Estimation of standing wood volume and species composition in managed nemoral multi-layer mixed forests by using nearest neighbour classifier, multispectral satellite images and airborne lidar data / Puistute liigilise koosseisu ja tüvemahu hindamine k-lähima naabri meetodil mitmerindelistes majandatavates segametsades

Mait Lang 1 , 2 , Tauri Arumäe 2 , Tõnu Lükk 1 , 2 ,  and Allan Sims 2
  • 1 Tartu Observatory, 61602 Tõravere, Tartumaa, Estonia
  • 2 Institute of Forestry and Rural Engineering, Estonian University of Life Sciences, Kreutzwaldi 5, Tartu 51014, Estonia


Nearest neighbour techniques are useful for constructing maps of forest inventory variables based on sample plot and auxiliary data from remote sensing. The most problematic issue of the nearest neighbour technique is possible systematic bias in the estimated values. In this study a 15 by 15 km test site in nemoral multilayer mixed forests was established in Laeva, Estonia. A set of 444 circular sample plots was used as reference set. Airborne lidar data and Landsat-8 Operational Land Imager image were used to construct five different feature variable sets consisting of original variables and alternatively principal components. The response variables were wood volume of first tree layer, wood volume of the second tree layer and main species code. A special test was carried out where a substantial amount of Silver birch dominated plots were removed from the reference set. The wood volume prediction validation was carried out on 89 forest growth sample plots and on 2290 forest stands. Species composition prediction was validated on 986 forest stands. As in many previous studies the results confirmed superiority of airborne lidar variables over spectral variables for wood volume estimation. The first three principal components of airborne lidar variables and first five principal components of all possible original feature variables contained over 99% of the information and performed well in imputations. The imputed wood volume at small values was overestimated and underestimated at large values regardless of used reference set. The feature variable sets containing spectral data performed better for species composition imputation. There was a forest age dependent discrepancy in predicted species proportions: birch and spruce proportions were underestimated in young stands and overestimated in older stands while proportion of aspen had exactly the opposite errors. The lack of fit depended slightly on the feature variable sets. The birch dominated plot partial removal from the reference set changed the predicted proportion of species but did not remove the forest age dependent lack of fit. The result can be important for the studies in which bootstrap samples are used to estimate error statistics for nearest neighbour technique based forest inventory variable maps.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Adermann, V. 2010. Development of Estonian National Forest Inventory. - Tomppo, E., Gschwantner, T., Lawrence, M., McRoberts, R.E. (eds.). National Forest Inventories. Heidelberg, Springer, 171-184.

  • Arumäe, T., Lang, M. 2013. A simple model to estimate forest canopy base height from airborne lidar data. - Forestry Studies / Metsanduslikud Uurimused, 58, 46-56.

  • Breidenbach, J., Nothdurfth, A., Kändler, G. 2010. Comparison of nearest neighbour approaches for small area estimation of tree species-specifi c forest inventory attributes in central Europe using airborne laser scanner data. - European Journal of Forest Research, 129, 833-846.

  • Chirici, G., Barbati, A., Corona, P., Marchetti, M., Travaglini, D., Maselli, F., Bertini, R. 2008. Nonparametric and parametric methods using satellite images for estimating growing stock volume in alpine and Mediterranean forest ecosystems. - Remote Sensing of Environment, 112, 2686-2700.

  • Fassnacht, F.E., Hartig, F., Latifi , H., Berger, C., Hernández, J., Corvalán, P., Koch, B. 2014. Importance of sample size, data type and prediction method for remote sensing-based estimations of aboveground forest biomass. - Remote Sensing of Environment, 154, 102-114.

  • Fazakas, Z., Nilsson, M., Olsson, H. 1999. Regional forest biomass and wood volume estimation using satellite data and ancillary data. - Agricultural and Forest Meteorology, 98/99, 417-425.

  • Franco-Lopez, H., Ek, A., Bauer, M. 2001. Estimation and mapping of forest sand density, volume, and cover type using the k-nearest neighbors method. - Remote Sensing of Environment, 77, 251-274.

  • Gilichinsky, M., Heiskanen, J., Barth, A., Wallerman, J., Egberth, M., Nilsson, M. 2012. Histogram matching for the calibration of kNN stem volume estimates. - International Journal of Remote Sensing, 33, 7117-7131.

  • Holmgren, J., Joyce, S., Nilsson, M., Olsson, H. 2000. Estimating stem volume and basal area in forest compartments by combining satellite image data with fi eld data. - Scandinavian Journal of Forest Research, 15, 103-111.

  • Howard, J.A. 1991, Remote sensing of forest resources. Chapman & Hall, London, UK. 420pp.

  • Huiyan, G., Limin, D., Gang, W., Dong, X., Shunzhong, W., Hui, W. 2006. Estimation of forest volumes by integrating Landsat TM imagery and forest inventory data. - Science in China: Series E Technological Sciences, 49, 54-62.

  • Kajisa, T., Murakami, T., Mizoue, N., Kitahara, F., Yoshida, S. 2008. Estimation of stand volume using k-nearest neighbors method in Kyushu, Japan. - Journal of Forest Research, 13, 249-254.

  • Kangur, A., Sims, A., Jõgiste, K., Kiviste, A., Korjus, H., von Gadow, K. 2007. Comparative modeling of stand development in Scots pine dominated forests in Estonia. - Forest Ecology and Management, 250, 109-118.

  • Katila, M., Tomppo, E., 2001. Selecting estimation parameters for the Finnish Multisource National Forest Inventory. - Remote Sensing of Environment, 76, 16-32.

  • Kiviste, A., Hordo, M. 2002. Network of permanent forest growth plots in Estonia. - Metsanduslikud Uurimused / Metsanduslikud Uurimused, 37, 43-58.

  • Krigul, T. 1972. Forest mensuration. (Metsatakseerimine). Valgus, Tallinn. 358 pp. (In Estonian).

  • Lang, M. 2010. Estimation of crown and canopy cover from airborne lidar data. - Forestry Studies / Metsanduslikud Uurimused, 52, 5-17.

  • Lang, M. Lükk, T., Rähn, A., Sims, A. 2005. Change detection on permanent forest growth sample plots using satellite images. - Forestry Studies / Metsanduslikud Uurimused, 43, 24-37.

  • Lang, M., Arumäe, T., Anniste, J. 2012. Estimation of main forest inventory variables from spectral and airborne lidar data in Aegviidu test site, Estonia. - Forestry Studies/ Metsanduslikud Uurimused, 56, 27-41.

  • Latifi , H., Koch, B. 2012. Evaluation of most similar neighbour and random forest methods for imputing forest inventory variables using data from target and auxiliary stands. - International Journal of Remote Sensing, 33, 6668-6694.

  • Lõhmus, E. 2004. Estonian forest site types. (Eesti metsakasvukohatüübid). Eesti loodusfoto, Tartu. 80 pp. (In Estonian).

  • McGaughey, R.J. 2014. FUSION/LDV: Software for LIDAR Data Analysis and visualization. March 2014 - FUSION, Version 3.42. United States Department of Agriculture Forest Service Pacifi c Northwest Research Station.

  • McInerney, D.O., Nieuwenhuis, M. 2009. A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory. - International Journal of Remote Sensing, 30, 4937-4955.

  • McRoberts, R.E. 2008. Using satellite imagery and the k-nearest neighbors technique as a bridge between strategic and management forest inventories. - Remote Sensing of Environment, 112, 2212-2221.

  • McRoberts, R.E. 2012. Estimating forest attribute parameters for small areas using nearest neighbour techniques. - Forest Ecology and Management, 272, 3-12.

  • McRoberts, R.E., Tomppo, E.O. 2007. Remote sensing support for national forest inventories. - Remote Sensing of Environment, 110, 412-419.

  • McRoberts, R.E., Næsset, E., Gobakken, T. 2015. Optimizing the k-Nearest Neighbors technique for estimating forest aboveground biomass using airborne laser scanning data. - Remote Sensing of Environment, 163, 13-22.

  • Moeur, M., Stage, A. R. 1995. Most similar Neighbor: An improved sampling inference procedure for natural resource planning. - Forest Science, 41, 337-359.

  • Nilson, T., Peterson, U. 1994. Age dependence of forest refl ectance - analysis of main driving factors. - Remote Sensing of Environment, 48, 319-331.

  • Packalén, P., Maltamo, M., 2007. The k-MSN method for the prediction of species specifi c stand attributes using airborne laser scanning and aerial photographs. - Remote Sensing of Environment, 109, 328-341.

  • Poso, S., Karlsson, M., Pekkonen, T., Härmä, P. 1990. A system for combining data from remote sensing, maps and fi eld measurement for forest planning purposes. - University of Helsinki, Department of Forest Mensuration and Management. Research notes, 23, 40 pp.

  • R Core Team. 2014. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0. [WWW document]. - URL [Accessed 10 October 2014].

  • Raudsaar, M., Pärt, E., Adermann, V. 2014. Review of Estonian forest resources. Yearbook Forest 2013. Compiled by Keskkonnaagentuur. OÜ Paar, Tartu, p. 1-2. (In Estonian).

  • Tamm, T., Remm, K. 2009. Estimating the parameters of forest inventory using machine learning and the reduction of remote sensing features. - International Journal of Applied Earth Observation and Geoinformation, 11, 290-297.

  • Tomppo, E., Gagliano, C., De Natale, F., Katila, M., McRoberts, R.E. 2009. Predicting categorical forest variables using an improved k-Nearest Neighbour estimator and Landsat imagery. - Remote Sensing of Environment, 113, 500-517.

  • Tomppo, E., Schadauer, K., McRoberts, R. E., Gschwantner, T., Gabler, K., Ståhl, G. 2010. History of NFIs. - Tomppo, E., Gschwantner, T., Lawrence, M., McRoberts, R.E. (eds.). National Forest Inventories. Heidelberg, Springer, 1-2.

  • Zald, H.S.J., Ohmann, J.L., Roberts, H.M., Gregory, M.J., Henderson, E.B., McGaughey, R.J., Braaten, J. 2014. Infl uence of lidar, Landsat imagery, disturbance history, plot location accuracy, and plot size on accuracy of imputation maps of forest composition and structure. Remote Sensing of Environment, 143, 26-38.


Journal + Issues