A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Land Use—Classification by Machine Learning Classifiers Using Landsat 8 Imagery
https://orcid.org/http://orcid.org/0000-0002-7595-6934
https://orcid.org/http://orcid.org/0000-0001-8129-1214
Through the twentieth and first decades of the twenty-first century, quick and abandoned population growth, in combination with industrial and economic development, enhanced the frequency of land-use-land-cover change (LULCC) for several times, particularly in evolving nations. Moreover, the most effective ways to manage and analyze land transformation are the quantifiable valuation of changes in LULC, it is important to evaluate the comparison of the accuracy of different Land Use-Land Cover mapping algorithms in order to choose the good classifier for future earth observation and its applications. The QGIS tool is applied to consider minimal distance, maximum likelihood, and spectral angle mapping in this paper. Various classes have been explored, and training is carried out based on these to determine the accuracy of each method.
Land Use—Classification by Machine Learning Classifiers Using Landsat 8 Imagery
https://orcid.org/http://orcid.org/0000-0002-7595-6934
https://orcid.org/http://orcid.org/0000-0001-8129-1214
Through the twentieth and first decades of the twenty-first century, quick and abandoned population growth, in combination with industrial and economic development, enhanced the frequency of land-use-land-cover change (LULCC) for several times, particularly in evolving nations. Moreover, the most effective ways to manage and analyze land transformation are the quantifiable valuation of changes in LULC, it is important to evaluate the comparison of the accuracy of different Land Use-Land Cover mapping algorithms in order to choose the good classifier for future earth observation and its applications. The QGIS tool is applied to consider minimal distance, maximum likelihood, and spectral angle mapping in this paper. Various classes have been explored, and training is carried out based on these to determine the accuracy of each method.
Land Use—Classification by Machine Learning Classifiers Using Landsat 8 Imagery
https://orcid.org/http://orcid.org/0000-0002-7595-6934
https://orcid.org/http://orcid.org/0000-0001-8129-1214
Through the twentieth and first decades of the twenty-first century, quick and abandoned population growth, in combination with industrial and economic development, enhanced the frequency of land-use-land-cover change (LULCC) for several times, particularly in evolving nations. Moreover, the most effective ways to manage and analyze land transformation are the quantifiable valuation of changes in LULC, it is important to evaluate the comparison of the accuracy of different Land Use-Land Cover mapping algorithms in order to choose the good classifier for future earth observation and its applications. The QGIS tool is applied to consider minimal distance, maximum likelihood, and spectral angle mapping in this paper. Various classes have been explored, and training is carried out based on these to determine the accuracy of each method.
Land Use—Classification by Machine Learning Classifiers Using Landsat 8 Imagery
Lecture Notes in Civil Engineering
Pathak, Krishna Kant (editor) / Bandara, J. M. S. J. (editor) / Agrawal, Ramakant (editor) / Thakur, Reena (author) / Panse, Prashant (author)
International Conference on Recent Advances in Civil Engineering ; 2022
2023-10-03
10 pages
Article/Chapter (Book)
Electronic Resource
English
Mapping despoiled land cover from Landsat Thematic Mapper imagery
| Online Contents | 1995
Pansharpened Landsat 7 Imagery for Improved Urban Area Classification
| Online Contents | 2004
WAVELET COMPRESSION AND THE AUTOMATIC CLASSIFICATION OF LANDSAT IMAGERY
| Online Contents | 2000