Full waveform (FW) LiDAR systems have proven their effectiveness to map forest biophysical variables in the last two decades, owing to their ability of measuring, with high accuracy, forest vertical structures. The Global Ecosystem Dynamics Investigation (GEDI) system on board the International Space Station (ISS) is the latest FW spaceborne LiDAR instrument for the continuous observation of Earth's forests. FW systems rely on very sophisticated pre-processing steps to generate a priori metrics in order to leverage their capabilities for the accurate estimation of the aforementioned forest characteristics. The ever-expanding volume of acquired GEDI data, which to date comprises more than 25 billion acquired unfiltered shots, and along with the pre-processed data, amounting to more than 90 TB of data, raises new challenges in terms of adapted preprocessing methods for the suitable exploitation of such a huge and complex amount of LiDAR data. To overcome the issues related to the generation of relevant metrics from GEDI data, we propose a new metric-free approach to estimate canopy dominant heights (H_dom) and wood volume (V) of Eucalyptus plantations over five different regions in Brazil. To avoid metric computation, we leverage deep learning techniques and, more in detail, convolutional neural networks with the aim to analyze the GEDI Level 1B geolocated waveforms. Performance comparisons were conducted between four convolutional neural network (CNN) variants using GEDI waveform data (either untouched, or subsetted) and a metric based Random Forest regressor (RF). Additionally, we tested if our framework can improve the generalization of the models to different distant regions. First, the models were trained using data from all the study regions. Cross validated results showed that the CNN based models compared well against their RF counterpart for both H_dom and V. The RMSE on the estimation of H_dom from the CNN based models varied between 1.54 and 1.94 m with a coefficient of determination (R²) between 0.86 and 0.91, while the RF model produced an accuracy on H_dom estimates of 1.45 m (R² = 0.92). For V, CNN based estimations ranged from 27.76 to 33.33 m³.ha⁻¹ (R² between 0.82 and 0.88), while for RF, the RMSE was 27.61 m³.ha⁻¹ (R² = 0.88). Next, model generalization was assessed by means of a spatial transfer experiment. For H_dom, both the CNN and RF approaches showed similar performances to a global model, however, the CNN based approach showed higher variability on the estimation accuracy, and the variability was related to the forest structure between the trained and tested data (similar tree heights yield better accuracies). For the estimation of V, considering both approaches, the accuracy was dependent on the allometric relationship between H_dom and V in the training and testing regions while lower accuracies on V were obtained when the testing and training regions exhibited a different allometric relationship.

在过去的二十年里，全波形 (FW) LiDAR 系统已经证明了它们在映射森林生物物理变量方面的有效性，因为它们能够以高精度测量森林垂直结构。国际空间站 (ISS) 上的全球生态系统动力学调查 (GEDI) 系统是最新的 FW 星载 LiDAR 仪器，用于连续观测地球森林。FW 系统依靠非常复杂的预处理步骤来生成先验指标，以利用其功能来准确估计上述森林特征。获取的 GEDI 数据量不断扩大，迄今为止包括超过 250 亿次获取的未过滤镜头，以及预处理数据，总计超过 90 TB 的数据，在合适的预处理方法方面提出了新的挑战，以适当利用如此庞大而复杂的 LiDAR 数据量。为了克服与从 GEDI 数据生成相关指标相关的问题，我们提出了一种新的无指标方法来估计冠层优势高度（H _dom ) 和巴西五个不同地区桉树种植园的木材体积 (V)。为了避免度量计算，我们利用深度学习技术，更详细地利用卷积神经网络，旨在分析 GEDI 1B 级地理定位波形。使用 GEDI 波形数据（未受影响或子集）和基于度量的随机森林回归器 (RF) 在四个卷积神经网络 (CNN) 变体之间进行性能比较。此外，我们测试了我们的框架是否可以改进模型对不同远距离区域的泛化。首先，使用来自所有研究区域的数据训练模型。交叉验证的结果表明，基于 CNN 的模型与它们的 RF 对应模型在两个H _dom和 V.从基于 CNN 的模型估计H _dom的 RMSE 在1.54 和 1.94  m之间变化，确定系数 ( R ² ) 在 0.86 和 0.91 之间，而 RF 模型对H _dom估计产生的精度为 1.45  m ( R ² = 0.92)。对于 V，基于 CNN 的估计范围从 27.76 到 33.33 m ³。ha ^-1 ( R ²在0.82和0.88之间)，而对于RF，RMSE是27.61 m ³。公顷^-1 ( R ²  = 0.88）。接下来，通过空间转移实验评估模型泛化。对于H _dom，CNN 和 RF 方法都表现出与全局模型相似的性能，但是，基于 CNN 的方法在估计精度上表现出更高的变异性，并且变异性与训练数据和测试数据之间的森林结构有关（类似树高度产生更好的精度）。对于 V 的估计，考虑到这两种方法，精度取决于训练和测试区域中H _dom和 V之间的异速生长关系，而当测试和训练区域表现出不同的异速生长关系时，V 的准确度较低。