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

2020 ◽  
Vol 9 (4) ◽  
pp. 277 ◽  
Author(s):  
Luka Rumora ◽  
Mario Miler ◽  
Damir Medak
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Classification Accuracy ◽  
Atmospheric Correction ◽  
Land Cover Classification ◽  
Support Vector ◽  
Atmospheric Effects ◽  
Surface Reflectance ◽  
The Impact ◽  
Sentinel 2

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%.

scholarly journals Urban land cover classification using hyperspectral data

2014 ◽  
Vol XL-8 ◽  
pp. 751-754 ◽  
Author(s):  
G. Hegde ◽  
J. Mohammed Ahamed ◽  
R. Hebbar ◽  
U. Raj
Keyword(s):  
Land Cover ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Urban Land ◽  
Hyperspectral Data ◽  
Support Vector ◽  
Atmospheric Effects ◽  
Spectral Angle Mapper ◽  
Urban Land Cover ◽  
Lower Accuracy

Urban land cover classification using remote sensing data is quite challenging due to spectrally and spatially complex urban features. The present study describes the potential use of hyperspectral data for urban land cover classification and its comparison with multispectral data. EO-1 Hyperion data of October 05, 2012 covering parts of Bengaluru city was analyzed for land cover classification. The hyperspectral data was initially corrected for atmospheric effects using MODTRAN based FLAASH module and Minimum Noise Fraction (MNF) transformation was applied to reduce data dimensionality. The threshold Eigen value of 1.76 in VNIR region and 1.68 in the SWIR region was used for selection of 145 stable bands. Advanced per pixel classifiers <i>viz.</i>, Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) were used for general urban land cover classification. Accuracy assessment of the classified data revealed that SVM was quite superior (82.4 per cent) for urban land cover classification as compared to SAM (67.1 per cent). Selecting training samples using end members significantly improved the classification accuracy by 20.1 per cent in SVM. The land cover classification using multispectral LISS-III data using SVM showed lower accuracy mainly due to limitation of spectral resolution. The study indicated the requirement of additional narrow bands for achieving reasonable classification accuracy of urban land cover. Future research is focused on generating hyperspectral library for different urban features.

scholarly journals Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery

Water ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 82
Author(s):  
Huaxin Liu ◽  
Qigang Jiang ◽  
Yue Ma ◽  
Qian Yang ◽  
Pengfei Shi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Classification Scheme ◽  
Land Cover Classification ◽  
Support Vector ◽  
Wetland Classification ◽  
Positive Contribution ◽  
Object Based ◽  
Extreme Gradient Boosting ◽  
Sentinel 2

The development of advanced and efficient methods for mapping and monitoring wetland regions is essential for wetland resources conservation, management, and sustainable development. Although remote sensing technology has been widely used for detecting wetlands information, it remains a challenge for wetlands classification due to the extremely complex spatial patterns and fuzzy boundaries. This study aims to implement a comprehensive and effective classification scheme for wetland land covers. To achieve this goal, a novel object-based multigrained cascade forest (OGCF) method with multisensor data (including Sentinel-2 and Radarsat-2 remote sensing imagery) was proposed to classify the wetlands and their adjacent land cover classes in the wetland National Natural Reserve. Moreover, a hybrid selection method (ReliefF-RF) was proposed to optimize the feature set in which the spectral and polarimetric decomposition features are contained. We obtained six spectral features from visible and shortwave infrared bands and 10 polarimetric decomposition features from the H/A/Alpha, Pauli, and Krogager decomposition methods. The experimental results showed that the OGCF method with multisource features for land cover classification in wetland regions achieved the overall accuracy and kappa coefficient of 88.20% and 0.86, respectively, which outperformed the support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The accuracy of the wetland classes ranged from 75.00% to 97.53%. The proposed OGCF method exhibits a good application potential for wetland land cover classification. The classification scheme in this study will make a positive contribution to wetland inventory and monitoring and be able to provide technical support for protecting and developing natural resources.

scholarly journals BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

2016 ◽  
Vol XLI-B7 ◽  
pp. 335-340 ◽  
Author(s):  
F. Pirotti ◽  
F. Sunar ◽  
M. Piragnolo
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Cross Validation ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Learning Methods ◽  
Control Dataset ◽  
Vector Machines ◽  
Sentinel 2

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. <br><br> In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km<sup>2</sup>, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. <br><br> Validation is carried out using three different approaches: (i) using pixels from the training dataset (<i>train</i>), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (<i>kfold</i>) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (<i>full</i>) and with k-fold cross-validation (<i>kfold</i>) with ten folds. Results from validation of predictions of the whole dataset (<i>full</i>) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

scholarly journals Land use/land cover classification using machine learning models

2022 ◽  
Vol 12 (2) ◽  
pp. 2040
Author(s):  
Subhra Swetanisha ◽  
Amiya Ranjan Panda ◽  
Dayal Kumar Behera
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Land Cover ◽  
Land Cover Classification ◽  
Support Vector ◽  
Landsat 8 ◽  
Electromagnetic Spectrum ◽  
Learning Models ◽  
Extreme Gradient Boosting ◽  
Machine Learning Models

<p>An ensemble model has been proposed in this work by combining the extreme gradient boosting classification (XGBoost) model with support vector machine (SVM) for land use and land cover classification (LULCC). We have used the multispectral Landsat-8 operational land imager sensor (OLI) data with six spectral bands in the electromagnetic spectrum (EM). The area of study is the administrative boundary of the twin cities of Odisha. Data collected in 2020 is classified into seven land use classes/labels: river, canal, pond, forest, urban, agricultural land, and sand. Comparative assessments of the results of ten machine learning models are accomplished by computing the overall accuracy, kappa coefficient, producer accuracy and user accuracy. An ensemble classifier model makes the classification more precise than the other state-of-the-art machine learning classifiers.</p>

scholarly journals BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

2016 ◽  
Vol XLI-B7 ◽  
pp. 335-340 ◽  
Author(s):  
F. Pirotti ◽  
F. Sunar ◽  
M. Piragnolo
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Cross Validation ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Learning Methods ◽  
Control Dataset ◽  
Vector Machines ◽  
Sentinel 2

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. &lt;br&gt;&lt;br&gt; In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km&lt;sup&gt;2&lt;/sup&gt;, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. &lt;br&gt;&lt;br&gt; Validation is carried out using three different approaches: (i) using pixels from the training dataset (&lt;i&gt;train&lt;/i&gt;), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (&lt;i&gt;kfold&lt;/i&gt;) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (&lt;i&gt;full&lt;/i&gt;) and with k-fold cross-validation (&lt;i&gt;kfold&lt;/i&gt;) with ten folds. Results from validation of predictions of the whole dataset (&lt;i&gt;full&lt;/i&gt;) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

scholarly journals Using Sentinel-1, Sentinel-2, and Planet Imagery to Map Crop Type of Smallholder Farms

2021 ◽  
Vol 13 (10) ◽  
pp. 1870
Author(s):  
Preeti Rao ◽  
Weiqi Zhou ◽  
Nishan Bhattarai ◽  
Amit K. Srivastava ◽  
Balwinder Singh ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Farming Systems ◽  
Support Vector ◽  
Smallholder Farming ◽  
High Resolution Imagery ◽  
Crop Types ◽  
Spatio Temporal ◽  
The Impact ◽  
Sentinel 2 ◽  
Smallholder Systems

Remote sensing offers a way to map crop types across large spatio-temporal scales at low costs. However, mapping crop types is challenging in heterogeneous, smallholder farming systems, such as those in India, where field sizes are often smaller than the resolution of historically available imagery. In this study, we examined the potential of relatively new, high-resolution imagery (Sentinel-1, Sentinel-2, and PlanetScope) to identify four major crop types (maize, mustard, tobacco, and wheat) in eastern India using support vector machine (SVM). We found that a trained SVM model that included all three sensors led to the highest classification accuracy (85%), and the inclusion of Planet data was particularly helpful for classifying crop types for the smallest farms (<600 m2). This was likely because its higher spatial resolution (3 m) could better account for field-level variations in smallholder systems. We also examined the impact of image timing on the classification accuracy, and we found that early-season images did little to improve our models. Overall, we found that readily available Sentinel-1, Sentinel-2, and Planet imagery were able to map crop types at the field-scale with high accuracy in Indian smallholder systems. The findings from this study have important implications for the identification of the most effective ways to map crop types in smallholder systems.

scholarly journals Sentinel-2 Satellite Imagery for Urban Land Cover Classification by Optimized Random Forest Classifier

2021 ◽  
Vol 11 (2) ◽  
pp. 543
Author(s):  
Tianxiang Zhang ◽  
Jinya Su ◽  
Zhiyong Xu ◽  
Yulin Luo ◽  
Jiangyun Li
Keyword(s):  
Random Forest ◽  
Land Cover ◽  
Satellite Imagery ◽  
Parameter Optimization ◽  
Satellite Image ◽  
Land Cover Classification ◽  
Random Forest Classifier ◽  
Support Vector ◽  
Wide Range ◽  
Sentinel 2

Land cover classification is able to reflect the potential natural and social process in urban development, providing vital information to stakeholders. Recent solutions on land cover classification are generally addressed by remotely sensed imagery and supervised classification methods. However, a high-performance classifier is desirable but challenging due to the existence of model hyperparameters. Conventional approaches generally rely on manual tuning, which is time-consuming and far from satisfying. Therefore, this work aims to propose a systematic method to automatically tune the hyperparameters by Bayesian parameter optimization for the random forest classifier. The recently launched Sentinel-2A/B satellites are drawn to provide the remote sensing imageries for land cover classification case study in Beijing, China, which have the best spectral/spatial resolutions among the freely available satellites. The improved random forest with Bayesian parameter optimization is compared against the support vector machine (SVM) and random forest (RF) with default hyperparameters by discriminating five land cover classes including building, tree, road, water, and crop field. Comparative experimental results show that the optimized RF classifier outperforms the conventional SVM and the RF with default hyperparameters in terms of accuracy, precision, and recall. The effects of band/feature number and the band usefulness are also assessed. It is envisaged that the improved classifier for Sentinel-2 satellite image processing can find a wide range of applications where high-resolution satellite imagery classification is applicable.

scholarly journals Environmental land-cover classification for integrated watershed studies: Cape Bounty, Melville Island, Nunavut

2020 ◽  
Vol 6 (4) ◽  
pp. 404-422
Author(s):  
Jacqueline K.Y. Hung ◽  
Paul Treitz
Keyword(s):  
Land Cover ◽  
Classification Accuracy ◽  
Vegetation Type ◽  
Land Cover Classification ◽  
Support Vector ◽  
Moisture Regime ◽  
Permafrost Degradation ◽  
Topographic Wetness Index ◽  
Surface Water Chemistry

Thematic maps developed from remote sensing data are extremely useful for designing intensive field studies, particularly for large areas that are logistically challenging to access. The integrated watershed studies at the Cape Bounty Arctic Watershed Observatory (CBAWO), Melville Island, Nunavut, rely heavily on land cover for establishing sampling locations regardless of the type of research being conducted (e.g., permafrost degradation, greenhouse gas exchange, surface water chemistry, etc.). Here, we present an environmental land-cover classification of the CBAWO that was developed through an iterative process employing parametric and non-parametric classification algorithms applied to WorldView-2 satellite data and topographic variables. The support vector machine classification of eight-band WorldView-2 spectral data and a topographic wetness index produced the highest classification accuracy for eight land-cover classes (overall classification accuracy: 90.7%; Kappa coefficient (κ): 0.89). This analysis also provided a more precise classification scheme, particularly in the context of the relationship between vegetation type and moisture regime. The environmental land-cover classification derived will better inform future integrated studies of the watershed and allow for upscaling of site-level characteristics to the watershed-scale using the updated vegetation classes.

Sign in / Sign up

Export Citation Format

Share Document