Cookies Notification

We use cookies to improve your website experience. To learn about our use of cookies and how you can manage your cookie settings, please see our Cookie Policy.
×

Mixtures of airborne lidar-based approaches improve predictions of forest structure

Publication: Canadian Journal of Forest Research
3 March 2021

Abstract

The most common method for modeling forest attributes with airborne lidar, the area-based approach, involves summarizing the point cloud of individual plots and relating this to attributes of interest. Tree- and voxel-based approaches have been considered as alternatives to the area-based approach but are rarely considered in an area-based context. We estimated three forest attributes (basal area, overstory biomass, and volume) across 1680 field plots in Arizona and New Mexico. Variables from the three lidar approaches (area, tree, and voxel) were created for each plot. Random forests were estimated using subsets of variables based on each individual lidar approach and mixtures of each approach. Boruta feature selection was performed on variable subsets, including the mixture of all lidar-approach predictors (KS-Boruta). A corrected paired t test was utilized to compare six validated models (area-Boruta, tree-Boruta, voxel-Boruta, KS-Boruta, KS-all, and ridge-all) for each forest attribute. Based on significant reductions in error (SMdAPE), basal area and biomass were best modeled with KS-Boruta, while volume was best modeled with KS-all. Analysis of variable importance shows that voxel-based predictors are critical for the prediction of the three forest attributes. This study highlights the importance of multiresolution voxel-based variables for modeling forest attributes in an area-based context.

Résumé

La méthode la plus courante pour modéliser les attributs de la forêt avec le lidar aéroporté, l’approche par zone, consiste à résumer le nuage de points des parcelles individuelles et à le relier aux attributs d’intérêt. Les approches basées sur les arbres et sur les voxels ont été considérées comme des solutions de rechange à l’approche basée sur la zone, mais elles sont rarement considérées dans un contexte basé sur la zone. Nous avons estimé trois attributs de la forêt (la surface terrière, la biomasse de l’étage supérieur et le volume) sur 1680 parcelles de terrain en Arizona et au Nouveau-Mexique. Pour chaque parcelle, ces variables ont été calculées selon trois approches lidar (par zone, par arbre et par voxel). Des forêts d’arbres décisionnels ont été estimées à l’aide de sous-ensembles de variables basés sur chaque approche lidar prise individuellement et à l’aide d’assemblages de ces approches. Une sélection des caractéristiques a été effectuée sur des sous-ensembles des variables à l’aide d’un algorithme de Boruta, y compris un assemblage de tous les prédicteurs de l’approche lidar (KS-Boruta). Un test de t apparié corrigé a été utilisé pour comparer six modèles validés (Boruta par zone, Boruta par arbre, Boruta par voxel, KS-Boruta, KS-toutes les méthodes, régression ridge-toutes les méthodes) pour chaque attribut de la forêt. Sur la base de la réduction significative de l’erreur, la surface terrière et la biomasse étaient mieux modélisées avec le KS-Boruta tandis que le volume était mieux modélisé avec le KS- outes les méthodes. L’analyse de l’importance des variables montre que les prédicteurs basés sur les voxels sont essentiels pour la prédiction des trois attributs de la forêt. Cette étude met en évidence l’importance des variables basées sur le voxel multi-résolution pour la modélisation des attributs de la forêt dans une approche basée sur la zone. [Traduit par la Rédaction]

Get full access to this article

View all available purchase options and get full access to this article.

References

Allen C.D., Savage M., Falk D.A., Suckling K.F., Swetnam T.W., Schulke T., et al. 2002. Ecological restoration of southwestern ponderosa pine ecosystems: A broad perspective. Ecol. Appl. 12(5): 1418–1433.
Arjasakusuma S., Swahyu Kusuma S., and Phinn S. 2020. Evaluating variable selection and machine learning algorithms for estimating forest heights by combining lidar and hyperspectral data. ISPRS Int. J. Geo. Inf. 9(9): 507.
Armstrong J.S. and Collopy F. 1992. Error measures for generalizing about forecasting methods: Empirical comparisons. Int. J. Forecasting, 8(1): 69–80.
Benjamini Y. and Hochberg Y. 1995. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B. (Methodol.), 57(1): 289–300.
Bortolot Z.J. and Wynne R.H. 2005. Estimating forest biomass using small footprint LiDAR data: An individual tree-based approach that incorporates training data. ISPRS J. Photogramm. Remote Sens. 59(6): 342–360.
Bouckaert, R.R., and Frank, E. 2004. Evaluating the replicability of significance tests for comparing learning algorithms. In Advances in Knowledge Discovery and Data Mining. Edited by H. Dai, R. Srikant, and C. Zhang. Springer Berlin Heidelberg, Berlin, Heidelberg. pp. 3–12.
Breshears D.D., Cobb N.S., Rich P.M., Price K.P., Allen C.D., Balice R.G., et al. 2005. Regional vegetation die-off in response to global-change-type drought. Proc. Natl. Acad. Sci. U.S.A. 102(42): 15144–15148.
Cannon J.B., Barrett K.J., Gannon B.M., Addington R.N., Battaglia M.A., Fornwalt P.J., et al. 2018. Collaborative restoration effects on forest structure in ponderosa pine-dominated forests of Colorado. For. Ecol. Manage. 424: 191–204.
Chen Q., Gong P., Baldocchi D., and Tian Y.Q. 2007. Estimating basal area and stem volume for individual trees from lidar data. Photogramm. Eng. Remote Sens. 73(12): 1355–1365.
Chung Y.-W., Khaki B., Li T., Chu C., and Gadh R. 2019. Ensemble machine learning-based algorithm for electric vehicle user behavior prediction. Appl. Energy, 254: 113732.
Crookston N.L. and Dixon G.E. 2005. The forest vegetation simulator: A review of its structure, content, and applications. Comput. Electron. Agric. 49(1): 60–80.
Dalponte M. and Coomes D.A. 2016. Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data. Methods Ecol. Evol. 7(10): 1236–1245.
Degenhardt F., Seifert S., and Szymczak S. 2019. Evaluation of variable selection methods for random forests and omics data sets. Brief. Bioinform. 20(2): 492–503.
Dixon, G.E. 2020. A user’s guide to the Forest Vegetation Simulator. USDA Forest Service, Forest Manager Service Center, Fort Collins, Colorado. Available at https://www.fs.fed.us/fmsc/ftp/fvs/docs/gtr/EssentialFVS.pdf.
Fekety P.A., Falkowski M.J., Hudak A.T., Jain T.B., and Evans J.S. 2018. Transferability of lidar-derived basal area and stem density models within a northern Idaho ecoregion. Can. J. Remote Sens. 44(2): 131–143.
Friedman J., Hastie T., and Tibshirani R. 2010. Regularization paths for generalized linear models via coordinate descent. J. Stat. Soft. 33(1): 1–22.
Ganey J.L., Wan H.Y., Cushman S.A., and Vojta C.D. 2017. Conflicting perspectives on spotted owls, wildfire, and forest restoration. Fire Ecol. 13: 146–165.
Gleason C.J. and Im J. 2012. Forest biomass estimation from airborne LiDAR data using machine learning approaches. Remote Sens. Environ. 125: 80–91.
Goodbody T.R.H., Tompalski P., Coops N.C., Hopkinson C., Treitz P., and van Ewijk K. 2020. Forest inventory and diversity attribute modelling using structural and intensity metrics from multi-spectral airborne laser scanning data. Remote Sens. 12(13): 2109.
Heidemann, H., 2012. Lidar Base Specification. In Collection and delineation of spatial data. USGS. Available at https://pubs.usgs.gov/tm/11b4/pdf/tm11-B4.pdf.
Hemery G.E., Savill P.S., and Pryor S.N. 2005. Applications of the crown diameter – stem diameter relationship for different species of broadleaved trees. For. Ecol. Manage. 215(1–3): 285–294.
Hicke J.A., Meddens A.J.H., and Kolden C.A. 2016. Efficacy of resource objective wildfires for restoration of ponderosa pine (Pinus ponderosa) forests in northern Arizona. For. Sci. 62(2): 141–153.
Holl K.D. 2017. Restoring tropical forests from the bottom up. Science, 355(6324): 455–456.
Huffman D.W., Sánchez Meador A.J., Stoddard M.T., Crouse J.E., and Roccaforte J.P. 2017. Efficacy of resource objective wildfires for restoration of ponderosa pine (Pinus ponderosa) forests in northern Arizona. For. Ecol. Manage. 389: 395–403.
Hummel S., Hudak A.T., Uebler E.H., Falkowski M.J., and Megown K.A. 2011. A comparison of accuracy and cost of LiDAR versus stand exam data for landscape management on the Malheur National Forest. J. For. 109(5): 267–273.
Hyndman R.J. and Koehler A.B. 2006. Another look at measures of forecast accuracy. Int. J. Forecasting, 22(4): 679–688.
James, G., Witten, D., Hastie, T., and Tibshirani, R. 2013. An introduction to statistical learning: with applications in R. Springer, New York.
Jeronimo S.M.A., Kane V.R., Churchill D.J., McGaughey R.J., and Franklin J.F. 2018. Applying LiDAR individual tree detection to management of structurally diverse forest landscapes. J. For. 116(4): 336–346.
Kamoske A.G., Dahlin K.M., Stark S.C., and Serbin S.P. 2019. Leaf area density from airborne LiDAR: Comparing sensors and resolutions in a temperate broadleaf forest ecosystem. For. Ecol. Manage. 433: 364–375.
Kankare V., Vastaranta M., Holopainen M., Räty M., Yu X., Hyyppä J., et al. 2013. Retrieval of forest aboveground biomass and stem volume with airborne scanning LiDAR. Remote Sens. 5(5): 2257–2274.
Keyser, C., 2020. Southern (SN) variant overview — Forest Vegetation Simulator. USDA Forest Service, Internal Report, Forest Management Service Center, Fort Collins, Colorado. Available at https://www.fs.fed.us/fmsc/ftp/fvs/docs/overviews/FVSsn_Overview.pdf.
Kim E., Lee W.-K., Yoon M., Lee J.-Y., Son Y., and Abu Salim K. 2016. Estimation of voxel-based above-ground biomass using airborne LiDAR data in an intact tropical rain forest, Brunei. Forests, 7(12): 259.
Krofcheck D., Litvak M., Lippitt C., and Neuenschwander A. 2016. Woody biomass estimation in a southwestern U.S. juniper savanna using LiDAR-derived clumped tree segmentation and existing allometries. Remote Sens. 8(6): 453.
Kursa M.B. and Rudnicki W.R. 2010. Feature selection with the Boruta package. J. Stat. Soft. 36(11): 1–13.
Landres P.B., Morgan P., and Swanson F.J. 1999. Overview of the use of natural variability concepts in managing ecological systems. Ecol. Appl. 9(4): 1179–1188.
Latifi H., Fassnacht F.E., Müller J., Tharani A., Dech S., and Heurich M. 2015. Forest inventories by LiDAR data: A comparison of single tree segmentation and metric-based methods for inventories of a heterogeneous temperate forest. Int. J. Appl. Earth Obs. Geoinf. 42: 162–174.
Laughlin D.C., Moore M.M., Bakker J.D., Casey C.A., Springer J.D., Fule P.Z., and Covington W.W. 2006. Assessing targets for the restoration of herbaceous vegetation in ponderosa pine forests. Restor. Ecol. 14(4): 548–560.
Lindberg E. and Hollaus M. 2012. Comparison of methods for estimation of stem volume, stem number and basal area from airborne laser scanning data in a hemi-boreal forest. Remote Sens. 4(4): 1004–1023.
Maltamo, M. 2014. Forestry applications of airborne laser scanning: Concepts and case studies. Springer, New York.
Maxwell A.E., Warner T.A., and Fang F. 2018. Implementation of machine-learning classification in remote sensing: an applied review. Int. J. Remote Sens. 39(9): 2784–2817.
McGaughey, R.J. 2009. FUSION/LDV: Software for LIDAR data analysis and visualization. USDA Forest Service, Pacific Northwest Research Station, Seattle, Wash., USA.
Næsset E. 2002. Predicting forest stand characteristics with airborne scanning laser using a practical two-stage procedure and field data. Remote Sens. Environ. 80(1): 88–99.
Pau G., Fuchs F., Sklyar O., Boutros M., and Huber W. 2010. EBImage — an R package for image processing with applications to cellular phenotypes. Bioinformatics, 26(7): 979–981.
Pearse G.D., Watt M.S., Dash J.P., Stone C., and Caccamo G. 2019. Comparison of models describing forest inventory attributes using standard and voxel-based lidar predictors across a range of pulse densities. Int. J. Appl. Earth Obs. Geoinf. 78: 341–351.
Pebesma E. 2018. Simple features for R: Standardized support for spatial vector data. R Journal, 10(1): 439–446.
Popescu, S.C., and Hauglin, M. 2014. Estimation of biomass components by airborne laser scanning. In Forestry applications of airborne laser scanning: Concepts and case studies. Springer, New York. pp. 157–175.
Reynolds, R.T., Sanchez Meador, A.J., Youtz, J.A., Nicolet, T., Matonis, M.S., Jackson, P.L., et al. 2013. Restoring composition and structure in Southwestern frequent-fire forests: A science-based framework for improving ecosystem resiliency. USDA Forest Service, Rocky Mountain Research Station, Ft. Collins, Colorado.
Rodman K.C., Sánchez Meador A.J., Huffman D.W., and Waring K.M. 2016. Reference conditions and historical fine-scale spatial dynamics in a dry mixed-conifer forest, Arizona, USA. For. Sci. 62(3): 268–280.
Roussel J.-R., Auty D., Coops N.C., Tompalski P., Goodbody T.R.H., Meador A.S., et al. 2020. lidR: An R package for analysis of Airborne Laser Scanning (ALS) data. Remote Sens. Environ. 251: 112061.
Shaw, J.D., Menlove, J., Witt, C., Morgan, T.A., Amacher, M.C., Goeking, S.A., and Werstak, C.E. 2018. Arizona’s forest resources, 2001–2014. Resour. Bull. RMRS-RB-25. USDA Forest Service, Rocky Mountain Research Station, Fort Collins, Colorado.
Silva C.A., Hudak A.T., Vierling L.A., Loudermilk E.L., O’Brien J.J., Hiers J.K., et al. 2016. Imputation of individual longleaf pine (Pinus palustris Mill.) tree attributes from field and LiDAR data. Can. J. Remote Sens. 42(5): 554–573.
Tenneson K., Patterson M., Mellin T., Nigrelli M., Joria P., and Mitchell B. 2018. Development of a regional lidar-derived above-ground biomass model with Bayesian model averaging for use in ponderosa pine and mixed conifer forests in Arizona and New Mexico, USA. Remote Sens. 10(3): 442.
Tofallis C. 2015. A better measure of relative prediction accuracy for model selection and model estimation. J. Oper. Res. Soc. 66(8): 1352–1362.
Vastaranta M., Kankare V., Holopainen M., Yu X., Hyyppä J., and Hyyppä H. 2012. Combination of individual tree detection and area-based approach in imputation of forest variables using airborne laser data. ISPRS J. Photogramm. Remote Sens. 67: 73–79.
Venier L.A., Swystun T., Mazerolle M.J., Kreutzweiser D.P., Wainio-Keizer K.L., McIlwrick K.A., et al. 2019. Modelling vegetation understory cover using LiDAR metrics. PLoS One, 14(11): e0220096.
Wang Y., Hyyppa J., Liang X., Kaartinen H., Yu X., Lindberg E., et al. 2016. International benchmarking of the individual tree detection methods for modeling 3-D canopy structure for silviculture and forest ecology using airborne laser scanning. IEEE Trans. Geosci. Remote Sens. 54(9): 5011–5027.
Westerling A.L. 2006. Warming and earlier spring increase western U.S. forest wildfire activity. Science, 313(5789): 940–943.
White J.C., Coops N.C., Wulder M.A., Vastaranta M., Hilker T., and Tompalski P. 2016. Remote sensing technologies for enhancing forest inventories: A review. Can. J. Remote Sens. 42(5): 619–641.
Wiggins H.L., Nelson C.R., Larson A.J., and Safford H.D. 2019. Using LiDAR to develop high-resolution reference models of forest structure and spatial pattern. For. Ecol. Manage. 434: 318–330.
Woods M., Lim K., and Treitz P. 2008. Predicting forest stand variables from LiDAR data in the Great Lakes St. Lawrence forest of Ontario. For. Chron. 84(6): 827–839.
Wright M.N. and Ziegler A. 2017. ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. J. Stat. Soft. 77(1): 1–17.
Yu X., Ge H., Lu D., Zhang M., Lai Z., and Yao R. 2019. Comparative study on variable selection approaches in establishment of remote sensing model for forest biomass estimation. Remote Sens. 11(12): 1437.
Yu L., Liang L., Wang J., Zhao Y., Cheng Q., Hu L., et al. 2014. Meta-discoveries from a synthesis of satellite-based land-cover mapping research. Int. J. Remote Sens. 35(13): 4573–4588.
Yu X., Hyyppä J., Holopainen M., and Vastaranta M. 2010. Comparison of area-based and individual tree-based methods for predicting plot-level forest attributes. Remote Sens. 2(6): 1481–1495.

Supplementary Material

Supplementary data (cjfr-2020-0506suppla.docx)

Information & Authors

Information

Published In

cover image Canadian Journal of Forest Research
Canadian Journal of Forest Research
Volume 51Number 8August 2021
Pages: 1106 - 1116

History

Received: 30 November 2020
Accepted: 28 February 2021
Accepted manuscript online: 3 March 2021
Version of record online: 3 March 2021

Notes

This article is part of the special issue “Advances in forest mensuration and biometrics, featuring papers presented at the 2020 Western Mensurationists Conference”.

Permissions

Request permissions for this article.

Key Words

  1. voxel
  2. individual-tree detection
  3. area-based approach
  4. random forest
  5. Boruta

Mots-clés

  1. voxel
  2. détection des arbres individuels
  3. approche basée sur la zone
  4. forêts d’arbres décisionnels
  5. Boruta

Authors

Affiliations

Ryan C. Blackburn [email protected]
School of Forestry, Northern Arizona University, Flagstaff, Arizona, USA.
Robert Buscaglia
Department of Mathematics and Statistics, Northern Arizona University, Flagstaff, Arizona, USA.
Andrew J. Sánchez Meador
School of Forestry, Northern Arizona University, Flagstaff, Arizona, USA.
Ecological Restoration Institute, Northern Arizona University, Flagstaff, Arizona, USA.

Notes

Copyright remains with the author(s) or their institution(s). Permission for reuse (free in most cases) can be obtained from copyright.com.

Metrics & Citations

Metrics

Other Metrics

Citations

Cite As

Export Citations

If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.

Cited by

1. Ecological and climatic transferability of airborne lidar-driven aboveground biomass models in Piñon-Juniper woodlands
2. Innovative educational and research center for monitoring forest resources of Siberia based on laser and microwave aerospace imaging
3. Modeling spatial patterns of longleaf pine needle dispersal using long-term data
4. Modeling needle fuel dispersal in longleaf pine-dominated forests
5. Improving generalized models of forest structure in complex forest types using area- and voxel-based approaches from lidar
6. Lost in the woods: Forest vegetation, and not topography, most affects the connectivity of mesh radio networks for public safety
7. Influences of vegetation, model, and data parameters on forest aboveground biomass assessment using an area-based approach
8. Combining Area-Based and Individual Tree Metrics for Improving Merchantable and Non-Merchantable Wood Volume Estimates in Coastal Douglas-Fir Forests
9. Advancements in forest mensuration and biometrics in the artificial intelligence era1

View Options

Login options

Check if you access through your login credentials or your institution to get full access on this article.

Subscribe

Click on the button below to subscribe to Canadian Journal of Forest Research

Purchase options

Purchase this article to get full access to it.

Restore your content access

Enter your email address to restore your content access:

Note: This functionality works only for purchases done as a guest. If you already have an account, log in to access the content to which you are entitled.

View options

PDF

View PDF

Full Text

View Full Text

Figures

Tables

Media

Share Options

Share

Share the article link

Share on social media