Application of deep learning algorithm for estimating stand volume in South Korea

17950 7 97476 2 300309 document 97476 Cha_2022_JARS-210436_preprint.pdf application/pdf 446b649b1765618a53f29ae17fbafb72 MD5 964421 2022-04-11 08:52:22 https://pure.iiasa.ac.at/id/eprint/17950/1/Cha_2022_JARS-210436_preprint.pdf 17950 1 1 application/pdf text en public cc_by_nc_4

Cha_2022_JARS-210436_preprint.pdf

accepted 97477 2 300312 document 97477 lightbox.jpg image/png 827566cd7784655393e98bacee897d60 MD5 59087 2022-04-11 09:22:47 https://pure.iiasa.ac.at/id/eprint/17950/2/lightbox.jpg 17950 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/97476 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/97476 http://eprints.org/relation/isIndexCodesVersionOf https://pure.iiasa.ac.at/id/document/97476 archive 353 disk0/00/01/79/50 2022-04-11 07:46:41 2022-04-11 09:14:29 2022-04-11 07:46:41 article show Cha S. Jo H.-W. Kim M. Song C. Lee H. Park E. Lim J. Shchepashchenko D. 7435 0000-0002-7814-4990 Shvidenko A. 1487 Lee W.-K. Application of deep learning algorithm for estimating stand volume in South Korea pub BNR AFE ASA NODES stand volume estimation; convolutional neural networks; national level of stand volume; satellite imageries; geospatial information Current estimates of stand volume for South Korean forests are mostly derived from expensive field data. Techniques that allow reducing the amount of ground data with reliable accuracy would decrease the cost and time. The fifth National Forest Inventory (NFI) has been conducted annually for all forest areas in South Korea from 2006 to 2010 and using these data we can make a model for estimating the stand volume of forests. The purpose of this study is to test deep learning whether it is available for measurement of stand volume with satellite imageries and geospatial information. The spatial distribution of the stand volume of South Korean forests was predicted with the convolutional neural networks (CNNs) algorithm. NFI data were randomly sampled for training from 90% to 10%, with 10% decrement, and the rest of the area was estimated using satellite imagery and geospatial information. Consequently, we found that the error rate of total stand volume was <5 % when using over 17% of NFI data for training (R2 = 0.96). We identified that using CNNs model based on satellite imageries and geospatial information is considered to be suitable for estimating the national level of stand volume. This study is meaningful in that we (1) estimated the stand volume using a deep learning algorithm with high accuracy compare with previous studies, (2) identified the minimum training rate of the CNNs model to estimate the stand volume of South Korean forest, and (3) identified the effect of diameter class on error hotspots in stand volume estimates through clustering analysis. 2022-04-08 published Society of Photo-optical Instrumentation Engineers 10.1117/1.JRS.16.024503 279 281 public Journal of Applied Remote Sensing 16 02 e024503 TRUE 1931-3195 no info:eu-repo/semantics/article