A Comparative Study of Advanced Land Use/Land Cover Classification Algorithms Using Sentinel-2 Data

Abstract

<p><strong>Abstract.</strong> Land Use/ Land Cover (LU/LC) is a major driving phenomenon of distributed ecosystems and its functioning. Interpretation of remote sensor data acquired from satellites requires enhancement through classification in order to attain better results. Classification of satellite products provides detailed information about the existing landscape that can also be analyzed on temporal basis. Image processing techniques acts as a platform for analysis of raw data using supervised and unsupervised classification algorithms. Classification comprises two broad ranges in which, the analyst specifies the classes by defining the training sites called supervised classification where as automatically clustering of pixels to the defined number of classes namely the unsupervised classification. This study attempts to perform the LU/LC classification for Paonta Sahib region of Himachal Pradesh which is a major industrial belt. The data obtained from Sentinel 2A, from which the stacked bands of 10<span class="thinspace"></span>m resolution are only used. Various classification algorithms such as Minimum Distance, Maximum Likelihood, Parallelepiped and Support Vector Machine (SVM) of supervised classifiers and ISO Data, K-Means of unsupervised classifiers are applied. Using the applied classification results, accuracy assessment is estimated and compared. Of these applied methods, the classification method, maximum likelihood provides highest accuracy and is considered to be the best for LU/LC classification using Sentinel-2A data.</p>

Comprehensive review on land use/land cover change classification in remote sensing

“…Maximum Likelihood Classification 1,4,7,9,12,13,[15][16][17]22,23,25,26,30,[32][33][34][35][36][37]39,40,42,[47][48][49]51,54,55,57,68,70,80 Estimation of each pixel to the LU/LC class which has the highest probability.…”

“…SVM Classification 4,20,40,41,44,47,51,56,62,63,67 This method helps to find the hyper-plane that separates two or more LU/LC classes in the satellite image.…”

“…Researchers use image enhancement techniques to reduce the dimensionality of the satellite data: PCA, MNF, Independent Component Analysis (ICA) and wavelet dimensionality reduction. 9,19,25,29,30,34,46,47,51,53,54,56,[61][62][63]67,80,82 Frequently used atmospheric correction methods are Dark Object Subtraction (DOS), Quick Atmospheric Correction (QUAC), FLAASH, Apparent Reflectance Model (ARM) and the F mask method. [7][8][9]12,15,[18][19][20]23,28,29,33,35,37,40,41,45,49,[61][62][63]66,67,70,74,75,79 Geometric corrections include Orthorectification, Geo-referencing, Image Registration, ASCII Coordinate Conversion and Resampling.…”

“…Image Enhancement 9,19,25,29,30,34,46,47,51,53,54,56,[61][62][63]67,80,82 This method helps in reducing the dimensionality and enhancing the contrast of the satellite image.…”

Assessment on the Potential of Multispectral and Hyperspectral Datasets for Land Use/Land Cover Classification

“…Technical advancements in spatial sciences havefavored the researches to utilize remotely sensed imageries for extraction of land cover information. Potential remote sensing methods are highly capable of providingdatasets with high spatial, spectral, and temporal resolutions that promote further analysis [1,2]. Multispectral and hyperspectral datasets obtained from spaceborne and airborne platforms yield possible results when used for numerous geospatial use cases.…”