Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco
The development of efficient classifiers for land cover remains challenging due to the presence of hyperparameters in the model. Conventional approaches rely on manual tuning, which is both time-consuming and impractical, often leading to suboptimal results. This study aimed to optimize the hyperpar...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitat Politècnica de València
2024-11-01
|
| Series: | Revista de Teledetección |
| Subjects: | |
| Online Access: | https://polipapers.upv.es/index.php/raet/article/view/22060 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549739313233920 |
|---|---|
| author | Abdelhak El Kharki Jamila Mechbouh Miriam Wahbi Otmane Yazidi Alaoui Hakim Boulaassal Mustapha Maatouk Omar El Kharki |
| author_facet | Abdelhak El Kharki Jamila Mechbouh Miriam Wahbi Otmane Yazidi Alaoui Hakim Boulaassal Mustapha Maatouk Omar El Kharki |
| author_sort | Abdelhak El Kharki |
| collection | DOAJ |
| description | The development of efficient classifiers for land cover remains challenging due to the presence of hyperparameters in the model. Conventional approaches rely on manual tuning, which is both time-consuming and impractical, often leading to suboptimal results. This study aimed to optimize the hyperparameters of the Support Vector Machine (SVM) algorithm using the grid search method to map the distribution of the Argan forest in the Souss-Massa region of Morocco from Sentinel-2 satellite image. To achieve this, we examined the C parameter for the linear function, as well as the C and gamma parameters for the radial RBF and sigmoid functions. Similarly, we explored the C, gamma, and degree parameters for the polynomial function chosen using the grid search method. These parameters are compared with the default hyperparameters of each SVM function. The results are validated using the cross-validation method and by the following scores: accuracy, precision, recall, F1 score, and Cohen’s Kappa. The experiments were conducted using the Earth Engine Python API in Google Colab (Google Collaboratory). In addition, experimental results indicate that the hyperparameters selected by grid search yield higher scores than the default hyperparameters. The best results were achieved using the hyperparameters of the polynomial base kernel, specifically with C = 10, degree = 2, and gamma = 10. Accuracy = 96.61%. |
| format | Article |
| id | doaj-art-ac29343177944a67982baee6b9f2a562 |
| institution | Kabale University |
| issn | 1133-0953 1988-8740 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Universitat Politècnica de València |
| record_format | Article |
| series | Revista de Teledetección |
| spelling | doaj-art-ac29343177944a67982baee6b9f2a5622025-02-03T06:10:08ZengUniversitat Politècnica de ValènciaRevista de Teledetección1133-09531988-87402024-11-016510.4995/raet.2025.2206021250Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, MoroccoAbdelhak El Kharki0Jamila Mechbouh1Miriam Wahbi2Otmane Yazidi Alaoui3https://orcid.org/0000-0002-7100-2391Hakim Boulaassal4https://orcid.org/0000-0003-2342-4431Mustapha Maatouk5Omar El Kharki6Abdelmalek Essaâdi UniversityRif GéomatiqueAbdelmalek Essaâdi University Abdelmalek Essaâdi University Abdelmalek Essaâdi University Abdelmalek Essaâdi University Abdelmalek Essaâdi University The development of efficient classifiers for land cover remains challenging due to the presence of hyperparameters in the model. Conventional approaches rely on manual tuning, which is both time-consuming and impractical, often leading to suboptimal results. This study aimed to optimize the hyperparameters of the Support Vector Machine (SVM) algorithm using the grid search method to map the distribution of the Argan forest in the Souss-Massa region of Morocco from Sentinel-2 satellite image. To achieve this, we examined the C parameter for the linear function, as well as the C and gamma parameters for the radial RBF and sigmoid functions. Similarly, we explored the C, gamma, and degree parameters for the polynomial function chosen using the grid search method. These parameters are compared with the default hyperparameters of each SVM function. The results are validated using the cross-validation method and by the following scores: accuracy, precision, recall, F1 score, and Cohen’s Kappa. The experiments were conducted using the Earth Engine Python API in Google Colab (Google Collaboratory). In addition, experimental results indicate that the hyperparameters selected by grid search yield higher scores than the default hyperparameters. The best results were achieved using the hyperparameters of the polynomial base kernel, specifically with C = 10, degree = 2, and gamma = 10. Accuracy = 96.61%.https://polipapers.upv.es/index.php/raet/article/view/22060sentinel-2support vector machinehyperparameterargan forestsgrid search |
| spellingShingle | Abdelhak El Kharki Jamila Mechbouh Miriam Wahbi Otmane Yazidi Alaoui Hakim Boulaassal Mustapha Maatouk Omar El Kharki Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco Revista de Teledetección sentinel-2 support vector machine hyperparameter argan forests grid search |
| title | Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco |
| title_full | Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco |
| title_fullStr | Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco |
| title_full_unstemmed | Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco |
| title_short | Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco |
| title_sort | optimizing svm for argan tree classification using sentinel 2 data a case study in the sous massa region morocco |
| topic | sentinel-2 support vector machine hyperparameter argan forests grid search |
| url | https://polipapers.upv.es/index.php/raet/article/view/22060 |
| work_keys_str_mv | AT abdelhakelkharki optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT jamilamechbouh optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT miriamwahbi optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT otmaneyazidialaoui optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT hakimboulaassal optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT mustaphamaatouk optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco AT omarelkharki optimizingsvmforargantreeclassificationusingsentinel2dataacasestudyinthesousmassaregionmorocco |