Abstract
Abstract. Due to concerns of recent earth climate changes such as an increase of earth surface temperature and monitoring its effect on earth surface, environmental monitoring is a necessity. Environmental change monitoring in earth sciences needs land use land cover change (LULCC) modelling as a key factor to investigate impact of climate change phenomena such as droughts and floods on earth surface land cover. There are several free and commercial multi/hyper spectral data sources of Earth Observation (EO) satellites including Landsat, Sentinel and Spot. In this paper, for land use land cover modelling (LULCM), image classification of Landsat 8 using several mathematical and machine learning algorithms including Support Vector Machine (SVM), Random Forest (RF), Maximum Likelihood (ML) and a combination of SVM, ML and RF as a fit-for-purpose algorithm are implemented in R programming language and compared in terms of overall accuracy for image classification.
Highlights
Land cover is a fundamental factor that links and affect with many parts of the human and physical environment (Foody, 2002)
Support Vector Machine (SVM) and Random Forest (RF) methods are implemented within R programming language where Maximum Likelihood (ML) is implemented in QGIS using semi-automatic classification plug-in developed by Luca Congedo
RF (Breiman, 2001) method is an extension of classification and regression trees (CART; Breiman et al, 1984)
Summary
Land cover is a fundamental factor that links and affect with many parts of the human and physical environment (Foody, 2002). The change in land cover is considered as an important factor of global change affecting ecological systems (Vitousek, 1994) with an impact on the earth that is linked with climatic change (Skole, 1994). Complex landscapes are difficult to monitor due to sudden changes in environmental gradients (e.g. moisture, elevation and temperature) and a legacy of past interference (Rogan and Miller, 2006). Such heterogeneous landscapes are defined by land-cover categories that are complicated to be defined spectrally due to low inter-class separability and high intra-class variability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
