Search

Urban tree species identification is the basis for studying the urban-environment coordination mechanism at the species level. Although the gradual maturity of remote sensing data and related research including light detection and ranging (LiDAR) provides a good foundation for the realization of this technology, multiple reasons such as cost, data openness, study scope limitations, and weakness of traditional morphological features make such data still challenging to apply to subtropical urban trees with heterogeneous canopy structures and high biodiversity. To address the problem, we developed two large-scale LiDAR morphological features in this research by, 1) modifying the rotate image method based on the axisymmetric structure to make it easier to use, and 2) developing an innovative adaptive ellipsoid method to extract the canopy features of the non-axisymmetric structure effectively. We evaluated the ability of these two morphological features to describe 12 common subtropical urban tree (SUT) species in Hong Kong growing in urban parks and streets, obtaining an accuracy of 88%. And the advantages of the proposed method are demonstrated by comparison with existing LiDAR morphological features and mean decrease accuracy (MDA) analysis. Our results illustrated that the rotate image feature based on the axisymmetric structure did not perform as well as the adaptive ellipsoid feature based on the non-axisymmetric structure in SUT, and the combined application of these two new morphological features got further accuracy improvement. The method proposed in this study had significant advantages in terms of accuracy, the number of species included, and generalisation capability compared to existing studies on the identification of subtropical urban trees. [ABSTRACT FROM AUTHOR]

Hyperspectral data has been widely used in species discrimination of plants with rich spectral information in hundreds of spectral bands, while the availability of hyperspectral data has hindered its applications in many specific cases. The successful operation of the Chinese satellite, Gaofen-5 (GF-5), provides potentially promising new hyperspectral dataset with 330 spectral bands in visible and near infrared range. Therefore, there is much demand for assessing the effectiveness and superiority of GF-5 hyperspectral data in plants species mapping, particularly mangrove species mapping, to better support the efficient mangrove management. In this study, mangrove forest in Mai Po Nature Reserve (MPNR), Hong Kong was selected as the study area. Four dominant native mangrove species were investigated in this study according to the field surveys. Two machine learning methods, Random Forests and Support Vector Machines, were employed to classify mangrove species with Landsat 8, Simulated Hyperion and GF-5 data sets. The results showed that 97 more bands of GF-5 over Hyperion brought a higher over accuracy of 87.12%, in comparison with 86.82% from Hyperion and 73.89% from Landsat 8. The higher spectral resolution of 5 nm in GF-5 was identified as making the major contribution, especially for the mapping of Aegiceras corniculatum. Therefore, GF-5 is likely to improve the classification accuracy of mangrove species mapping via enhancing spectral resolution and thus has promising potential to improve mangrove monitoring at species level to support mangrove management. [ABSTRACT FROM AUTHOR]

• Delineated individual plant communities in tropical forests from airborne LiDAR data. • Investigated the relationships between plant species diversity and canopy structure. • Species richness and Shannon index are accurately predicted by random forest models. • Species richness is primarily determined by return number metrics. • Shannon index is influenced by both return number and canopy height metrics. Tropical forests are widely regarded as the Earth's most important ecosystems, yet they are severely threatened by anthropogenic disturbances. Rapid and extensive monitoring of forest structure and biodiversity is crucial for developing ecologically sound conservation and restoration strategies. Airborne light detection and ranging (LiDAR) can effectively monitor three-dimensional forest canopy structures. Traditionally, LiDAR-based plant diversity estimation has relied on individual tree-based and area-based approaches. However, these approaches face significant challenges in tropical forests due to their complex canopy structures and diverse plant compositions. Therefore, by proposing a novel community-based approach, this study aims to examine the relationship between field-derived biodiversity indices and LiDAR-derived canopy structural metrics of plant communities in a species-rich ForestGEO forest dynamic plot in tropical Hong Kong. Our goal is to determine whether canopy structural metrics extracted from airborne LiDAR data can serve as a robust and efficient alternative for expediting plant diversity monitoring in highly dense and diverse tropical forests. Our results indicate that an integration watershed segmentation technique (for automatic patch-scale plant community delineation), LiDAR-derived canopy structural metrics, and machine learning-based random forest regression analysis can provide accurate predictions of community-based species diversity indices. Among various diversity indices, species richness and the Shannon-Wiener index are most accurately estimated using LiDAR-derived metrics. This study reveals that species richness is predominantly influenced by the existence of multi-layered canopy structures, whereas the Shannon-Wiener index is associated with both multi-layered structures and canopy morphologies. Overall, our findings showcase the immense potential of airborne LiDAR data in advancing the monitoring of structure and biodiversity in dense-canopy and species-rich tropical forests in a spatially explicit manner. [ABSTRACT FROM AUTHOR]

• The species-level estimation model can describe the urban AGB dynamics. • Natural disturbances can have significant effects on urban vegetation AGB. • Existing AGB products underestimate biomass of the high-density urban parks. Aboveground biomass (AGB) estimation for urban parks has received less attention as an essential component of the global carbon cycle. Current studies focus on vast areas of natural or planted forests. The characteristics of these study areas make the use of homogenised vegetation grids (using remote sensing data) and plots (using field data) as the basic research unit a consensus. However, this data-level simplification can be significantly affected by buildings when applied to urban areas. Developing tree species identification methods based on remote sensing provides us with new ideas to explore urban AGB estimation methods at the species level. To this end, we developed a species-level AGB estimation model to address the AGB distribution in urban parks by combining multitemporal airborne light detection and ranging (LiDAR), optical remote sensing data, and field data from two urban parks in Hong Kong through a two-step strategy. First, we constructed optimal remote sensing feature-AGB mapping relationships for each sample species using sample data from the study area, the tropical allometric growth equation, and the five regression algorithms. We then explored a tree species identification method based on the annual vegetation phenological change index (AVPCI), which allowed us to quickly obtain species distribution maps for the study area. Combining these two steps allowed us to obtain AGB information for the study area based on species-level mapping relationships based on species distributions. In the model validation, the correlation between the estimated and true values of the remote sensing feature and AGB mapping relationship was 0.91, with a significantly lower normalised root mean square deviation (RMSE). The overall accuracy of the sample tree species identification was 87.5%, which was better than the results of existing studies. The final AGB obtained was also within the reasonable interval of existing studies. In addition, with the model proposed in this study, we noted that the super typhoon Mangkhut in 2018 reduced the AGB in the study area by 32.6% and demonstrated the significant underestimation of high-density urban areas in existing global biomass products. The model developed in this study addresses the problems of existing AGB estimation methods for urban vegetation represented by urban parks while effectively contributing to understanding AGB distribution and short-term carbon cycle dynamics in urban scenarios. [ABSTRACT FROM AUTHOR]