Abstract
Multi-temporal imagery classification using spectral information and indices with random forest allows improving accuracy in land use and cover classification in semiarid Mediterranean areas, where the high fragmentation of the landscape caused by multiple factors complicates the task. Hence, since data come from different dates, atmospheric correction is needed to retrieve surface reflectivity values. The Sen2Cor, MAJA and ACOLITE algorithms have proven their good performances in these areas in different comparative studies, and DOS is a basic method that is widely used. The aim in this study was to test the feasibility of its application to the data set to improve the values of accuracy in classification and the performance in properly labelling different classes. Additionally, we tried to correct accuracy and separability mixing predictors with different algorithms. The results showed that, using a single algorithm, the general accuracy and kappa index from ACOLITE were the highest, 0.80 ± 0.01 and 0.76 ± 0.01., but the separability between problematic classes was slightly improved by using MAJA. Any combination of the different algorithms tested increased the values of classification, although they may help with separability between some pairs of classes.
Highlights
IntroductionRemote sensing imagery classification is generally used to monitor land use and land cover on the Earth’s surface
Land use, land cover and their changes are among the most relevant environmental variables [1,2] with an influence on topics of crucial importance such as global change and land management at all spatial scales [1].Remote sensing imagery classification is generally used to monitor land use and land cover on the Earth’s surface
Our main objectives were to test if the Atmospheric correction (AC) methods introduce a significant increase in classification accuracy, to identify the methods whose increase is significantly higher than others and to compare those increases with those produced by the use of 4, instead of 3, images, as well as by the introduction of spectral indices
Summary
Remote sensing imagery classification is generally used to monitor land use and land cover on the Earth’s surface. The availability of a wide range of spaceborne optical and radar systems has boosted the use of multi-spectral and multi-sensor imagery with high temporal and spatial resolution from different satellites and has generalized studies aiming to improve land cover classification accuracy. Sentinel-2 (S2) consists of two twin-polar orbiting satellites (Sentinel-2A and 2B) active since 2018 [4,5]. They contain a Multi-Spectral Instrument (MSI) that samples 13 spectral bands including visible, near-infrared and shortwave infrared. Several studies [6,7,8,9] have tested these images with good results due to their better temporal and spatial resolution and a complete interoperability with previous satellite programs such as Landsat [4]
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
