datasets 21 were presented and compared with two traditional methods: the 22 algorithm of GA feature selection companied with default SVR 23 parameters (GA +Default SVR), and the algorithm of GA feature 24 selection companied with grid searching for SVR parameter 25 selection (GA+Grid SVR). The results showed that the proposed 26 GA-SVR algorithm improved the forest AGB estimation 27 accuracy with cross-validation coefficient (CVC) of 80.21% for 28 GF-3 and 71.41% for ALOS-2 PALSAR-2 data.