Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco
Accurate lithological mapping is a crucial juncture for geological studies and mineral exploration. Hyperspectral data provide the opportunity to extract detailed information about the geology and mineralogy of the Earth’s surface. Machine learning (ML) and deep learning (DL) techniques provide an a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI
2023
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/105849/1/AminBeiranvandPour2023_EvaluatingthePerformanceofMachineLearning.pdf |
| _version_ | 1811132215391682560 |
|---|---|
| author | Hajaj, Soufiane El Harti, Abderrazak Jellouli, Amine Pour, Amin Beiranvand Himyari, Saloua Mnissar Hamzaoui, Abderrazak Hashim, Mazlan |
| author_facet | Hajaj, Soufiane El Harti, Abderrazak Jellouli, Amine Pour, Amin Beiranvand Himyari, Saloua Mnissar Hamzaoui, Abderrazak Hashim, Mazlan |
| author_sort | Hajaj, Soufiane |
| collection | ePrints |
| description | Accurate lithological mapping is a crucial juncture for geological studies and mineral exploration. Hyperspectral data provide the opportunity to extract detailed information about the geology and mineralogy of the Earth’s surface. Machine learning (ML) and deep learning (DL) techniques provide an accurate and effective mapping of various types of lithologies in arid and semi-arid regions. This article discusses the use of machine learning algorithms, specifically Support Vector Machines (SVM), one-dimensional Convolutional Neural Network (1D-CNN), random forest (RF), and k-nearest neighbor (KNN), for lithological mapping in a complex area with strong hydrothermal alteration. The study evaluates the performance of the four algorithms in three different zones in the Ameln valley shear zone (AVSZ) area at eastern Kerdous inlier, Moroccan western Anti-Atlas. The results demonstrated that 1D-CNN achieved the best classification results for most lithological units. Additionally, the LK-SVM demonstrated good mapping results compared to the other SVM models, as well as RF and KNN. Our study concludes that the combination of the CNN and HyMap data can provide the most accurate lithologic mapping for the three selected region, with an overall accuracy of ~95%. However, this study highlights the challenges in identifying different lithological units using remotely sensed data due to spectrum similarities induced by similar chemical and mineralogical compositions. This study emphasizes the importance of carefully considering and evaluating ML and DL methods for lithological mapping studies, then recommends the high-resolution hyperspectral data and DL models for accurate results. The implications of this study would be fascinating to exploration geologists for Mineral Prospectivity Mapping (MPM), especially in selecting the most appropriate techniques for highly accurate mineral mapping in metallogenic provinces. |
| first_indexed | 2024-09-23T23:59:49Z |
| format | Article |
| id | utm.eprints-105849 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-09-23T23:59:49Z |
| publishDate | 2023 |
| publisher | MDPI |
| record_format | dspace |
| spelling | utm.eprints-1058492024-05-20T07:10:43Z http://eprints.utm.my/105849/ Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco Hajaj, Soufiane El Harti, Abderrazak Jellouli, Amine Pour, Amin Beiranvand Himyari, Saloua Mnissar Hamzaoui, Abderrazak Hashim, Mazlan G Geography (General) Accurate lithological mapping is a crucial juncture for geological studies and mineral exploration. Hyperspectral data provide the opportunity to extract detailed information about the geology and mineralogy of the Earth’s surface. Machine learning (ML) and deep learning (DL) techniques provide an accurate and effective mapping of various types of lithologies in arid and semi-arid regions. This article discusses the use of machine learning algorithms, specifically Support Vector Machines (SVM), one-dimensional Convolutional Neural Network (1D-CNN), random forest (RF), and k-nearest neighbor (KNN), for lithological mapping in a complex area with strong hydrothermal alteration. The study evaluates the performance of the four algorithms in three different zones in the Ameln valley shear zone (AVSZ) area at eastern Kerdous inlier, Moroccan western Anti-Atlas. The results demonstrated that 1D-CNN achieved the best classification results for most lithological units. Additionally, the LK-SVM demonstrated good mapping results compared to the other SVM models, as well as RF and KNN. Our study concludes that the combination of the CNN and HyMap data can provide the most accurate lithologic mapping for the three selected region, with an overall accuracy of ~95%. However, this study highlights the challenges in identifying different lithological units using remotely sensed data due to spectrum similarities induced by similar chemical and mineralogical compositions. This study emphasizes the importance of carefully considering and evaluating ML and DL methods for lithological mapping studies, then recommends the high-resolution hyperspectral data and DL models for accurate results. The implications of this study would be fascinating to exploration geologists for Mineral Prospectivity Mapping (MPM), especially in selecting the most appropriate techniques for highly accurate mineral mapping in metallogenic provinces. MDPI 2023-06 Article PeerReviewed application/pdf en http://eprints.utm.my/105849/1/AminBeiranvandPour2023_EvaluatingthePerformanceofMachineLearning.pdf Hajaj, Soufiane and El Harti, Abderrazak and Jellouli, Amine and Pour, Amin Beiranvand and Himyari, Saloua Mnissar and Hamzaoui, Abderrazak and Hashim, Mazlan (2023) Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco. Minerals, 13 (6). pp. 1-22. ISSN 2075-163X http://dx.doi.org/10.3390/min13060766 DOI:10.3390/min13060766 |
| spellingShingle | G Geography (General) Hajaj, Soufiane El Harti, Abderrazak Jellouli, Amine Pour, Amin Beiranvand Himyari, Saloua Mnissar Hamzaoui, Abderrazak Hashim, Mazlan Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title | Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title_full | Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title_fullStr | Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title_full_unstemmed | Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title_short | Evaluating the performance of machine learning and deep learning techniques to HyMap imagery for lithological mapping in a semi-arid region: case study from Western Anti-Atlas, Morocco |
| title_sort | evaluating the performance of machine learning and deep learning techniques to hymap imagery for lithological mapping in a semi arid region case study from western anti atlas morocco |
| topic | G Geography (General) |
| url | http://eprints.utm.my/105849/1/AminBeiranvandPour2023_EvaluatingthePerformanceofMachineLearning.pdf |
| work_keys_str_mv | AT hajajsoufiane evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT elhartiabderrazak evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT jellouliamine evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT pouraminbeiranvand evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT himyarisalouamnissar evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT hamzaouiabderrazak evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco AT hashimmazlan evaluatingtheperformanceofmachinelearninganddeeplearningtechniquestohymapimageryforlithologicalmappinginasemiaridregioncasestudyfromwesternantiatlasmorocco |