Mapping growing stock volume and forest live biomass: a case study of the Polissya region of Ukraine

14855 11 79262 2 218982 document 79262 Bilous_2017_Environ._Res._Lett._12_105001.pdf application/pdf 129f2341bab1a8c50d3bd85c3c20c378 MD5 2716729 2017-09-28 06:12:24 https://pure.iiasa.ac.at/id/eprint/14855/1/Bilous_2017_Environ._Res._Lett._12_105001.pdf 14855 1 1 application/pdf text en public cc_by

Bilous_2017_Environ._Res._Lett._12_105001.pdf

published 79268 2 218995 document 79268 lightbox.jpg image/png ac4f09533f1d3191fb3a1f681f65c9ff MD5 12477 2017-09-28 06:22:30 https://pure.iiasa.ac.at/id/eprint/14855/2/lightbox.jpg 14855 2 2 image/png other Thumbnails conversion from text to thumbnail_lightbox en public

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

indexcodes.txt

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/79262 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/79262 http://eprints.org/relation/isIndexCodesVersionOf https://pure.iiasa.ac.at/id/document/79262 archive 353 disk0/00/01/48/55 2017-09-28 06:14:12 2021-08-27 17:29:26 2017-09-28 06:14:12 article show Bilous A. Myroniuk V. Holiaka D. Bilous S. See L. 8571 0000-0002-2665-7065 Schepaschenko D. 7435 0000-0002-7814-4990 Mapping growing stock volume and forest live biomass: a case study of the Polissya region of Ukraine pub prog_esm Forest inventory and biomass mapping are important tasks that require inputs from multiple data sources. In this paper we implement two methods for the Ukrainian region of Polissya: random forest (RF) for tree species prediction and k-nearest neighbors (k-NN) for growing stock volume and biomass mapping. We examined the suitability of the five-band RapidEye satellite image to predict the distribution of six tree species. The accuracy of RF is quite high: ~99% for forest/non-forest mask and 89% for tree species prediction. Our results demonstrate that inclusion of elevation as a predictor variable in the RF model improved the performance of tree species classification. We evaluated different distance metrics for the k-NN method, including Euclidean or Mahalanobis distance, most similar neighbor (MSN), gradient nearest neighbor, and independent component analysis. The MSN with the four nearest neighbors (k = 4) is the most precise (according to the root-mean-square deviation) for predicting forest attributes across the study area. The k-NN method allowed us to estimate growing stock volume with an accuracy of 3 m3 ha−1 and for live biomass of about 2 t ha−1 over the study area. 2017-09-27 published Institute of Physics Publishing (IOP) 10.1088/1748-9326/aa8352 276 279 public Environmental Research Letters 12 10 e105001 TRUE 1748-9326 FALSE no info:eu-repo/semantics/article