Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers
In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Eng...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5498 |
| _version_ | 1827645546482892800 |
|---|---|
| author | Imane Serbouti Mohammed Raji Mustapha Hakdaoui Fouad El Kamel Biswajeet Pradhan Shilpa Gite Abdullah Alamri Khairul Nizam Abdul Maulud Abhirup Dikshit |
| author_facet | Imane Serbouti Mohammed Raji Mustapha Hakdaoui Fouad El Kamel Biswajeet Pradhan Shilpa Gite Abdullah Alamri Khairul Nizam Abdul Maulud Abhirup Dikshit |
| author_sort | Imane Serbouti |
| collection | DOAJ |
| description | In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km<sup>2</sup> area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions. |
| first_indexed | 2024-03-09T18:41:42Z |
| format | Article |
| id | doaj.art-0ded2700b888428b815ea767258f1d64 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:41:42Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0ded2700b888428b815ea767258f1d642023-11-24T06:40:00ZengMDPI AGRemote Sensing2072-42922022-10-011421549810.3390/rs14215498Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-ClassifiersImane Serbouti0Mohammed Raji1Mustapha Hakdaoui2Fouad El Kamel3Biswajeet Pradhan4Shilpa Gite5Abdullah Alamri6Khairul Nizam Abdul Maulud7Abhirup Dikshit8Laboratory of Applied Geology, Geomatic and Environment, Department of Geology, Faculty of Sciences Ben M’Sik, Hassan II University of Casablanca, Casablanca 20000, MoroccoLaboratory of Applied Geology, Geomatic and Environment, Department of Geology, Faculty of Sciences Ben M’Sik, Hassan II University of Casablanca, Casablanca 20000, MoroccoLaboratory of Applied Geology, Geomatic and Environment, Department of Geology, Faculty of Sciences Ben M’Sik, Hassan II University of Casablanca, Casablanca 20000, MoroccoLaboratory of Geosciences Applied to Urban Development Engineering (GAIA), Department of Geology, University Hassan II-Faculty of Sciences, Casablanca 20000, MoroccoCentre for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Civil and Environmental Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, AustraliaArtificial Intelligence and Machine Learning Department, Symbiosis Institute of Technology, Sym-Biosis International (Deemed) University, Pune 412115, IndiaDepartment of Geology and Geophysics, College of Science, King Saud University, Riyadh 11451, Saudi ArabiaEarth Observation Centre, Institute of Climate Change, Universiti Kebangsaan Malaysia, Bangi 43600, MalaysiaCentre for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Civil and Environmental Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, AustraliaIn this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km<sup>2</sup> area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions.https://www.mdpi.com/2072-4292/14/21/5498machine learning algorithmsgoogle earth enginedempster–shafer theorylithological mappingSentinel 2AMoroccan Meseta |
| spellingShingle | Imane Serbouti Mohammed Raji Mustapha Hakdaoui Fouad El Kamel Biswajeet Pradhan Shilpa Gite Abdullah Alamri Khairul Nizam Abdul Maulud Abhirup Dikshit Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers Remote Sensing machine learning algorithms google earth engine dempster–shafer theory lithological mapping Sentinel 2A Moroccan Meseta |
| title | Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers |
| title_full | Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers |
| title_fullStr | Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers |
| title_full_unstemmed | Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers |
| title_short | Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers |
| title_sort | improved lithological map of large complex semi arid regions using spectral and textural datasets within google earth engine and fused machine learning multi classifiers |
| topic | machine learning algorithms google earth engine dempster–shafer theory lithological mapping Sentinel 2A Moroccan Meseta |
| url | https://www.mdpi.com/2072-4292/14/21/5498 |
| work_keys_str_mv | AT imaneserbouti improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT mohammedraji improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT mustaphahakdaoui improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT fouadelkamel improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT biswajeetpradhan improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT shilpagite improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT abdullahalamri improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT khairulnizamabdulmaulud improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers AT abhirupdikshit improvedlithologicalmapoflargecomplexsemiaridregionsusingspectralandtexturaldatasetswithingoogleearthengineandfusedmachinelearningmulticlassifiers |