Abstract
To facilitate the advances in Sentinel-2A products for land cover from Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat imagery, Sentinel-2A MultiSpectral Instrument Level-1C (MSIL1C) images are investigated for large-scale vegetation mapping in an arid land environment that is located in the Ili River delta, Kazakhstan. For accurate classification purposes, multi-resolution segmentation (MRS) based extended object-guided morphological profiles (EOMPs) are proposed and then compared with conventional morphological profiles (MPs), MPs with partial reconstruction (MPPR), object-guided MPs (OMPs), OMPs with mean values (OMPsM), and object-oriented (OO)-based image classification techniques. Popular classifiers, such as C4.5, an extremely randomized decision tree (ERDT), random forest (RaF), rotation forest (RoF), classification via random forest regression (CVRFR), ExtraTrees, and radial basis function (RBF) kernel-based support vector machines (SVMs) are adopted to answer the question of whether nested dichotomies (ND) and ensembles of ND (END) are truly superior to direct and error-correcting output code (ECOC) multiclass classification frameworks. Finally, based on the results, the following conclusions are drawn: 1) the superior performance of OO-based techniques over MPs, MPPR, OMPs, and OMPsM is clear for Sentinel-2A MSIL1C image classification, while the best results are achieved by the proposed EOMPs; 2) the superior performance of ND, ND with class balancing (NDCB), ND with data balancing (NDDB), ND with random-pair selection (NDRPS), and ND with further centroid (NDFC) over direct and ECOC frameworks is not confirmed, especially in the cases of using weak classifiers for low-dimensional datasets; 3) from computationally efficient, high accuracy, redundant to data dimensionality and easy of implementations points of view, END, ENDCB, ENDDB, and ENDRPS are alternative choices to direct and ECOC frameworks; 4) surprisingly, because in the ensemble learning (EL) theorem, “weaker” classifiers (ERDT here) always have a better chance of reaching the trade-off between diversity and accuracy than “stronger” classifies (RaF, ExtraTrees, and SVM here), END with ERDT (END-ERDT) achieves the best performance with less than a 0.5% difference in the overall accuracy (OA) values, but is 100 to 10000 times faster than END with RaF and ExtraTrees, and ECOC with SVM while using different datasets with various dimensions; and, 5) Sentinel-2A MSIL1C is better choice than the land cover products from MODIS and Landsat imagery for vegetation species mapping in an arid land environment, where the vegetation species are critically important, but sparsely distributed.
Highlights
Arid and semiarid lands encompass approximately 30–40% of the Earth’s surface, and Central Asia contains one of the world’s largest arid and semiarid areas
The superiority of MPs with partial reconstruction (MPPR) compared to M1P4sofa3n1d object guided morphological profiles (OMPs) and the superiority of OMPsM when compared to MPPR is clear, which again supports the fifninddininggssbybyLiLaioaoeteatl.a[l9. 7[9] 7a]ndanSdamSaamt eattaelt. [a9l8. ][.9A8]d. dAidtidonitaiollnya, ltlhye, ptheerfopremrfaonrmceaonfcOe Oof aOnOd OanMdPOs cMouPlsd accotuualdllyacbteualilmlyitbeed lbimy isteetdtinbgy tsheettsineggmtheentsaetgiomnesnctaalteiopnasrcaamleetpearrλamtoevteerryλ ltaorgveevryalluaergs.eFvoarluexesa.mFpolre, aedxeacmrepalsei,nagdterecnredasinintghetrOenAd vinaltuheesOfrAomvaOluMesPfsrcoamn ObeMoPbssecravnebdeaoftbesretrhveedstaafrtteinrgthsecasltearitsinlagrgscearltehiasn 1l0a0rgweirthth1a0n01o0r05w0istcha1le00stoerp5s0(ssecealtehsetebprosw(sneelitnhees)b.rown lines)
Sentinel-2 MSIL1C images of the Ili River delta region of Kazakhstan were classified while using spectral and extended OMPs (EOMPs) to investigate the performance of the Sentinel-2A MSIL1C products for vegetation mapping in an arid land environment with respect to land cover products from Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat and to answer the question of “is ND and END are superior to state-of-the-art direct and ECOC-based-multiclass classification approaches?” and an accurate classification purposes
Summary
Arid and semiarid lands encompass approximately 30–40% of the Earth’s surface, and Central Asia contains one of the world’s largest arid and semiarid areas. The effects and responses of landscape heterogeneity on the local and regional atmosphere, the surface energy balance, the carbon exchange, and climate changes are major topics that have attracted widespread interest [1,2,3,4,5]. Among these responses, the vegetation species, distribution, diversity, and biomass in these lands typically undergo wide seasonal and international fluctuations, which are largely regulated by water availability and impacted by both climatic shifts and human activities [6,7,8]. Monitoring the vegetation status of these lands is an essential part of identifying problems, developing solutions, and assessing the effects of actions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
