Machine Learning Algorithms of Remote Sensing Data Processing for Mapping Changes in Land Cover Types over Central Apennines, Italy DOI Creative Commons
Polina Lemenkova

Journal of Imaging, Journal Year: 2025, Volume and Issue: 11(5), P. 153 - 153

Published: May 12, 2025

This work presents the use of remote sensing data for land cover mapping with a case Central Apennines, Italy. The include 8 Landsat 8-9 Operational Land Imager/Thermal Infrared Sensor (OLI/TIRS) satellite images in six-year period (2018–2024). operational workflow included image processing which were classified into raster maps automatically detected 10 classes types over tested study. approach was implemented by using set modules Geographic Resources Analysis Support System (GRASS) Information (GIS). To classify (RS) data, two approaches carried out. first is unsupervised classification based on MaxLike and clustering extracted Digital Numbers (DN) landscape feature spectral reflectance signals, second supervised performed several methods Machine Learning (ML), technically realised GRASS GIS scripting software. latter four ML algorithms embedded from Python’s Scikit-Learn library. These classifiers have been to detect subtle changes as derived showing different vegetation conditions spring autumn periods central northern

Language: Английский

Machine Learning Algorithms of Remote Sensing Data Processing for Mapping Changes in Land Cover Types over Central Apennines, Italy DOI Creative Commons
Polina Lemenkova

Journal of Imaging, Journal Year: 2025, Volume and Issue: 11(5), P. 153 - 153

Published: May 12, 2025

This work presents the use of remote sensing data for land cover mapping with a case Central Apennines, Italy. The include 8 Landsat 8-9 Operational Land Imager/Thermal Infrared Sensor (OLI/TIRS) satellite images in six-year period (2018–2024). operational workflow included image processing which were classified into raster maps automatically detected 10 classes types over tested study. approach was implemented by using set modules Geographic Resources Analysis Support System (GRASS) Information (GIS). To classify (RS) data, two approaches carried out. first is unsupervised classification based on MaxLike and clustering extracted Digital Numbers (DN) landscape feature spectral reflectance signals, second supervised performed several methods Machine Learning (ML), technically realised GRASS GIS scripting software. latter four ML algorithms embedded from Python’s Scikit-Learn library. These classifiers have been to detect subtle changes as derived showing different vegetation conditions spring autumn periods central northern

Language: Английский

Citations

0