Temporal transferability of LiDAR-based imputation of forest inventory attributes

Fekety, Patrick A.; Falkowski, Michael J.; Hudak, Andrew T.

doi:10.1139/cjfr-2014-0405

Cited by 57 publications

(43 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a forest inventory context, recent research has focused on species characterization (Ørka et al 2013;Yu et al 2014, tree size or diameter distributions (Magnussen et al 2013;Saad et al 2015;Kankare et al 2015;Mehtätalo et al 2015;Tompalski et al 2015, Xu et al 2014, and exploration of issues that directly impact the cost and efficiency of the ABA (Fekety et al 2015;Junttila et al 2015;Keränen et al 2015;White, Arnett, et al 2015;Packalén et al 2015). Species composition information is required in order to inform a broad range of forest management information needs, including biodiversity, sustainable harvesting, and silvicultural prescriptions, to name but a few.…”

Section: Advanced Remote Sensing Technologies and Their Current Use Imentioning

confidence: 99%

Remote Sensing Technologies for Enhancing Forest Inventories: A Review

White

Coops

Wulder

et al. 2016

Canadian Journal of Remote Sensing

614

354

View full text Add to dashboard Cite

Abstract. Forest inventory and management requirements are changing rapidly in the context of an increasingly complex set of economic, environmental, and social policy objectives. Advanced remote sensing technologies provide data to assist in addressing these escalating information needs and to support the subsequent development and parameterization of models for an even broader range of information needs. This special issue contains papers that use a variety of remote sensing technologies to derive forest inventory or inventory-related information. Herein, we review the potential of 4 advanced remote sensing technologies, which we posit as having the greatest potential to influence forest inventories designed to characterize forest resource information for strategic, tactical, and operational planning: airborne laser scanning (ALS), terrestrial laser scanning (TLS), digital aerial photogrammetry (DAP), and high spatial resolution (HSR)/very high spatial resolution (VHSR) satellite optical imagery. ALS, in particular, has proven to be a transformative technology, offering forest inventories the required spatial detail and accuracy across large areas and a diverse range of forest types. The coupling of DAP with ALS technologies will likely have the greatest impact on forest inventory practices in the next decade, providing capacity for a broader suite of attributes, as well as for monitoring growth over time.

show abstract

Section: Advanced Remote Sensing Technologies and Their Current Use Imentioning

confidence: 99%

Remote Sensing Technologies for Enhancing Forest Inventories: A Review

White

Coops

Wulder

et al. 2016

Canadian Journal of Remote Sensing

614

354

View full text Add to dashboard Cite

show abstract

“…We evaluated how well the 34 sample plots captured the mangrove structural variability in the study area using a principal component analysis (PCA) approach, similar to [71,72]. We performed PCA on the lidar statistical metrics dataset for the whole mangrove study area as a dimension reduction method by finding the principal components of the input data.…”

Section: Sample Plot Coverage Assessmentmentioning

confidence: 99%

Reducing Uncertainty in Mapping of Mangrove Aboveground Biomass Using Airborne Discrete Return Lidar Data

et al. 2018

View full text Add to dashboard Cite

Remote sensing techniques offer useful tools for estimating forest biomass to large extent, thereby contributing to the monitoring of land use and landcover dynamics and the effectiveness of environmental policies. The main goal of this study was to investigate the potential use of discrete return light detection and ranging (lidar) data to produce accurate aboveground biomass (AGB) maps of mangrove forests. AGB was estimated in 34 small plots scatted over a 50 km 2 mangrove forest in Rio de Janeiro, Brazil. Plot AGB was computed using either species-specific or non-species-specific allometric models. A total of 26 descriptive lidar metrics were extracted from the normalized height of the lidar point cloud data, and various model forms (random forest and partial least squares regression with backward selection of predictors (Auto-PLS)) were tested to predict the recorded AGB. The models developed using species-specific allometric models were distinctly more accurate (R 2 (calibration) = 0.89, R 2 (validation) = 0.80, root-mean-square error (RMSE, calibration) = 11.20 t·ha −1 , and RMSE(validation) = 14.80 t·ha −1 ). The use of non-species-specific allometric models yielded large errors on a landscape scale (+14% or −18% bias depending on the allometry considered), indicating that using poor quality training data not only results in low precision but inaccuracy at all scales. It was concluded that under suitable sampling pattern and provided that accurate field data are used, discrete return lidar can accurately estimate and map the AGB in mangrove forests. Conversely this study underlines the potential bias affecting the estimates of AGB in other forested landscapes where only non-species-specific allometric equations are available.

show abstract

“…Subsequently, an RF-based model selection procedure [61,62] was applied to obtain a parsimonious set of model predictor variables for each training data frame. The RF model selection procedure uses a percentage increase in model MSE to select a suite of the least number of predictor variables that explains the greatest proportion of variation in AGB (e.g., [29,63]. The set of predictors identified in the RF model selection procedure were further subjected to both forward and backwards elimination methods of stepwise regression [59,64] to remove predictors that did not contribute statistically significantly to improving the fit of the model to the data.…”

Section: Modeling and Validationmentioning

confidence: 99%

Evaluating Site-Specific and Generic Spatial Models of Aboveground Forest Biomass Based on Landsat Time-Series and LiDAR Strip Samples in the Eastern USA

et al. 2017

View full text Add to dashboard Cite

Large-area assessment of aboveground tree biomass (AGB) to inform regional or national forest monitoring programs can be efficiently carried out by combining remotely sensed data and field sample measurements through a generic statistical model, in contrast to site-specific models. We integrated forest inventory plot data with spatial predictors from Landsat time-series imagery and LiDAR strip samples at four sites across the eastern USA-Minnesota (MN), Maine (ME), Pennsylvania-New Jersey (PANJ) and South Carolina (SC)-in statistical modeling frameworks to analyze the performance of generic (all sites combined) versus site-specific models. The major objective was to evaluate the prediction accuracy of generic and site-specific models when applied to particular sites. Pixel-level polynomial model fitting was applied to the time-series of near-anniversary date Landsat variables to obtain projected metrics in the target year 2014 for which LiDAR strip samples were available. Two forms of models based on ordinary least-squares multiple linear regressions (MLR) and the random forest (RF) machine learning approach were developed for each site and for the pooled (i.e., generic) reference data frame. The models were evaluated using national forest inventory (NFI) data for the USA. We observed stronger fit statistics with the MLR than with RF for both the site-specific and the generic models. The proportions of variances explained (adjusted R 2 ) with the site-specific models were 0.86, 0.78, 0.82 and 0.92 for ME, MN, PANJ and SC, respectively while the generic model had adjusted R 2 = 0.85. A test of statistical equivalence of observed and predicted AGB for the NFI locations did not reveal equivalence with any of the models, possibly due to the different resolutions of the observed and predicted data. In contrast, predictions by the generic and site-specific models were equivalent. We conclude that a generic model provides accuracies comparable to the site-specific models for large-area AGB assessment across our study sites in the eastern USA.

show abstract

Temporal transferability of LiDAR-based imputation of forest inventory attributes

Cited by 57 publications

References 35 publications

Remote Sensing Technologies for Enhancing Forest Inventories: A Review

Remote Sensing Technologies for Enhancing Forest Inventories: A Review

Reducing Uncertainty in Mapping of Mangrove Aboveground Biomass Using Airborne Discrete Return Lidar Data

Evaluating Site-Specific and Generic Spatial Models of Aboveground Forest Biomass Based on Landsat Time-Series and LiDAR Strip Samples in the Eastern USA

Contact Info

Product

Resources

About