Forest Type, Diversity and Biomass Estimation in Tropical Forests of Western Ghat of Maharashtra Using Geospatial Techniques

2016 ◽  
Vol 15 (4) ◽  
pp. 517-532 ◽  
Author(s):  
Sandipan Das ◽  
T. P. Singh
Keyword(s):  
Tropical Forests ◽  
Forest Type ◽  
Western Ghat ◽  
Biomass Estimation ◽  
Geospatial Techniques

Above-ground biomass estimation of Indian tropical forests using X band Pol-InSAR and Random Forest

2021 ◽  
Vol 21 ◽  
pp. 100462
Author(s):  
Sadhana Yadav ◽  
Hitendra Padalia ◽  
Sanjiv K. Sinha ◽  
Ritika Srinet ◽  
Prakash Chauhan
Keyword(s):  
Random Forest ◽  
Tropical Forests ◽  
Biomass Estimation ◽  
Above Ground Biomass ◽  
Ground Biomass ◽  
X Band

scholarly journals Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

Forests ◽  
2019 ◽  
Vol 10 (12) ◽  
pp. 1073 ◽  
Author(s):  
Li ◽  
Li ◽  
Li ◽  
Liu
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Variable Selection ◽  
Aboveground Biomass ◽  
Forest Type ◽  
Learning Algorithms ◽  
Forest Biomass ◽  
Machine Learning Algorithms ◽  
Biomass Estimation ◽  
Landsat 8

Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is well developed and extensively used, improving the accuracy of biomass estimation remains challenging. In this paper, we used China’s National Forest Continuous Inventory data and Landsat 8 Operational Land Imager data in combination with three algorithms, either the linear regression (LR), random forest (RF), or extreme gradient boosting (XGBoost), to establish biomass estimation models based on forest type. In the modeling process, two methods of variable selection, e.g., stepwise regression and variable importance-base method, were used to select optimal variable subsets for LR and machine learning algorithms (e.g., RF and XGBoost), respectively. Comfortingly, the accuracy of models was significantly improved, and thus the following conclusions were drawn: (1) Variable selection is very important for improving the performance of models, especially for machine learning algorithms, and the influence of variable selection on XGBoost is significantly greater than that of RF. (2) Machine learning algorithms have advantages in aboveground biomass (AGB) estimation, and the XGBoost and RF models significantly improved the estimation accuracy compared with the LR models. Despite that the problems of overestimation and underestimation were not fully eliminated, the XGBoost algorithm worked well and reduced these problems to a certain extent. (3) The approach of AGB modeling based on forest type is a very advantageous method for improving the performance at the lower and higher values of AGB. Some conclusions in this paper were probably different as the study area changed. The methods used in this paper provide an optional and useful approach for improving the accuracy of AGB estimation based on remote sensing data, and the estimation of AGB was a reference basis for monitoring the forest ecosystem of the study area.

scholarly journals The accuracy of species-specific allometric equations for estimating aboveground biomass in tropical moist montane forests: case study of Albizia grandibracteata and Trichilia dregeana

2019 ◽  
Vol 14 (1) ◽  
Author(s):  
Damena Edae Daba ◽  
Teshome Soromessa
Keyword(s):  
Forest Ecosystem ◽  
Aboveground Biomass ◽  
Forest Type ◽  
Model Performance ◽  
Allometric Equation ◽  
Allometric Equations ◽  
Coefficient Of Determination ◽  
Biomass Estimation ◽  
Moist Forest ◽  
Species Specific

Abstract Background Application of allometric equations for quantifying forests aboveground biomass is a crucial step related to efforts of climate change mitigation. Generalized allometric equations have been applied for estimating biomass and carbon storage of forests. However, adopting a generalized allometric equation to estimate the biomass of different forests generates uncertainty due to environmental variation. Therefore, formulating species-specific allometric equations is important to accurately quantify the biomass. Montane moist forest ecosystem comprises high forest type which is mainly found in the southwestern part of Ethiopia. Yayu Coffee Forest Biosphere Reserve is categorized into Afromontane Rainforest vegetation types in this ecosystem. This study was aimed to formulate species-specific allometric equations for Albizia grandibracteata Tuab. and Trichilia dregeana Sond. using the semi-destructive method. Results Allometric equations in form of power models were developed for each tree species by evaluating the statistical relationships of total aboveground biomass (TAGB) and dendrometric variables. TAGB was regressed against diameter at breast height (D), total height (H), and wood density (ρ) individually and in a combination. The allometric equations were selected based on model performance statistics. Equations with the higher coefficient of determination (adj.R2), lower residual standard error (RSE), and low Akaike information criterion (AIC) values were found best fitted. Relationships between TAGB and predictive variables were found statistically significant (p ≤ 0.001) for all selected equations. Higher bias was reported related to the application of pan-tropical or generalized allometric equations. Conclusions Formulating species-specific allometric equations is found important for accurate tree biomass estimation and quantifying the carbon stock. The developed biomass regression models can be applied as a species-specific equation to the montane moist forest ecosystem of southwestern Ethiopia.

scholarly journals Increasing the value of bird-habitat studies in tropical forests: choice of approach and habitat measures

2008 ◽  
Vol 18 (S1) ◽  
pp. S109-S124 ◽  
Author(s):  
David C. Lee ◽  
Stuart J. Marsden
Keyword(s):  
Tropical Forests ◽  
Forest Type ◽  
Bird Species ◽  
Alternative Methods ◽  
Design Quality ◽  
Lowland Forest ◽  
Individual Bird ◽  
Bird Habitat ◽  
Structural Variables ◽  
Habitat Variables

AbstractAn important component of many conservation studies is the assessment of bird-habitat relationships, but limited resources often lead to constraints on study design, quality and quantity of bird data, and restrict the number and types of habitat variables gathered. The aim of this study was to identify habitat features that were both relatively easy and quick to collect and powerful in identifying bird-habitat relationships. We also discuss some issues with our study and alternative approaches that may help in future bird-habitat studies in tropical forests. Twenty-four habitat measures representing geographical (e.g. altitude, topography, X and Y coordinates), vegetation structure (e.g. tree sizes), and tree floristics (abundance of 28 indicator tree species) features were collected in association with bird presence/absence data from point transects within a 1,500 ha Philippine lowland forest. We used hierarchical partitioning of regression analyses to assess which of these geographical and structural variables along with four floristics axes derived from DECORANA were the most important variables for explaining the occurrence of individual bird species and guilds. The ten most powerful variables for a range of bird species included seven geographical and three floristic variables, while the ten least important were all structural variables. There were differences in importance of individual variables across guilds, with, for example, floristics very important in canopy frugivores, and geographical variables more important for upperstorey gleaning insectivores. We stress the importance of geographical variables in linking birds to habitat at this local scale, but also suggest that efforts are made to collect some floristics data, perhaps a subset of species that represent resources for birds (e.g. Ficus spp.), people's use of the forest (e.g. dipterocarps), and indicators of forest type. While the habitat variables and approach in this study adequately identified bird-habitat relationships for most species, we suggest improvements and alternative methods that may improve results in other studies.

scholarly journals Stratification-Based Forest Aboveground Biomass Estimation in a Subtropical Region Using Airborne Lidar Data

2020 ◽  
Vol 12 (7) ◽  
pp. 1101 ◽  
Author(s):  
Xiandie Jiang ◽  
Guiying Li ◽  
Dengsheng Lu ◽  
Erxue Chen ◽  
Xinliang Wei
Keyword(s):  
Aboveground Biomass ◽  
Forest Type ◽  
Forest Stand ◽  
Airborne Lidar ◽  
Accurate Estimation ◽  
Biomass Estimation ◽  
Lidar Data ◽  
Forest Types ◽  
Estimation Model ◽  
Forest Aboveground Biomass

Species-rich subtropical forests have high carbon sequestration capacity and play important roles in regional and global carbon regulation and climate changes. A timely investigation of the spatial distribution characteristics of subtropical forest aboveground biomass (AGB) is essential to assess forest carbon stocks. Lidar (light detection and ranging) is regarded as the most reliable data source for accurate estimation of forest AGB. However, previous studies that have used lidar data have often beenbased on a single model developed from the relationships between lidar-derived variables and AGB, ignoring the variability of this relationship in different forest types. Although stratification of forest types has been proven to be effective for improving AGB estimation, how to stratify forest types and how many strata to use are still unclear. This research aims to improve forest AGB estimation through exploring suitable stratification approaches based on lidar and field survey data. Different stratification schemes including non-stratification and stratifications based on forest types and forest stand structures were examined. The AGB estimation models were developed using linear regression (LR) and random forest (RF) approaches. The results indicate the following: (1) Proper stratifications improved AGB estimation and reduced the effect of under- and overestimation problems; (2) the finer forest type strata generated higher accuracy of AGB estimation but required many more sample plots, which were often unavailable; (3) AGB estimation based on stratification of forest stand structures was similar to that based on five forest types, implying that proper stratification reduces the number of sample plots needed; (4) the optimal AGB estimation model and stratification scheme varied, depending on forest types; and (5) the RF algorithm provided better AGB estimation for non-stratification than the LR algorithm, but the LR approach provided better estimation with stratification. Results from this research provide new insights on how to properly conduct forest stratification for AGB estimation modeling, which is especially valuable in tropical and subtropical regions with complex forest types.

scholarly journals Predicting biomass of hyperdiverse and structurally complex central Amazonian forests – a virtual approach using extensive field data

2016 ◽  
Vol 13 (5) ◽  
pp. 1553-1570 ◽  
Author(s):  
Daniel Magnabosco Marra ◽  
Niro Higuchi ◽  
Susan E. Trumbore ◽  
Gabriel H. P. M. Ribeiro ◽  
Joaquim dos Santos ◽  
...  
Keyword(s):  
Size Distribution ◽  
Tropical Forests ◽  
Floristic Composition ◽  
Data Availability ◽  
Extreme Weather Events ◽  
Biomass Estimation ◽  
Compositional Variation ◽  
Wide Range ◽  
Landscape Level ◽  
Estimation Models

Abstract. Old-growth forests are subject to substantial changes in structure and species composition due to the intensification of human activities, gradual climate change and extreme weather events. Trees store ca. 90 % of the total aboveground biomass (AGB) in tropical forests and precise tree biomass estimation models are crucial for management and conservation. In the central Amazon, predicting AGB at large spatial scales is a challenging task due to the heterogeneity of successional stages, high tree species diversity and inherent variations in tree allometry and architecture. We parameterized generic AGB estimation models applicable across species and a wide range of structural and compositional variation related to species sorting into height layers as well as frequent natural disturbances. We used 727 trees (diameter at breast height  ≥  5 cm) from 101 genera and at least 135 species harvested in a contiguous forest near Manaus, Brazil. Sampling from this data set we assembled six scenarios designed to span existing gradients in floristic composition and size distribution in order to select models that best predict AGB at the landscape level across successional gradients. We found that good individual tree model fits do not necessarily translate into reliable predictions of AGB at the landscape level. When predicting AGB (dry mass) over scenarios using our different models and an available pantropical model, we observed systematic biases ranging from −31 % (pantropical) to +39 %, with root-mean-square error (RMSE) values of up to 130 Mg ha−1 (pantropical). Our first and second best models had both low mean biases (0.8 and 3.9 %, respectively) and RMSE (9.4 and 18.6 Mg ha−1) when applied over scenarios. Predicting biomass correctly at the landscape level in hyperdiverse and structurally complex tropical forests, especially allowing good performance at the margins of data availability for model construction/calibration, requires the inclusion of predictors that express inherent variations in species architecture. The model of interest should comprise the floristic composition and size-distribution variability of the target forest, implying that even generic global or pantropical biomass estimation models can lead to strong biases. Reliable biomass assessments for the Amazon basin (i.e., secondary forests) still depend on the collection of allometric data at the local/regional scale and forest inventories including species-specific attributes, which are often unavailable or estimated imprecisely in most regions.

scholarly journals Biomass and total carbon in oak forests of Southern Colombian Andes: contributions to the REDD+ project-wide approach.

2016 ◽  
Vol 64 (1) ◽  
pp. 399
Author(s):  
Adriana Yepes ◽  
Andrés Sierra ◽  
Luz Milena Niño ◽  
Manuel López ◽  
César Garay ◽  
...  
Keyword(s):  
Tropical Forests ◽  
Aboveground Biomass ◽  
Belowground Biomass ◽  
Carbon Stocks ◽  
Total Carbon ◽  
Biomass Estimation ◽  
Natural Forests ◽  
Colombian Andes ◽  
Greenhouse Emission

Carbon estimations in tropical forests are very important to understand the role of these ecosystems in the carbon cycle, and to support decisions and the formulation of mitigation and adaptive strategies to reduce the greenhouse emission gases (GHG). Nevertheless, detailed ground-based quantifications of total carbon stocks in tropical montane forests are limited, despite their high value in science and ecosystem management (e.g. REDD+). The objective was to identify the role of these ecosystems as carbon stocks, to evaluate the contribution of the pools analyzed (aboveground biomass, belowground biomass and necromass), and to make contributions to the REDD+ approach from the project scale. For this study, we established 44 plots in a heterogeneous landscape composed by old-grown forests located in the Southern Colombian Andes. In each plot, all trees, palms and ferns with diameter (D) ≥ 15 cm were measured. In the case of palms, the height was measured for 40 % of the individuals, following the Colombia National Protocol to estimate biomass and carbon in natural forests. National allometric equations were used to estimate aboveground biomass, and a global equation proposed by IPCC was used for belowground biomass estimation; besides, palms’ aboveground biomass was estimated using a local model. The necromass was estimated for dead standing trees and the gross debris. In the latter case, the length and diameters of the extremes in the pieces were measured. Samples for wood density estimations were collected in the field and analyzed in the laboratory. The mean total carbon stock was estimated as 545.9 ± 84.1 Mg/ha (± S.E.). The aboveground biomass contributed with 72.5 %, the belowground biomass with 13.6 %, and the necromass with 13.9 %. The main conclusion is that montane tropical forests store a huge amount of carbon, similar to low land tropical forests. In addition, the study found that the inclusion of other pools could contribute with more than 20 % to total carbon storage, indicating that estimates that only include the aboveground biomass, largely underestimate carbon stocks in tropical forest ecosystems. These results support the importance of including other carbon pools in REDD+ initiatives’ estimations. 

Sign in / Sign up

Export Citation Format

Share Document