Purpose of the Review: Many LiDAR remote sensing studies over the past decade promised data fusion as a potential avenue to increase accuracy, spatial-temporal resolution, and information extraction in the final data products. Here, we performed a structured literature review to analyze relevant studies on these topics published in the last decade and the main motivations and applications for fusion, and the methods used. We discuss the findings with a panel of experts and report important lessons, main challenges, and future directions. Recent Findings: LiDAR fusion with other datasets, including multispectral, hyperspectral, and radar, is found to be useful for a variety of applications in the literature, both at individual tree level and at area level, for tree/crown segmentation, aboveground biomass assessments, canopy height, tree species identification, structural parameters, and fuel load assessments etc. In most cases, gains are achieved in improving the accuracy (e.g. better tree species classifications), and spatial-temporal resolution (e.g. for canopy height). However, questions remain regarding whether the marginal improvements reported in a range of studies are worth the extra investment, specifically from an operational point of view. We also provide a clear definition of “data fusion” to inform the scientific community on data fusion, combination, and integration. Summary: This review provides a positive outlook for LiDAR fusion applications in the decade to come, while raising questions about the trade-off between benefits versus the time and effort needed for collecting and combining multiple datasets.

In recent years, advancements in remote and proximal sensing technology have driven innovation in environmental and land surveys. The integration of various geomatics devices, such as reflex and UAVs equipped with RGB cameras and mobile laser scanners (MLS), allows detailed and precise surveys of monumental trees. With these data fusion method, we reconstructed three monumental 3D tree models, allowing the computation of tree metric variables such as diameter at breast height (DBH), total height (TH), crown basal area (CBA), crown volume (CV) and wood volume (WV), even providing information on the tree shape and its overall conditions. We processed the point clouds in software such as CloudCompare, 3D Forest, R and MATLAB, whereas the photogrammetric processing was conducted with Agisoft Metashape. Three-dimensional tree models enhance accessibility to the data and allow for a wide range of potential applications, including the development of a tree information model (TIM), providing detailed data for monitoring tree health, growth, biomass and carbon sequestration. The encouraging results provide a basis for extending the virtualization of these monumental trees to a larger scale for conservation and monitoring.

Automated tree classification from unmanned aerial vehicle (UAV) images is a challenging task with several applications in forest management and conservation. In this study, we propose UAV4Tree a Deep Learning based system that automatically classifies RGB optical images obtained by the UAV. In particular, we explore the use of augmented datasets and various deep learning models, including ResNet, DenseNet, InceptionV3, and Vision Transformer, for the classification of tree images obtained from UAVs. Our experiments show that the use of an augmented dataset can significantly improve the accuracy of the classification by approximately 10 points compared to the use of a non-augmented dataset. We also found that fine-tuning and the introduction of dropout were essential for improving the generalization ability of the models on the augmented dataset. Furthermore, the use of Super Resolution Generative Adversarial Network (SR-GAN) in the original dataset allowed us to increase the performance of some models. Our findings provide valuable insights into the use of deep learning models for automated tree classification from UAV imagery, which has significant implications for sustainable forest management and conservation.

In the context of forest inventory, there is a growing need for 3D data to produce detailed geometric information. While terrestrial laser scanning (TLS) is traditionally used for this purpose , several factors have prompted the exploration of alternative solutions, such as handheld mobile laser scanners (MLS). One key limitation of TLS is its static data acquisition, which makes it less suited for the complex and heterogeneous nature of forest environments. A primary challenge with TLS in forestry is the occlusion effect, where parts of trees (such as stems, branches, or leaves) may not be captured due to obstacles between the scanner and the target. Additionally, TLS is known for long acquisition times, which, while yielding high-quality data, may exceed the requirements for standard forest inventory tasks. The cost associated with TLS is also significant; although feasible for small forest patches, scaling these methods to larger areas would demand substantial resources. Similarly, while handheld MLS devices offer more flexibility in data acquisition and the possibility to cover a wider area in the same acquisition time, professional versions are still relatively costly, adding to the need for more affordable alternatives. This underlines the demand for a low-cost, efficient method for 3D data acquisition in forest inventories. In this study, forest structural variables obtained with a low-cost MLS (LC-MLS; Mandeye) were compared with two professional MLS devices (GeoSlam Horizon and GreenValley LiGrip H120) and a professional TLS (Trimble X7). With the open-source software 3DFin, we processed the point cloud data from all the devices, enabling the extraction of diameters at breast height (DBH) and total tree heights (TH). The LC-MLS device shows a positive bias in DBH measurements (1.62 cm), indicating it tends to overestimate compared to the TLS reference. Despite this, it demonstrates competitive quality relative to the two other MLS systems. In terms of TH, the LC-MLS has a negative bias of −2.16 m, suggesting it underestimates tree height. When compared to other professional MLS devices, the LC-MLS exhibits a higher RMSE% in TH measurements (12.97%), indicating less accuracy in tree height estimation.

Due to ever-accelerating urbanization in recent decades, exploring the contributions of trees in mitigating atmospheric carbon in urban areas has become one of the paramount concerns. Remote sensing-based approaches have been primarily implemented to estimate the tree-stand atmospheric carbon stock (CS) for the trees in parks and streets. However, a convenient yet high-accuracy computation methodology is hardly available. This study introduces an approach that has been tested for a small urban area. A data fusion approach based on a three-dimensional (3D) computation methodology was applied to calibrate the individual tree CS. This photogrammetry-based technique employed an unmanned aerial vehicle (UAV) and spherical image data to compute the total height (H) and diameter at breast height (DBH) for each tree, consequently estimating the tree-stand CS. A regression analysis was conducted to compare the results with the ones obtained with high-cost laser scanner data. Our study demonstrates the applicability of this method, highlighting its advantages even for large city areas in contrast to other approaches that are often more expensive. This approach could serve as an efficient tool for assisting urban planners in ensuring the proper utilization of the available green space, especially in a complex urban environment.