scholarly journals A Comparison of Imputation Approaches for Estimating Forest Biomass Using Landsat Time-Series and Inventory Data

2018 ◽  
Vol 10 (11) ◽  
pp. 1825 ◽  
Author(s):  
Trung Nguyen ◽  
Simon Jones ◽  
Mariela Soto-Berelov ◽  
Andrew Haywood ◽  
Samuel Hislop
Keyword(s):  
Time Series ◽  
Forest Biomass ◽  
Basal Area ◽  
Imputation Method ◽  
Stem Volume ◽  
Biomass Estimation ◽  
Stem Density ◽  
Nearest Neighbour ◽  
Dead Trees ◽  
Model Scenarios

The prediction of forest biomass at the landscape scale can be achieved by integrating data from field plots with satellite imagery, in particular data from the Landsat archive, using k-nearest neighbour (kNN) imputation models. While studies have demonstrated different kNN imputation approaches for estimating forest biomass from remote sensing data and forest inventory plots, there is no general agreement on which approach is most appropriate for biomass estimation across large areas. In this study, we compared several imputation approaches for estimating forest biomass using Landsat time-series and inventory plot data. We evaluated 18 kNN models to impute three aboveground biomass (AGB) variables (total AGB, AGB of live trees and AGB of dead trees). These models were developed using different distance techniques (Random Forest or RF, Gradient Nearest Neighbour or GNN, and Most Similar Neighbour or MSN) and different combinations of response variables (model scenarios). Direct biomass imputation models were trained according to the biomass variables while indirect biomass imputation models were trained according to combinations of forest structure variables (e.g., basal area, stem density and stem volume of live and dead-standing trees). We also assessed the ability of our imputation method to spatially predict biomass variables across large areas in relation to a forest disturbance history over a 30-year period (1987–2016). Our results show that RF consistently outperformed MSN and GNN distance techniques across different model scenarios and biomass variables. The lowest error rates were achieved by RF-based models with generalized root mean squared difference (gRMSD, RMSE divided by the standard deviation of the observed values) ranging from 0.74 to 1.24. Whereas gRMSD associated with MSN-based and GNN-based models ranged from 0.92 to 1.36 and from 1.04 to 1.42, respectively. The indirect imputation method generally achieved better biomass predictions than the direct imputation method. In particular, the kNN model trained with the combination of basal area and stem density variables was the most robust for estimating forest biomass. This model reported a gRMSD of 0.89, 0.95 and 1.08 for total AGB, AGB of live trees and AGB of dead trees, respectively. In addition, spatial predictions of biomass showed relatively consistent trends with disturbance severity and time since disturbance across the time-series. As the kNN imputation method is increasingly being used by land managers and researchers to map forest biomass, this work helps those using these methods ensure their modelling and mapping practices are optimized.

scholarly journals WIDE-AREA MAPPING OF FOREST WITH NATIONAL AIRBORNE LASER SCANNING AND FIELD INVENTORY DATASETS

2016 ◽  
Vol XLI-B8 ◽  
pp. 727-731 ◽  
Author(s):  
J.-M. Monnet ◽  
C. Ginzler ◽  
J.-C. Clivaz
Keyword(s):  
Laser Scanning ◽  
Prediction Models ◽  
Basal Area ◽  
National Forest Inventory ◽  
Airborne Laser Scanning ◽  
Stem Volume ◽  
Stem Density ◽  
Maximum Height ◽  
Airborne Laser

Airborne laser scanning (ALS) remote sensing data are now available for entire countries such as Switzerland. Methods for the estimation of forest parameters from ALS have been intensively investigated in the past years. However, the implementation of a forest mapping workflow based on available data at a regional level still remains challenging. A case study was implemented in the Canton of Valais (Switzerland). The national ALS dataset and field data of the Swiss National Forest Inventory were used to calibrate estimation models for mean and maximum height, basal area, stem density, mean diameter and stem volume. When stratification was performed based on ALS acquisition settings and geographical criteria, satisfactory prediction models were obtained for volume (R<sup>2</sup> = 0.61 with a root mean square error of 47 %) and basal area (respectively 0.51 and 45 %) while height variables had an error lower than 19%. This case study shows that the use of nationwide ALS and field datasets for forest resources mapping is cost efficient, but additional investigations are required to handle the limitations of the input data and optimize the accuracy.

scholarly journals Tree- and Stand-Level Biomass Estimation in a Larix decidua Mill. Chronosequence

Forests ◽  
2018 ◽  
Vol 9 (10) ◽  
pp. 587 ◽  
Author(s):  
Andrzej Jagodziński ◽  
Marcin Dyderski ◽  
Kamil Gęsikiewicz ◽  
Paweł Horodecki
Keyword(s):  
Aboveground Biomass ◽  
Biomass Conversion ◽  
Basal Area ◽  
Biomass Accumulation ◽  
Larix Decidua ◽  
Forest Stand ◽  
Stem Volume ◽  
Stand Age ◽  
Biomass Estimation ◽  
Forest Stands

Carbon pool assessments in forests is one of the most important tasks of forest ecology. Despite the wide cultivation range, and economical and traditional importance, the aboveground biomass of European larch (Larix decidua Mill.) stands is poorly characterized. To increase knowledge about forest biomass accumulation and to provide a set of tools for aboveground biomass estimation, we studied a chronosequence of 12 larch forest stands (7–120 years old). From these stands, we measured the biomass of 96 sample trees ranging from 1.9 to 57.9 cm in diameter at breast height. We provided age-specific and generalized allometric equations, biomass conversion and expansion factors (BCEFs) and biomass models based on forest stand characteristics. Aboveground biomass of stands ranged from 4.46 (7-year-old forest stand) to 445.76 Mg ha−1 (106-year-old). Stand biomass increased with increasing stand age, basal area, mean diameter, height and total stem volume and decreased with increasing density. BCEFs of the aboveground biomass and stem were almost constant (mean BCEFs of 0.4688 and 0.3833 Mg m−3, respectively). Our generalized models at the tree and stand level had lower bias in predicting the biomass of the forest stands studied, than other published models. The set of tools provided fills the gap in biomass estimation caused by the low number of studies on larch biomass, which allows for better estimation of forest carbon pools.

scholarly journals Successional dynamics in Neotropical forests are as uncertain as they are predictable

2015 ◽  
Vol 112 (26) ◽  
pp. 8013-8018 ◽  
Author(s):  
Natalia Norden ◽  
Héctor A. Angarita ◽  
Frans Bongers ◽  
Miguel Martínez-Ramos ◽  
Iñigo Granzow-de la Cerda ◽  
...  
Keyword(s):  
Land Use ◽  
Time Series ◽  
Forest Succession ◽  
Initial Conditions ◽  
Basal Area ◽  
Species Density ◽  
Stand Age ◽  
Stem Density ◽  
Neotropical Forests ◽  
Study Sites

Although forest succession has traditionally been approached as a deterministic process, successional trajectories of vegetation change vary widely, even among nearby stands with similar environmental conditions and disturbance histories. Here, we provide the first attempt, to our knowledge, to quantify predictability and uncertainty during succession based on the most extensive long-term datasets ever assembled for Neotropical forests. We develop a novel approach that integrates deterministic and stochastic components into different candidate models describing the dynamical interactions among three widely used and interrelated forest attributes—stem density, basal area, and species density. Within each of the seven study sites, successional trajectories were highly idiosyncratic, even when controlling for prior land use, environment, and initial conditions in these attributes. Plot factors were far more important than stand age in explaining successional trajectories. For each site, the best-fit model was able to capture the complete set of time series in certain attributes only when both the deterministic and stochastic components were set to similar magnitudes. Surprisingly, predictability of stem density, basal area, and species density did not show consistent trends across attributes, study sites, or land use history, and was independent of plot size and time series length. The model developed here represents the best approach, to date, for characterizing autogenic successional dynamics and demonstrates the low predictability of successional trajectories. These high levels of uncertainty suggest that the impacts of allogenic factors on rates of change during tropical forest succession are far more pervasive than previously thought, challenging the way ecologists view and investigate forest regeneration.

scholarly journals WIDE-AREA MAPPING OF FOREST WITH NATIONAL AIRBORNE LASER SCANNING AND FIELD INVENTORY DATASETS

2016 ◽  
Vol XLI-B8 ◽  
pp. 727-731
Author(s):  
J.-M. Monnet ◽  
C. Ginzler ◽  
J.-C. Clivaz
Keyword(s):  
Laser Scanning ◽  
Prediction Models ◽  
Basal Area ◽  
National Forest Inventory ◽  
Airborne Laser Scanning ◽  
Stem Volume ◽  
Stem Density ◽  
Maximum Height ◽  
Airborne Laser

Airborne laser scanning (ALS) remote sensing data are now available for entire countries such as Switzerland. Methods for the estimation of forest parameters from ALS have been intensively investigated in the past years. However, the implementation of a forest mapping workflow based on available data at a regional level still remains challenging. A case study was implemented in the Canton of Valais (Switzerland). The national ALS dataset and field data of the Swiss National Forest Inventory were used to calibrate estimation models for mean and maximum height, basal area, stem density, mean diameter and stem volume. When stratification was performed based on ALS acquisition settings and geographical criteria, satisfactory prediction models were obtained for volume (R<sup>2</sup>&thinsp;=&thinsp;0.61 with a root mean square error of 47&thinsp;%) and basal area (respectively 0.51 and 45&thinsp;%) while height variables had an error lower than 19%. This case study shows that the use of nationwide ALS and field datasets for forest resources mapping is cost efficient, but additional investigations are required to handle the limitations of the input data and optimize the accuracy.

scholarly journals Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

2020 ◽  
Vol 12 (18) ◽  
pp. 3019 ◽  
Author(s):  
Kourosh Ahmadi ◽  
Bahareh Kalantar ◽  
Vahideh Saeidi ◽  
Elaheh K. G. Harandi ◽  
Saeid Janizadeh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Temperate Forests ◽  
Elevation Gradient ◽  
Basal Area ◽  
Forest Stand ◽  
Stem Volume ◽  
Support Vector ◽  
Stem Density ◽  
Stand Characteristics ◽  
Sentinel 2

The estimation and mapping of forest stand characteristics are vital because this information is necessary for sustainable forest management. The present study considers the use of a Bayesian additive regression trees (BART) algorithm as a non-parametric classifier using Sentinel-2A data and topographic variables to estimate the forest stand characteristics, namely the basal area (m2/ha), stem volume (m3/ha), and stem density (number/ha). These results were compared with those of three other popular machine learning (ML) algorithms, such as generalised linear model (GLM), K-nearest neighbours (KNN), and support vector machine (SVM). A feature selection was done on 28 variables including the multi-spectral bands on Sentinel-2 satellite, related vegetation indices, and ancillary data (elevation, slope, and topographic solar-radiation index derived from digital elevation model (DEM)) and then the most insignificant variables were removed from the datasets by recursive feature elimination (RFE). The study area was a mountainous forest with high biodiversity and an elevation gradient from 26 to 1636 m. An inventory dataset of 1200 sample plots was provided for training and testing the algorithms, and the predictors were fed into the ML models to compute and predict the forest stand characteristics. The accuracies and certainties of the ML models were assessed by their root mean square error (RMSE), mean absolute error (MAE), and R-squared (R2) values. The results demonstrated that BART generated the best basal area and stem volume predictions, followed by GLM, SVM, and KNN. The best RMSE values for both basal area (8.12 m2/ha) and stem volume (29.28 m3/ha) estimation were obtained by BART. Thus, the ability of the BART model for forestry application was established. On the other hand, KNN exhibited the highest RMSE values for all stand variable predictions, thereby exhibiting the least accuracy for this specific application. Moreover, the effectiveness of the narrow Sentinel-2 bands around the red edge and elevation was highlighted for predicting the forest stand characteristics. Therefore, we concluded that the combination of the Sentinel-2 products and topographic variables derived from the PALSAR data used in this study improved the estimation of the forest attributes in temperate forests.

scholarly journals Snag abundance 20, 30, and 40 years following fire and harvesting in boreal forests

2003 ◽  
Vol 79 (3) ◽  
pp. 541-549 ◽  
Author(s):  
Steven H Ferguson ◽  
Philip C Elkie
Keyword(s):  
Forest Management ◽  
Boreal Forests ◽  
Woody Debris ◽  
Ecological Factors ◽  
Basal Area ◽  
Natural Disturbance ◽  
Timber Harvest ◽  
Stem Density ◽  
Dead Trees ◽  
Diameter Classes

The retention of standing dead trees (snags) has become an important conservation concern, especially when forest management efforts attempt to emulate natural disturbance. We investigate the abundance of snags within Ontario's boreal forest following 10–20, 21–30, and 31–40 years of both fire and forest harvest disturbance over a 24 000-km2 area. Fire frequency varied considerably, with 90% of the fires in the study area occurring in the 1970s. We did not detect differences in basal area of snags (m2/km2) between burned and harvested stands. However, differences occurred in dead-stem density (number/km2); the burned stands produced more snags in the 21- to 30-year post-disturbance class and the harvested stands produced more snags in the 31- to 40-year post-disturbance class. Similarly, the distribution of diameter classes of snags differed between the burned and harvested stands. In size classes greater than 32 cm (diameter at breast height), we found more snags in the harvested forests 21–40 years following disturbance. We did not find differences in the basal area of snags between disturbance types, whether they were hardwood or softwood. However, hardwood snags occurred in greater abundance in the larger diameter classes. Our findings are limited by the changing timber harvest treatments (selective harvest, clearcut, and ecological cut), the small number of disturbance events, and the variety of stand compositions. More research is required on the ecological factors influencing snag abundance to improve development of local forest management plans and to design landscapes that conserve forest structure and biodiversity. Key words: biodiversity, clearcut, conservation, coarse woody debris, dead trees, forest management, landscape, snags, wildlife

Improved Forest Biomass Estimation by Adding Time-Series Characteristics of Landsat Reflectance

2021 ◽  
Author(s):  
Xia Liu ◽  
Zhanmang Liao ◽  
Albert Van Dijk ◽  
Binbin He ◽  
Yue Shi
Keyword(s):  
Time Series ◽  
Forest Biomass ◽  
Biomass Estimation

scholarly journals Tropical-Forest Biomass Estimation at X-Band From the Spaceborne TanDEM-X Interferometer

2015 ◽  
Vol 12 (2) ◽  
pp. 239-243 ◽  
Author(s):  
Robert Treuhaft ◽  
Fabio Gonzalves ◽  
Joao Roberto dos Santos ◽  
Michael Keller ◽  
Michael Palace ◽  
...  
Keyword(s):  
Tropical Forest ◽  
Forest Biomass ◽  
Biomass Estimation ◽  
X Band
Sign in / Sign up

Export Citation Format

Share Document