Classifying Eucalyptus forests with high spatial and spectral resolution imagery: an investigation of individual species and vegetation communities

2005 ◽  
Vol 53 (4) ◽  
pp. 337 ◽  
Author(s):  
Nicholas Goodwin ◽  
Russell Turner ◽  
Ray Merton

Mapping the spatial distribution of individual species is an important ecological and forestry issue that requires continued research to coincide with advances in remote-sensing technologies. In this study, we investigated the application of high spatial resolution (80 cm) Compact Airborne Spectrographic Imager 2 (CASI-2) data for mapping both spectrally complex species and species groups (subgenus grouping) in an Australian eucalypt forest. The relationships between spectral reflectance curves of individual tree species and identified statistical differences among species were analysed with ANOVA. Supervised maximum likelihood classifications were then performed to assess tree species separability in CASI-2 imagery. Results indicated that turpentine (Syncarpia glomulifera Smith), mesic vegetation (primarily rainforest species), and an amalgamated group of eucalypts could be readily distinguished. The discrimination of S. glomulifera was particularly robust, with consistently high classification accuracies. Eucalypt classification as a broader species group, rather than individual species, greatly improved classification performance. However, separating sunlit and shaded aspects of tree crowns did not increase classification accuracy.

2020 ◽  
Vol 12 (18) ◽  
pp. 3092 ◽  
Author(s):  
Mathieu Varin ◽  
Bilel Chalghaf ◽  
Gilles Joanisse

Species identification in Quebec, Canada, is usually performed with photo-interpretation at the stand level, and often results in a lack of precision which affects forest management. Very high spatial resolution imagery, such as WorldView-3 and Light Detection and Ranging have the potential to overcome this issue. The main objective of this study is to map 11 tree species at the tree level using an object-based approach. For modeling, 240 variables were derived from WorldView-3 with pixel-based and arithmetic feature calculation techniques. A global approach (11 species) was compared to a hierarchical approach at two levels: (1) tree type (broadleaf/conifer) and (2) individual broadleaf (five) and conifer (six) species. Five different model techniques were compared: support vector machine, classification and regression tree, random forest (RF), k-nearest neighbors, and linear discriminant analysis. Each model was assessed using 16-band or first 8-band derived variables, with the results indicating higher precision for the RF technique. Higher accuracies were found using 16-band instead of 8-band derived variables for the global approach (overall accuracy (OA): 75% vs. 71%, Kappa index of agreement (KIA): 0.72 vs. 0.67) and tree type level (OA: 99% vs. 97%, KIA: 0.97 vs. 0.95). For broadleaf individual species, higher accuracy was found using first 8-band derived variables (OA: 70% vs. 68%, KIA: 0.63 vs. 0.60). No distinction was found for individual conifer species (OA: 94%, KIA: 0.93). This paper demonstrates that a hierarchical classification approach gives better results for conifer species and that using an 8-band WorldView-3 instead of a 16-band is sufficient.


Forests ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 1047 ◽  
Author(s):  
Ying Sun ◽  
Jianfeng Huang ◽  
Zurui Ao ◽  
Dazhao Lao ◽  
Qinchuan Xin

The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon–Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (R2Margalef = 0.4562, root-mean-square error RMSEMargalef = 0.5629; R2Shannon–Wiener = 0.7948, RMSEShannon–Wiener = 0.7202; R2Simpson = 0.7907, RMSESimpson = 0.1038; and R2Pielou = 0.5875, RMSEPielou = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.


Forests ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 213
Author(s):  
Ann E. Russell ◽  
William J. Parton

Research Highlights: Ongoing land-use change and climate change in wet tropical forests can potentially drive shifts in tree species composition, representing a change in individual species within a functional group, tropical evergreen trees. The impacts on the global carbon cycle are potentially large, but unclear. We explored the differential effects of species within this functional group, in comparison with the effects of climate change, using the Century model as a research tool. Simulating effects of individual tree species on biome-level biogeochemical cycles constituted a novel application for Century. Background and Objectives: A unique, long-term, replicated field experiment containing five evergreen tree species in monodominant stands under similar environmental conditions in a Costa Rican wet forest provided data for model evaluation. Our objectives were to gain insights about this forest’s biogeochemical cycles and effects of tree species within this functional group, in comparison with climate change. Materials and Methods: We calibrated Century, using long-term meteorological, soil, and plant data from the field-based experiment. In modeling experiments, we evaluated effects on forest biogeochemistry of eight plant traits that were both observed and modeled. Climate-change simulation experiments represented two climate-change aspects observed in this region. Results: Model calibration revealed that unmodeled soil processes would be required to sustain observed P budgets. In species-traits experiments, three separate plant traits (leaf death rate, leaf C:N, and allocation to fine roots) resulted in modeled biomass C stock changes of >50%, compared with a maximum 21% change in the climate-change experiments. Conclusions: Modeled ecosystem properties and processes in Century were sensitive to changes in plant traits and nutrient limitations to productivity. Realistic model output was attainable for some species, but unusual plant traits thwarted predictions for one species. Including more plant traits and soil processes could increase realism, but less-complex models provide an accessible means for exploring plant-soil-atmosphere interactions.


Zootaxa ◽  
2009 ◽  
Vol 2178 (1) ◽  
pp. 1-72 ◽  
Author(s):  
JOACHIM SCHMIDT

This paper summarizes the taxonomic and biogeographical knowledge of Trechus species known so far from the Transhimalaya of Central Tibet and from the southern adjacent Tibetan Himalaya of Tibet and Nepal. Nine species groups are proposed, 25 new species as well as three additional new subspecies are described: The species group of Trechus antonini Deuve, 1997, with ten species newly described: T. astrophilus sp. n., T. budhaensis sp. n., T. lama sp. n., T. rarus sp. n., T. religiosus sp. n., T. singularis sp. n., T. tsampa sp. n., T. tseringi sp. n., T. yak sp. n., with an additional subspecies T. yak shogulaensis ssp. n., and T. yeti sp. n., all from South Central Tibet; the monotypic species group of the newly described Trechus chaklaensis sp. n. from South Central Tibet; the species group of Trechus dacatraianus Deuve, 1996, with two species newly described: T. bastropi sp. n., and T. mieheorum sp. n., both from South Central Tibet; the species group of Trechus franzianus Mateu & Deuve, 1979, with four species newly described: T. aedeagalis sp. n. from Far West Nepal, T. eremita sp. n. from West Nepal, T. muguensis sp. n. from West Nepal, and T. sculptipennis sp. n. from Far West Nepal; the monotypic species group of the newly described Trechus rolwalingensis sp. n. from the upper Rolwaling Valley of Central Nepal, with an additional subspecies T. rolwalingensis daldunglana ssp. n. from the lower Rolwaling Valley; the monotypic species group of the newly described Trechus solhoeyi sp. n. from South Central Tibet; the monotypic species group of the newly described Trechus stratiotes sp. n. from north eastern Saipal Himal of Far West Nepal, with an additional subspecies T. stratiotes malikasthana ssp. n. from south eastern Saipal Himal; the species group of Trechus thibetanus Jeannel, 1928, with three species newly described: T. dongulaensis sp. n., T. glabratus sp. n., and T. namtsoensis sp. n., all from South Central Tibet; the species group of Trechus wrzecionkoi Deuve, 1996, with two species newly described: T. korae sp. n., and T. martinae sp. n., both from South Central Tibet. The following two synonymies are proposed: Trechus franzianus Mateu & Deuve, 1979 = Trechus surdipennis Mateu & Deuve, 1979, syn. n.; Trechus thibetanus Jeannel, 1928 = Trechus pseudocameroni Deuve, 1996, syn. n. A key to all species known of South Central Tibet and the Tibetan Himalaya is presented for the first time, and the distributional data of all these species are mapped. The distributional maps highlight the extremely limited distribution of all wingless Trechus species. In situ speciation following the geographical separation of the range of the ancestral species and lack of subsequent range expansion of strictly edaphic species is postulated. Trechus species do not only exhibit a stronger local endemism, but the individual species groups are also endemic to several parts of the Himalayan-Tibetan Orogen. This indicates that the evolution of these Trechus species groups is directly linked to separate geological formations. Based on geological knowledge, the evolution of the species groups endemic to the Tibetan Himalaya and the Transhimalaya started already in the Miocene after these mountains were lifted up to high montane elevations. The recent distributional area of the species can therefore not be the result of range expansion during the Holocene from Pleistocene refugia outside the Tibetan Himalaya or the Transhimalaya. Instead the existence of glacial refugia can be postulated to be in the lower parts of the same mountain slope on which the species occur today. These results clearly challenge the theory of a Tibetan inland ice sheet stretching through the Himalayan transverse valleys during the Last Glacial Maximum.


Author(s):  
C. Dechesne ◽  
C. Mallet ◽  
A. Le Bris ◽  
V. Gouet-Brunet

Forest stand delineation is a fundamental task for forest management purposes, that is still mainly manually performed through visual inspection of geospatial (very) high spatial resolution images. Stand detection has been barely addressed in the literature which has mainly focused, in forested environments, on individual tree extraction and tree species classification. From a methodological point of view, stand detection can be considered as a semantic segmentation problem. It offers two advantages. First, one can retrieve the dominant tree species per segment. Secondly, one can benefit from existing low-level tree species label maps from the literature as a basis for high-level object extraction. Thus, the semantic segmentation issue becomes a regularization issue in a weakly structured environment and can be formulated in an energetical framework. This papers aims at investigating which regularization strategies of the literature are the most adapted to delineate and classify forest stands of pure species. Both airborne lidar point clouds and multispectral very high spatial resolution images are integrated for that purpose. The local methods (such as filtering and probabilistic relaxation) are not adapted for such problem since the increase of the classification accuracy is below 5%. The global methods, based on an energy model, tend to be more efficient with an accuracy gain up to 15%. The segmentation results using such models have an accuracy ranging from 96% to 99%.


2021 ◽  
Vol 13 (3) ◽  
pp. 479
Author(s):  
Shijie Yan ◽  
Linhai Jing ◽  
Huan Wang

Tree species surveys are crucial to forest resource management and can provide references for forest protection policy making. The traditional tree species survey in the field is labor-intensive and time-consuming, supporting the practical significance of remote sensing. The availability of high-resolution satellite remote sensing data enable individual tree species (ITS) recognition at low cost. In this study, the potential of the combination of such images and a convolutional neural network (CNN) to recognize ITS was explored. Firstly, individual tree crowns were delineated from a high-spatial resolution WorldView-3 (WV3) image and manually labeled as different tree species. Next, a dataset of the image subsets of the labeled individual tree crowns was built, and several CNN models were trained based on the dataset for ITS recognition. The models were then applied to the WV3 image. The results show that the distribution maps of six ITS offered an overall accuracy of 82.7% and a kappa coefficient of 0.79 based on the modified GoogLeNet, which used the multi-scale convolution kernel to extract features of the tree crown samples and was modified for small-scale samples. The ITS recognition method proposed in this study, with multi-scale individual tree crown delineation, avoids artificial tree crown delineation. Compared with the random forest (RF) and support vector machine (SVM) approaches, this method can automatically extract features and outperform RF and SVM in the classification of six tree species.


Zootaxa ◽  
2018 ◽  
Vol 4532 (4) ◽  
pp. 561
Author(s):  
MARCOS A. RAPOSO ◽  
ALAIN DUBOIS ◽  
GUY M. KIRWAN ◽  
CLAYDSON PINTO DE ASSIS ◽  
ELIZABETH HÖFLING ◽  
...  

The polytypic Straight-billed Woodcreeper Dendroplex picus (J. F. Gmelin, 1788) is one of the most complex species-groups of Dendrocolaptidae (Aves: Passeriformes), from both the nomenclatural and morphological standpoints. Firstly, its alpha taxonomy is debatable. Virtually all recent works (e.g. Aleixo 2002; Marantz et al. 2003; del Hoyo & Collar 2016) have recognized just two species in the group—Dendroplex picus and Zimmer’s Woodcreeper Dendroplex kienerii (Des Murs, 1856)—although some of the other described taxa possess singular morphological characters and well-defined ranges somewhat isolated from their geographically closest relatives (e.g. Plain-throated Woodcreeper Dendroplex picirostris Lafresnaye, 1847). Secondly, the correct genus to which to allocate taxa presently included in this group (vide Aleixo 2002) has been controversial. There is a considerable confusion as to which nominal species should be regarded as the type of Dendroplex Swainson, 1827b. Three species are involved in the dispute (Cory & Hellmayr 1925; Peters 1951; Aleixo et al. 2002; Marantz et al. 2003; Aleixo et al. 2007): Oriolus picus J. F. Gmelin, 1788; Dendrocolaptes guttatus M. H. C. Lichtenstein, 1818; and Dendrocolaptes ocellatus Spix, 1824. Here, we re-examine the nomenclatural issue and show that application of the nomen Dendroplex to the clade comprising the species-group D. picus (Aleixo et al. 2007) is based on a misunderstanding of the application of Article 70.3 of the Code (Anon. 1999) and that Dendrocolaptes ocellatus Spix, 1824, is its real type species. Consequently, the genus Dendroplex Swainson, 1827b, must be considered a junior synonym of Xiphorhynchus Swainson, 1827a. Because no generic nomen is currently available for them, we propose a new genus nomen to encompass the species originally described as Oriolus picus J. F. Gmelin, 1788, Dendroplex picirostris Lafresnaye, 1847, and Dendrornis kienerii Des Murs, 1856. 


2013 ◽  
Vol 310 ◽  
pp. 64-73 ◽  
Author(s):  
Robin Engler ◽  
Lars T. Waser ◽  
Niklaus E. Zimmermann ◽  
Marcus Schaub ◽  
Savvas Berdos ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document