Application of the domain adaptation method using a phenological classification framework for the land-cover classification of North Korea

19611 6 105570 2 320993 document 105570 1-s2.0-S1574954124001183-main.pdf application/pdf 52533bfb3bcdbe5f540cfa99c9119f09 MD5 14330912 2024-04-12 08:07:42 https://pure.iiasa.ac.at/id/eprint/19611/1/1-s2.0-S1574954124001183-main.pdf 19611 1 1 application/pdf text en public cc_by_nc_nd_4

1-s2.0-S1574954124001183-main.pdf

published 105571 1 320999 document 105571 indexcodes.txt text/x-c++ 2ed54f67ac5f2175f7912170e8ef4d08 MD5 13381 2024-04-12 08:13:21 https://pure.iiasa.ac.at/id/eprint/19611/2/indexcodes.txt 19611 2 2 text/x-c++ other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/105570 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/105570 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/105570 archive 353 disk0/00/01/96/11 2024-04-12 08:10:45 2024-04-12 08:10:45 2024-04-12 08:10:45 article show Kim J. Jo H.-W. Kim W. Jeong Y. Park E. Lee S. Kim M. 8828 Lee W.-K. Application of the domain adaptation method using a phenological classification framework for the land-cover classification of North Korea pub BNR AFE Land-cover mapping, Phenological classification, Domain adaptation, North Korea, Deep learning Efforts to achieve carbon neutrality are global, encompassing a wide range of factors. For the estimation of greenhouse gas emissions from the agriculture, forestry, and other land use (AFOLU) sector, the Intergovernmental Panel on Climate Change has proposed an advanced method that requires Approach 3, the highest level of suggested method, of activity data. Accordingly, we propose a phenological classification framework (PCF) that can perform land-cover classification by training the climatic repeatability of the annual cycle using a U-Net deep learning model. Additionally, the domain adaptation (DA) method can be applied to classify areas with insufficient data. We applied these methods to classify North Korea (i.e., using South Korean data), with an accuracy of 81.31%; overall this effort culminated in the simultaneous classification of the Korean Peninsula. Domain distribution comparison showed that the results for the two regions were similar. The PCF and DA methods proposed in this study allow for annual production of a land-cover map and change matrix, regardless of the presence or absence of data. The application of these methods is expected to provide a scientific basis for policy decisions that can facilitate the global attainment of carbon neutrality. 2024-07 published Elsevier doi:10.1016/j.ecoinf.2024.102576 156 public Ecological Informatics 81 e102576 TRUE 1574-9541 no info:eu-repo/semantics/article