A Comparison of Selected Parametric and Non-Parametric Imputation Methods for Estimating Forest Biomass and Basal Area

Donald Gagliasso, Susan Hummel, Hailemariam Temesgen

Department of Forest Engineering, Resources and Management, Oregon State University, Corvallis, USA.
USDA Forest Service, Goods, Services, and Values Program, Portland Forest Sciences Laboratory, US Forest Service, Pacific Northwest Research Station, Portland, USA.

DOI: 10.4236/ojf.2014.41008                

Abstract

Various methods have been used to estimate the amount of above ground forest biomass across landscapes and to create biomass maps for specific stands or pixels across ownership or project areas. Without an accurate estimation method, land managers might end up with incorrect biomass estimate maps, which could lead them to make poorer decisions in their future management plans. The goal of this study was to compare various imputation methods to predict forest biomass and basal area, at a project planning scale (<20,000 acres) on the Malheur National Forest, located in eastern Oregon, USA. We examined the predictive performance of linear regression, geographic weighted regression (GWR), gradient nearest neighbor (GNN), most similar neighbor (MSN), random forest imputation, and k-nearest neighbor (k-nn) to estimate biomass (tons/acre) and basal area (sq. feet per acre) across 19,000 acres on the Malheur National Forest. To test the different methods, a combination of ground inventory plots, light detection and ranging (LiDAR) data, satellite imagery, and climate data was analyzed, and their root mean square error (RMSE) and bias were calculated. Results indicate that for biomass prediction, the k-nn (k = 5) had the lowest RMSE and least amount of bias. The second most accurate method consisted of the k-nn (k = 3), followed by the GWR model, and the random forest imputation. For basal area prediction, the GWR model had the lowest RMSE and least amount of bias. The second most accurate method was k-nn (k = 5), followed by k-nn (k = 3), and the random forest method. For both metrics, the GNN method was the least accurate based on the ranking of RMSE and bias.

Keywords

Gradient Nearest Neighbor; Most Similar Neighbor; K-Nearest Neighbor; Random Forest; Geographic Weighted Regression; Biomass; LiDAR

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Baskerville, G. L. (1972). Use of logarithmic regression in the estimation of plant biomass. Canadian Journal of Forestry, 2, 49-53. http://dx.doi.org/10.1139/x72-009
[2]	Camara, G., Souza, R., Freitas, U., & Garrido, J. (1996). SPRING: Integrating remote sensing and GIS by object-oriented data modeling. Computers and Graphics, 20, 395-403. http://dx.doi.org/10.1016/0097-8493(96)00008-8
[3]	Crookston, N. L., & Finley, A. O. (2008). yaImpute: An R package for kNN imputation. Journal of Statistical Software, 23, 1-16.
[4]	Crow, T. R., & Schlaegel, B. E. (1988). A guide to using regression Equations for estimating tree biomass. Northern Journal of Applied Forestry, 5, 15-22.
[5]	Eskelson, B. N. I., Temesgen, H., & Barrett, T. M. (2009a). Estimating current forest attributes from paneled inventory data using plot-level imputation: A study from the Pacific Northwest. Forest Science, 5, 64-71.
[6]	Eskelson, B. N. I., Temesgen, H., & Barrett, T. M. (2009b). Estimating cavity tree and snag abundance using negative binomial regression models and nearest neighbor imputation methods. Canadian Journal of Forest Research, 39, 1749-1765. http://dx.doi.org/10.1139/X09-086
[7]	Fotheringham, A. S., Brunsdon, C., & Charlton, M. (2002). Geographically weighted regression: The analysis of spatially varying relationships. Chichester, Hoboken, NJ: Wiley.
[8]	Goerndt, M. E., Monleon, V. J., & Temesgen, H. (2010). Relating forest attributes with areaand tree-based light detection and ranging metrics for Western Oregon. Western Journal of Applied Forestry, 25, 105-111.
[9]	Hudak, A. T., Crookston, N. L., Evans, J. S., Hall, D. E., & Falkowski, M. J. (2008). Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data. Remote Sensing of Environment, 112, 2232-2245. Corrigendum: (2009). Remote Sensing of Environment, 113, 289-290. http://dx.doi.org/10.1016/j.rse.2008.08.006
[10]	Hummel, S., Hudak, A. T., Uebler, E. H., Falkowski, M. J., & Megown, K. A. (2011). A comparison of accuracy and cost of LiDAR versus stand exam data for landscape management on the Malheur National Forest. Journal of Forestry, 109, 267-273.
[11]	Keyser, C. E., & Dixon, G. E. (2008). Blue Mountains (BM) variant overview—Forest vegetation simulator. Internal Rep., Fort Collins, CO: US Department of Agriculture, Forest Service, Forest Management Service Center. (revised February 3, 2010)
[12]	Koch, B., Straub, C., Dees, M., Wang, Y., & Weinacker, H. (2009). Airborne laser data for stand delineation and information extraction. International Journal of Remote Sensing, 30, 935-963. http://dx.doi.org/10.1080/01431160802395284
[13]	Maltamo, M., Malinen, J., Packalén, P., Suvanto, A., & Kangas, J. (2006). Nonparametric estimation of stem volume using airborne laser scanning, aerial photography, and stand-register data. Canadian Journal of Forest Research, 36, 426-436. http://dx.doi.org/10.1139/x05-246
[14]	McGaughey, R. J. (2009). FUSION/LDV: Software for LIDAR data analysis and visualization, Version 2.9. USDA FS. http://www.fs.fed.us/eng/rsac/fusion/
[15]	Moeur, M., & Stage, A. R. (1995). Most similar neighbor: An improved sampling inference procedure for natural resource planning. Forest Science, 41, 337-359.
[16]	Moisen, G. G., Edwards Jr., T. C., & Cutler, D. R. (1994). Spatial sampling to assess classification accuracy of remotely sensed data. In J. Brunt, S. S. Stafford, & W. K. Michener (Eds.), Environmental information management and analysis: Ecosystem to global scales (pp. 161-178). Philadelphia, PA: Taylor and Francis.
[17]	Mustonen, J., Packalén, P., & Kangas, A. (2008). Automatic segmentation of forest stands using canopy height model and aerial photograph. Scandinavian Journal of Forest Research, 23, 534-545. http://dx.doi.org/10.1080/02827580802552446
[18]	Ohmann, J. L., & Gregory, M. J. (2002). Predictive mapping of forest composition and structure with direct gradient analysis and nearestneighbor imputation in coastal Oregon, U.S.A. Canadian Journal of Forest Research, 32, 725-741. http://dx.doi.org/10.1139/x02-011
[19]	Næsset, E. (2004). Accuracy of forest inventory using airborne laser scanning: Evaluating the first Nordic full-scale operation project. Scandinavian Journal of Forest Research, 19, 554-557. http://dx.doi.org/10.1080/02827580410019544
[20]	Nelson, R., Short, A., & Valenti, M. (2004). Measuring biomass and carbon in Delaware using an airborne profiling LiDAR. Scandinavian Journal of Forest Research, 19, 500-511. http://dx.doi.org/10.1080/02827580410019508
[21]	R Development Core Team (2011). R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing. http://www.R-project.org/
[22]	Salas, C., Ene, L., Gregoire, T. G., Næsset, E., & Gobakken, T. (2010). Modelling tree diameter from airborne laser scanning derived variables: A comparison of spatial statistical models. Remote Sensing of Environment, 114, 1277-1285. http://dx.doi.org/10.1016/j.rse.2010.01.020
[23]	Sullivan, A. (2008). LIDAR based delineation in forest stands. Master’s Thesis, Seattle, WA: University of Washington.
[24]	Temesgen, H., LeMay, V. M., Marshall, P. L., & Froese, K. (2003). Imputing tree-lists from aerial attributes for complex stands of south-eastern British Columbia. Forest Ecology and Management, 177, 277-285. http://dx.doi.org/10.1016/S0378-1127(02)00321-3
[25]	Thornton, P. E. (2003). DAYMET climatological summaries for average air temperature and total precipitation (18-year mean for 19801997). Missoula, MT: University of Montana, Numerical Terradynamic Simulation Group. http://www.daymet.org
[26]	US Forest Service (2001). Region 6 inventory & monitoring system: Field procedures for the current vegetation survey. Natural Resource Inventory, Pacific Northwest Region. Version 2.04, Portland, OR: USDA Forest Service.
[27]	Wang, Q., Ni, J., & Tenhunen, J. (2005). Application of a geographically-weighted regression analysis to estimate net primary production of Chinese forest ecosystems. Global Ecology and Biogeography, 14, 379-393. http://dx.doi.org/10.1111/j.1466-822X.2005.00153.x
[28]	Wulder, M. A., Bater, C. W., Coops, N. C., Hiker, T., & White, J. C. (2008). The role of LiDAR in sustainable forest management. The Forestry Chronicle, 84, 807-826.