Open AccessWEIGHTED FUNCTIONS in the k-NN ESTIMATES of GROWING STOCK in HIGH FOREST in BOSNIA
Author(s) -
Azra Čabaravdić,
Dieter R. Pelz,
Gherardo Chirici,
Christian Kutzer,
E. Ćatić,
H. Delić
Publication year - 2011
Publication title -
radovi šumarskog fakulteta univerziteta u sarajevu
Language(s) - English
Resource type - Journals
eISSN - 2490-3183
pISSN - 1512-5769
DOI - 10.54652/rsf.2011.v41.i2.132
Subject(s) - weighting , stock (firearms) , euclidean distance , statistics , mathematics , inverse distance weighting , forest inventory , a weighting , carbon stock , estimation , euclidean geometry , geography , econometrics , forestry , forest management , economics , geology , physics , geometry , oceanography , archaeology , management , climate change , acoustics , multivariate interpolation , bilinear interpolation
UDK 630*52:311.2(497.6)
630*52:007.5(497.6)
Last decades permanent researches clarify possibilities for forest resource estimation based on terrestrial measurement and remote sensing. The most often the non- parametrical k-NN method is used integrating local estimates from terrestrial measurement and spectral Landsat data. In this paper the weighting functions of the k- NN related to value differences and distances were examined in a case of high forest in site Konjuh in Bosnia. It is found that weighting Euclidean distance has not resulted with efficiency increase. Procentual RMSE's of growing stock showed higher values for weighted estimates on the pixel level. Classified volume estimates on aggregated level compared with volumes from intensive regular forest inventory achieved moderate level of agreement. The agreements between volume estimates are almost perfect regardless on weighting functions. Obtained results point out unweighted estimates as reported in several cases.