Abstract
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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.