Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms
With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objec...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/7/1349 |
| _version_ | 1827696176274604032 |
|---|---|
| author | Laleh Ghayour Aminreza Neshat Sina Paryani Himan Shahabi Ataollah Shirzadi Wei Chen Nadhir Al-Ansari Marten Geertsema Mehdi Pourmehdi Amiri Mehdi Gholamnia Jie Dou Anuar Ahmad |
| author_facet | Laleh Ghayour Aminreza Neshat Sina Paryani Himan Shahabi Ataollah Shirzadi Wei Chen Nadhir Al-Ansari Marten Geertsema Mehdi Pourmehdi Amiri Mehdi Gholamnia Jie Dou Anuar Ahmad |
| author_sort | Laleh Ghayour |
| collection | DOAJ |
| description | With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers. |
| first_indexed | 2024-03-10T12:42:08Z |
| format | Article |
| id | doaj.art-fd1fad62f99744538f8c643e572ed54c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:42:08Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-fd1fad62f99744538f8c643e572ed54c2023-11-21T13:50:25ZengMDPI AGRemote Sensing2072-42922021-04-01137134910.3390/rs13071349Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning AlgorithmsLaleh Ghayour0Aminreza Neshat1Sina Paryani2Himan Shahabi3Ataollah Shirzadi4Wei Chen5Nadhir Al-Ansari6Marten Geertsema7Mehdi Pourmehdi Amiri8Mehdi Gholamnia9Jie Dou10Anuar Ahmad11Department of Natural Resources Engineering and Environment, Azad Hamedan University, Hamedan 65181-15743, IranDepartment of GIS/RS, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran 1477893855, IranDepartment of GIS/RS, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran 1477893855, IranDepartment of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaDepartment of Civil, Environmental and Natural Resources Engineering, Lulea University of Technology, 971 87 Lulea, SwedenResearch Geomorphologist, Ministry of Forests, Lands, Natural Resource Operations and Rural Development, 499 George Street, Prince George, BC V2L 1R5, CanadaDepartment of Geographic Information System and Remote Sensing, Aban Haraz Hitcher Education Institute, Amol 46131-46391, IranDepartment of Civil Engineering, Islamic Azad University, Sanandaj Branch, Sanandaj 6616935391, IranThree Gorges Research Center for Geo-Hazards, Ministry of Education, China University of Geosciences, Wuhan 430074, ChinaDepartment of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaWith the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers.https://www.mdpi.com/2072-4292/13/7/1349land covermachine learningremote sensingsatellite imageryclassification accuracySaqqez |
| spellingShingle | Laleh Ghayour Aminreza Neshat Sina Paryani Himan Shahabi Ataollah Shirzadi Wei Chen Nadhir Al-Ansari Marten Geertsema Mehdi Pourmehdi Amiri Mehdi Gholamnia Jie Dou Anuar Ahmad Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms Remote Sensing land cover machine learning remote sensing satellite imagery classification accuracy Saqqez |
| title | Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms |
| title_full | Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms |
| title_fullStr | Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms |
| title_full_unstemmed | Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms |
| title_short | Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms |
| title_sort | performance evaluation of sentinel 2 and landsat 8 oli data for land cover use classification using a comparison between machine learning algorithms |
| topic | land cover machine learning remote sensing satellite imagery classification accuracy Saqqez |
| url | https://www.mdpi.com/2072-4292/13/7/1349 |
| work_keys_str_mv | AT lalehghayour performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT aminrezaneshat performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT sinaparyani performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT himanshahabi performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT ataollahshirzadi performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT weichen performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT nadhiralansari performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT martengeertsema performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT mehdipourmehdiamiri performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT mehdigholamnia performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT jiedou performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms AT anuarahmad performanceevaluationofsentinel2andlandsat8olidataforlandcoveruseclassificationusingacomparisonbetweenmachinelearningalgorithms |