Mapping the spatial distribution of tree species selected by elephants (Loxodonta africana) in Venetia-Limpopo Nature Reserve using Sentinel-2 imagery

2021 ◽  
Author(s):  
S. E. Nkosi ◽  
E. Adam ◽  
A. S. Barrett ◽  
L. R. Brown
Keyword(s):  
Spatial Distribution ◽  
Tree Species ◽  
Nature Reserve ◽  
Loxodonta Africana ◽  
Sentinel 2

scholarly journals Tree Species Mapping on Sentinel-2 Satellite Imagery with Weakly Supervised Classification and Object-Wise Sampling

Forests ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 1413
Author(s):  
Svetlana Illarionova ◽  
Alexey Trekin ◽  
Vladimir Ignatiev ◽  
Ivan Oseledets
Keyword(s):  
Spatial Distribution ◽  
Satellite Imagery ◽  
Tree Species ◽  
Dominant Species ◽  
Specific Information ◽  
Data Set ◽  
Weakly Supervised ◽  
Markup Adjustment ◽  
Tree Type ◽  
Sentinel 2

Information on forest composition, specifically tree types and their distribution, aids in timber stock calculation and can help to better understand the biodiversity in a particular region. Automatic satellite imagery analysis can significantly accelerate the process of tree type classification, which is traditionally carried out by ground-based observation. Although computer vision methods have proven their efficiency in remote sensing tasks, specific challenges arise in forestry applications. The forest inventory data often contain the tree type composition but do not describe their spatial distribution within each individual stand. Therefore, some pixels can be assigned a wrong label in the semantic segmentation task if we consider each stand to be homogeneously populated by its dominant species. Another challenge is the spatial distribution of individual stands within the study area. Classes are usually imbalanced and distributed nonuniformly that makes sampling choice more critical. This study aims to enhance tree species classification based on a neural network approach providing automatic markup adjustment and improving sampling technique. For forest species markup adjustment, we propose using a weakly supervised learning approach based on the knowledge of dominant species content within each stand. We also propose substituting the commonly used CNN sampling approach with the object-wise one to reduce the effect of the spatial distribution of forest stands. We consider four species commonly found in Russian boreal forests: birch, aspen, pine, and spruce. We use imagery from the Sentinel-2 satellite, which has multiple bands (in the visible and infrared spectra) and a spatial resolution of up to 10 meters. A data set of images for Leningrad Oblast of Russia is used to assess the methods. We demonstrate how to modify the training strategy to outperform a basic CNN approach from F1-score 0.68 to 0.76. This approach is promising for future studies to obtain more specific information about stands composition even using incomplete data.

scholarly journals Spatial distribution of spruce trees in the nature reserve 'Jankove bare' on mt. Kopaonik

2009 ◽  
pp. 191-204
Author(s):  
Branko Stajic ◽  
Milivoj Vuckovic ◽  
Marko Smiljanic
Keyword(s):  
Spatial Distribution ◽  
Tree Growth ◽  
Environmental Conditions ◽  
National Park ◽  
Nature Reserve ◽  
Distance Methods ◽  
Study Results

The methodology and applicability of the study of spatial distribution of trees in Serbian forestry have been insufficiently reported and presented. This paper, based on mathematical?statistical principles, analyses the method of spatial distribution of spruce trees in the Nature Reserve 'Jankove Bare' in the National Park 'Kopaonik'. The following methods in the group of distance methods were applied: Kotar's method (1993), T2?method, and the index of distance dispersion (Johnson, Zimmer, 1985). The study results in a pure uneven-aged spruce stand based on all three methods showed that spruce trees are randomly distributed over the stand area. Therefore, environmental conditions in the study stand can be regarded as homogeneous and equally suitable for tree growth, and there are no significant interactions between the trees, which could cause a higher competition between the trees for nutrients, water, etc.

scholarly journals National mapping and estimation of forest area by dominant tree species using Sentinel-2 data

2020 ◽  
Author(s):  
Johannes Breidenbach ◽  
Lars T. Waser ◽  
Misganu Debella-Gilo ◽  
Johannes Schumacher ◽  
Johannes Rahlf ◽  
...  
Keyword(s):  
Tree Species ◽  
Deciduous Forest ◽  
National Level ◽  
National Forest Inventory ◽  
Forest Area ◽  
Forest Resource ◽  
Species Specific ◽  
Minimum Numbers ◽  
Generate Model ◽  
Sentinel 2

Nation-wide Sentinel-2 mosaics were used with National Forest Inventory (NFI) plot data for modelling and subsequent mapping of spruce-, pine- and deciduous-dominated forest in Norway at a 16m×16m resolution. The accuracies of the best model ranged between 74% for spruce and 87% for deciduous forest. An overall accuracy of 90% was found on stand level using independent data from more than 42,000 stands. Errors mostly resulting from a forest mask reduced the model accuracies by approximately 10%. The produced map was subsequently used to generate model-assisted (MA) and post stratified (PS) estimates of species-specific forest area. At the national level, efficiencies of the estimates increased by 20% to 50% for MA and up to 90% for PS. Greater minimum numbers of observations constrained the use of PS. For MA estimates of municipalities, efficiencies improved by up to a factor of 8 but were sometimes also less than 1. PS estimates were always equally as or more precise than direct and MA estimates but were applicable in fewer municipalities. The tree species prediction map is part of the Norwegian forest resource map and is used, among others, to improve maps of other variables of interest such as timber volume and biomass.

scholarly journals Modeling the Spatial Distribution of Three Typical Dominant Wetland Vegetation Species’ Response to the Hydrological Gradient in a Ramsar Wetland, Honghe National Nature Reserve, Northeast China

Water ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 2041
Author(s):  
Dandan Yan ◽  
Zhaoqing Luan ◽  
Dandan Xu ◽  
Yuanyuan Xue ◽  
Dan Shi
Keyword(s):  
Spatial Distribution ◽  
Water Level ◽  
Northeast China ◽  
Nature Reserve ◽  
Wetland Vegetation ◽  
Vegetation Communities ◽  
National Nature Reserve ◽  
Carex Lasiocarpa ◽  
Vegetation Species ◽  
Calamagrostis Angustifolia

Water level fluctuations resulting from natural and anthropogenic factors have been projected to affect the functions and structures of wetland vegetation communities. Therefore, it is important to assess the impact of the hydrological gradient on wetland vegetation. This paper presents a case study on the Honghe National Nature Reserve (HNNR) in the Sanjiang Plain, located in Northeast China. In this study, 210 plots from 18 sampling line transects were sampled in 2011, 2012, and 2014 along the hydrological gradient. Using a Gaussian logistic regression model, we determined a relationship between three wetland plant species and a hydrologic indicator—a combination of the water level and soil moisture—and then applied that relationship to simulate the distribution of plants across a larger landscape by the geographic information system (GIS). The results show that the optimum ecological amplitude of Calamagrostis angustifolia to the hydrological gradient based on the probability of occurrence model was [0.09, 0.41], that of Carex lasiocarpa was [0.35, 0.57], and that of Carex pseudocuraica was [0.49, 0.77]. The optimum of Calamagrostis angustifolia was 0.25, Carex lasiocarpa was 0.46, and Carex pseudocuraica was 0.63. Spatial distribution probability maps were generated, as were maps detailing the distribution of the most suitable habitats for wetland vegetation species. Finally, the model simulation results were verified, showing that this approach can be employed to provide an accurate simulation of the spatial distribution pattern of wetland vegetation communities. Importantly, this study suggests that it may be possible to predict the spatial distribution of different species from the hydrological gradient.

scholarly journals Tree Species Classification Using Hyperion and Sentinel-2 Data with Machine Learning in South Korea and China

2019 ◽  
Vol 8 (3) ◽  
pp. 150 ◽  
Author(s):  
Joongbin Lim ◽  
Kyoung-Min Kim ◽  
Ri Jin
Keyword(s):  
Machine Learning ◽  
Tree Species ◽  
North Korea ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Species Classification ◽  
Tree Species Classification ◽  
Hyperion Data ◽  
Study Sites ◽  
Sentinel 2

Remote sensing (RS) has been used to monitor inaccessible regions. It is considered a useful technique for deriving important environmental information from inaccessible regions, especially North Korea. In this study, we aim to develop a tree species classification model based on RS and machine learning techniques, which can be utilized for classification in North Korea. Two study sites were chosen, the Korea National Arboretum (KNA) in South Korea and Mt. Baekdu (MTB; a.k.a., Mt. Changbai in Chinese) in China, located in the border area between North Korea and China, and tree species classifications were examined in both regions. As a preliminary step in developing a classification algorithm that can be applied in North Korea, common coniferous species at both study sites, Korean pine (Pinus koraiensis) and Japanese larch (Larix kaempferi), were chosen as targets for investigation. Hyperion data have been used for tree species classification due to the abundant spectral information acquired from across more than 200 spectral bands (i.e., hyperspectral satellite data). However, it is impossible to acquire recent Hyperion data because the satellite ceased operation in 2017. Recently, Sentinel-2 satellite multispectral imagery has been used in tree species classification. Thus, it is necessary to compare these two kinds of satellite data to determine the possibility of reliably classifying species. Therefore, Hyperion and Sentinel-2 data were employed, along with machine learning techniques, such as random forests (RFs) and support vector machines (SVMs), to classify tree species. Three questions were answered, showing that: (1) RF and SVM are well established in the hyperspectral imagery for tree species classification, (2) Sentinel-2 data can be used to classify tree species with RF and SVM algorithms instead of Hyperion data, and (3) training data that were built in the KNA cannot be used for the tree classification of MTB. Random forests and SVMs showed overall accuracies of 0.60 and 0.51 and kappa values of 0.20 and 0.00, respectively. Moreover, combined training data from the KNA and MTB showed high classification accuracies in both regions; RF and SVM values exhibited accuracies of 0.99 and 0.97 and kappa values of 0.98 and 0.95, respectively.

Sign in / Sign up

Export Citation Format

Share Document