Abstract:
Remote sensing is a fundamental tool for problem solving and provides crucial insight into pressing environmental issues. Remote sensing data is increasingly supported to aid in forest management and conservation in numerous regions of the world where environmental concerns are of utmost relevance due to the rapid advancements in remote sensing technology and methods. The process of remote sensing for forestry has been shifted to an exploratory phase due to the growth in population and urbanization. This phase aids researchers in completing the majority of their study on data explanation rather than data generation. The LU/LC of deforestation in Khyber Pakhtunkhwa, in northern Pakistan, is the basis for this study. Landsat7/Landsat8 photos from the USGS Earth Explorer site were utilized for this study in order to detect LU/LC changes in forestry. Utilizing ENVI 5.2, the supervised classification method, or KNN, is used with several parameters, including training threshold contribution, training rate, training RMS Exit, and training momentum. The pictures that were utilized are from 2011 and 2022. Every image is split into three classes: forested, snow-covered, and dry and barren lands. The total accuracy provided by the KNN is 89.9529% for the year 2011, with a kappa coefficient of 0.988, and 100.00% for the year 2022, with a kappa coefficient of 1.000.
Page(s):
1-1
DOI:
DOI not available
Published:
Journal: Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book), Volume: 0, Issue: 0, Year: 2024