Forest height is an important forest biophysical parameter which is used to derive important information about forest ecosystems, such as forest above ground biomass. In this paper, the potential of combining Polarimetric Synthetic Aperture Radar (PolSAR) variables with LiDAR measurements for forest height estimation is investigated. This will be conducted using different machine learning algorithms including Random Forest (RFs), Rotation Forest (RoFs), Canonical Correlation Forest (CCFs) and Support Vector Machine (SVMs). Various PolSAR parameters are required as input variables to ensure a successful height retrieval across different forest heights ranges. The algorithms are trained with 5000 LiDAR samples (less than 1% of the full scene) and different polarimetric variables. To examine the dependency of the algorithm on input training samples, three different subsets are identified which each includes different features: subset 1 is quiet diverse and includes non-vegetated region, short/sparse vegetation (0–20 m), vegetation with mid-range height (20–40 m) to tall/dense ones (40–60 m); subset 2 covers mostly the dense vegetated area with height ranges 40–60 m; and subset 3 mostly covers the non-vegetated to short/sparse vegetation (0–20 m) .The trained algorithms were used to estimate the height for the areas outside the identified subset. The results were validated with independent samples of LiDAR-derived height showing high accuracy (with the average R² = 0.70 and RMSE = 10 m between all the algorithms and different training samples). The results confirm that it is possible to estimate forest canopy height using PolSAR parameters together with a small coverage of LiDAR height as training data.

森林高度是重要的森林生物物理参数，可用于获取有关森林生态系统的重要信息，例如地面生物量以上的森林。本文研究了将极化合成孔径雷达（PolSAR）变量与LiDAR测量值相结合来估算森林高度的潜力。这将使用不同的机器学习算法来进行，包括随机森林（RF），旋转森林（RoF），规范相关森林（CCF）和支持向量机（SVM）。需要使用各种PolSAR参数作为输入变量，以确保在不同森林高度范围内成功检索高度。使用5000个LiDAR样本（不到整个场景的1％）和不同的极化变量对算法进行训练。要检查算法对输入训练样本的依赖性，确定了三个不同的子集，每个子​​集包含不同的特征：子集1安静多样，包括无植被区，短/稀疏植被（0–20 m），中程高度（20–40 m）至高/密的植被一个（40-60 m）；子集2大部分覆盖了高度为40-60 m的茂密植被区；子集3大部分覆盖了非植被至短/稀疏的植被（0–20 m）。训练有素的算法用于估计已识别子集以外区域的高度。结果独立于LiDAR衍生的高度的独立样本进行了验证，这些样本显示出较高的准确度（平均R 中等高度（20–40 m）至高/密（40–60 m）的植被；子集2大部分覆盖了高度为40-60 m的茂密植被区；子集3大部分覆盖了非植被至短/稀疏的植被（0–20 m）。训练有素的算法用于估计已识别子集以外区域的高度。结果独立于LiDAR衍生的高度的独立样本进行了验证，这些样本显示出较高的准确度（平均R 中等高度（20–40 m）至高/密（40–60 m）的植被；子集2大部分覆盖了高度为40-60 m的茂密植被区；子集3大部分覆盖了非植被至短/稀疏的植被（0–20 m）。训练有素的算法用于估计已识别子集以外区域的高度。结果独立于LiDAR衍生的高度的独立样本进行了验证，这些样本显示出较高的准确度（平均R 所有算法和不同训练样本之间的差异为² = 0.70，RMSE = 10 m。结果证实可以使用PolSAR参数以及少量的LiDAR高度作为训练数据来估计森林冠层高度。