Impact of Various Atmospheric Corrections on Sentinel-2 Land Cover Classification Accuracy Using Machine Learning Classifiers

ISPRS International Journal of Geo-Information

Damir Medak¹  Luka Rumora¹  Mario Miler¹ 

[1] Faculty of Geodesy, University of Zagreb, 10000 Zagreb, Croatia;

关键词: atmospheric correction;    Sentinel-2;    land cover classification;    machine learning;    radiometric indices;    SVM;   

DOI  :  10.3390/ijgi9040277

来源: DOAJ

【 摘 要 】

Atmospheric correction is one of the key parts of remote sensing preprocessing because it can influence and change the final classification result. This research examines the impact of five different atmospheric correction processing on land cover classification accuracy using Sentinel-2 satellite imagery. Those are surface reflectance (SREF), standardized surface reflectance (STDSREF), Sentinel-2 atmospheric correction (S2AC), image correction for atmospheric effects (iCOR), dark object subtraction (DOS) and top of the atmosphere (TOA) reflectance without any atmospheric correction. Sentinel-2 images corrected with stated atmospheric corrections were classified using four different machine learning classification techniques namely extreme gradient boosting (XGB), random forests (RF), support vector machine (SVM) and catboost (CB). For classification, five different classes were used: bare land, low vegetation, high vegetation, water and built-up area. SVM classification provided the best overall result for twelve dates, for all atmospheric corrections. It was the best method for both cases: when using Sentinel-2 bands and radiometric indices and when using just spectral bands. The best atmospheric correction for classification with SVM using radiometric indices is S2AC with the median value of 96.54% and the best correction without radiometric indices is STDSREF with the median value of 96.83%.

【 授权许可】

Unknown