Ponderske funkcije u k-nn procjenama drvne zalihe u visokim šumama Bosne
DOI:
https://doi.org/10.54652/rsf.2011.v41.i2.132Ključne riječi:
growing stock, Landsat TM , k-NN estimates, Euclidian distance, weighting functionSažetak
UDK 630*52:311.2(497.6)
630*52:007.5(497.6)
Kombinovane inventure šuma u kojima se koriste daljinska istraživanja omogućile su podizanja efikasnosti procjena šumskih resursa primjenom različitih metodoloških pristupa. Najčešće korišteni metod procjene najvažnijih šumskih atributa je neparametrijski metod k najbližih susjeda koji je pokazao visoku efikasnost pri integraciji terenskih snimanja i LANDSAT satelitskih snimaka. Metod pruža mogućnost prilagođavanja konkretnim prilikama tj. podizanju efikasnosti procjena pomoću ponderskih funkcija koje daju različit značaj vrijednostima terenskih snimanja. U ovom radu analizirane su ponderske funkcije s obzirom na razlike vrijednosti koje se javljaju u cijelom uzorku i udaljenost registrovanih vrijednosti u multidimenzionalnom prostoru spektralnih kanala. Analizirane su greške procjena drvne zalihe na nivou pixela i na nivou visokih šuma kao kategorije. Ustanovljeno je da ponderisanje razlika vrijednosti i udaljenosti nije rezultiralo povećanom efikasnošću procjena na nivou pixela. Neparametrijske procjene drvnih zaliha u visokim šumama dostigle su umjeren stepen slaganja sa procjenama dobijenim redovnom taksacijom šuma kako za neponderisane tako i za ponderisane procjene. Između neponderisanih i ponderisanih procjena javlja se gotovo potpuno slaganje. Dobijeni rezultati podržavaju jednostavnije procedure procjene i potvrđuju predhodno izvedena rješenja. Dalja istraživanja treba usmjeriti na napredne metodološke mogućnosti i njihovo prilogođavanje za korištenje u konkretnim uvjetima.
References
BAFFETTA, F., CORONA, P., FATTORINI L. (2011): A matching procedure to improve k- NN estimation of forest attribute maps. Original Research Article. Forest Ecology and Management, In Press, Corrected Proof, Available online 20 July 2011.
BAFFETTA, F., FATTORINI, L., FRANCESCHI, S., CORONA, P. (2009): Design-based
approach to k-nearest neighbours technique for coupling field and remotely sensed data in forest surveys. Remote Sensing of Environment, 113(3):463–475, March 2009.
BORTZ, J. (1993): Statistik für Sozialwissenschaftler. 4. Auflage. Springer, Berlin.
CHIRICI, G. (2001): Developing an experimental survey protocol based on spatialized indicators to support forest management planning. Ph.D. thesis, Dipartmento di Scienze dell´Ambiente Forestale e delle sue Risorse. Universitádegli Studi della Tuscia. Italy.
CHIRICI, G., CORONA, P., MARCHETTI, M., MASELLI, F., BOTTAI, L. (2002): Spatial
distribution modelling of forest attributes coupling remotely sensed imagery and GIS techniques. Reality, models and parameter estimation – the forestry scenario 2-5 June 2002, Sesimbra, Portugal.
CONGLALTON, R. (1991): A review of assessing the accuracy of remotely sensed data. Remote Sensing of Environment 37: 35-46.
ČABARAVDIĆ, A. (2007): Efficient Estimation of Forest Attributes with k NN. Ph.D. thesis, Faculty of Forest and Environmental Sciences, Albert-Ludwigs-Universität Freiburg im Breisgau, Germany.
FINLEY A., MCROBERTS, R.E. (2008): Efficient k-nearest neighbour searches for multi- source forest attribute mapping. Remote Sensing of Environment, 112(5):2203– 2211.
FINLEY A., MCROBERTS, R.E.., EK. A.R. (2006): Applying an efficient k Nearest neighbor search to forest attribute imputation. Forest Science, Volume 52, Number 2, April 2006, pp. 130-135(6), 52(2):130–135.
FRANCO-LOPEZ, H., EK, A. R., BAUER, M. E. (2001): Estimation and mapping of forest stand density, volume, and cover type using the k nearest neighbors method. Remote Sensing of Environment, 77(3):251– 274.
GALLAUN, H., ZANCHI, G., NABUURS, G.J., HENGEVELD, G., SCHARDT, M., VERKERK P.J. (2010): EU-wide maps of growing stock and above-ground biomass in forests based on remote sensing and field measurements Original Research Article. Forest Ecology and Management, Volume 260, Issue 3, 30 June 2010, Pages 252-261.
HÄRKÖNEN, S., LEHTONEN, A., EERIKÄINEN, K., PELTONIEMI, M., MÄKELÄ A. (2011): Estimating forest carbon fluxes for large regions based on process-based modelling, NFI data and Landsat satellite images Original Research Article Forest Ecology and Management, Volume 262, Issue 12, 15 December 2011, Pages 2364-2377.
KANGAS A., MALTAMO M. (2006): Forest inventory – Methodology and Application. Springer.
KATILA, M. AND TOMPPO, E. (2001): Selecting estimation parameters for the Finnish multisource National Forest Inventory. Remote Sensing of Environment, 76: 16- 32.
KÖHL M., STÜMER, W., KENTER, B., RIEDEL T. (2008): Effect of the estimation of forest management and decay of dead woody material on the reliability of carbon stock and carbon stock changes - A simulation study Original Research Article Forest Ecology and Management, Volume 256, Issue 3, Pages 229-236.
KUTZER CH. (2007): Potential of the kNN Method for Estimation and Monitoring off- Reserve Forest Resources in Ghana. Ph.D. thesis, Faculty of Forest and Environmental Sciences, Albert-Ludwigs-Universität Freiburg im Breisgau, Germany.
KOUKAL, T. (2004): Nonparametric Assesment of Forest Attributes by Combination of Field Data of the Austrian Forest Inventory and Remote Sensing Data. Ph.D. thesis, Universität for Bodenkultur Wien.
KOHL, M.; STUMER, W.; KENTER, B.; RIEDEL, T. (2008): Effect of the estimation of forest management and decay of dead woody material on the reliability of carbon stock and carbon stock changes–A simulation study. Forest Ecology and Management. 256: 229-236.
MALTAMO, M. & KANGAS, A., (1998): Methods based on k-nearest neighbour regression in the prediction of basal area diameter distribution. Can. J. For. Res. 28: 1107- 1115.
MASELLI, F., CHIRICI, G., BOTTAI, L., CORONA, P., MARCHETTI, M. (2005): Estimation of mediterranean forest attributes by the application of k-NN procedures to multitemporal landsat ETM+ images. International Journal of Remote Sensing, 26(17):3781–3796.
MCROBERTS, R., E. TOMPPO, A. FINLEY, HEIKKINEN J. (2007): Estimating areal means and variances of forest attributes using the k-Nearest neighbors technique and satellite imagery. Remote Sensing of Environment, 111(4):466–480.
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(5):2212–2221, May 2008.
MCROBERTS, R.E. (2011): Estimating forest attribute parameters for small areas using nearest neighbors techniques Original Research Article Forest Ecology and Management, In Press, Corrected Proof, Available online 3 September 2011.
MCROBERTS, R.E., MAGNUSSEN, S., TOMPPO, E.O., CHIRICI G. (2011): Parametric, bootstrap, and jackknife variance estimators for the k-Nearest Neighbors technique with illustrations using forest inventory and satellite image data Original Research Article Remote Sensing of Environment, In Press, Corrected Proof, Available online 27 August 2011.
NABUURS, G.J., HENGEVELD, G.M., VAN DER WERF, D.C., HEIDEMA A.H. (2010): European forest carbon balance assessed with inventory based methods—An introduction to a special section Original Research Article. Forest Ecology and Management, Volume 260, Issue 3, 30 June 2010, Pages 239-240.
ÖZSAKABAŞI, F. (2008): Classification of forest areas by k nearest neighbor method: case study, Antalya. Master thesis. Geodetic and geographic information technologies department, Middle East Technical University.
RÄTY, M., KANGAS A. (2012): Comparison of k-MSN and kriging in local prediction Original Research Article Forest Ecology and Management, Volume 263, 1 January 2012, Pages 47-56.
STÜMER, W., KENTER, B., KÖHL M. (2010): Spatial interpolation of in situ data by self- organizing map algorithms (neural networks) for the assessment of carbon stocks in European forests. Original Research Article. Forest Ecology and Management, Volume 260, Issue 3, 30 June 2010, Pages 287-29.
STÜMER, W. (2004): Kombination von terrestrischen Aufnahmen und Fernerkundungsdaten mit Hilfe der kNN-Methode zur Klassifizierung und Kartierung von Wäldern. PHD. Fakultät für Forst-, Geo- und Hydrowissenschaften der Technischen Universität Dresden.
TOMPPO, E., KORHONEN, K.T., HEIKKINEN, J. AND YLI-KOJOLA, H. (2001): Multisource inventory of the forests of the Hebei Forestry Bureau, Heilongjiang, China. Silva Fennica 35: 309-328.
TOMPPO, E. & HALME, M. (2004): Using coarse scale forest variables as ancillary information and weighting of variables in k-NN estimation: a genetic algorithm approach. Remote Sensing of Environment 92: 1-20.
TOMPPO, E., OLSSON, H., STAHL, G., NILSSON, M., HAGNER, O., KATILA, M. (2008): Combining national forest inventory field plots and remote sensing data for forest databases. Remote Sensing of Environment, 112(5):1982–1999.
