Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq
Monitoring the propagation of dunes is essential for natural hazard management. Accurate dunes mapping is critical in this situation. Landscape elements such as vegetation, water, dunes, and built-up are commonly separated using spectral indices. The discovery of dune features using a spect...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Union of Iraqi Geologists (UIG)
2022-06-01
|
| Series: | Iraqi Geological Journal |
| Online Access: | https://igj-iraq.org/igj/index.php/igj/article/view/1027 |
| _version_ | 1798038389520334848 |
|---|---|
| author | Ehsan Ali Al-Zubaidi Ahmed H. Al-Sulttani Furkan Rabee |
| author_facet | Ehsan Ali Al-Zubaidi Ahmed H. Al-Sulttani Furkan Rabee |
| author_sort | Ehsan Ali Al-Zubaidi |
| collection | DOAJ |
| description | Monitoring the propagation of dunes is essential for natural hazard management. Accurate dunes mapping is critical in this situation. Landscape elements such as vegetation, water, dunes, and built-up are commonly separated using spectral indices. The discovery of dune features using a spectral index is one of the most significant achievements in earth observation. In this research, it was suggested Drifting Sand Index (DSI) is a newly created index that can be used to extract the land of dunes. The DSI is calculated using the normalized difference between six Landsat-8 bands (B, R, G, NIR, SWIR-1, SWIR-2). The linear SVM algorithm was implemented using library (LibLINEAR) in the R software to calculate a new linear equation. Two versions of the index have been proposed, the first is the complete version (DSI-C), and the second is the reduced version (DSI-R). The suggested indices results were compared to four previously proposed spectral indices (NDSI-1, NDSI-2, CI, and NDSLI). The acquired results demonstrated that the DSI-C and DSI-R had a high ability to distinguish between sand and different land covers, such as vegetation, water bodies, and various soil types. The average overall accuracy for all levels of the DSI-R, DSI-C, NDSI-1, NDSI-2, CI, and NDSLI was 88.59%, 83.43%, 78.030%, 68.52%, 65.98%, and 56.490%, respectively. The average Kappa Coefficient for DSI-R, DSI-C NDSI-1, NDSI-2, CI, and NDSLI was 77.20%, 66.87%, 56.076%, 37.073%, 31.978%, and 13.011%, respectively. |
| first_indexed | 2024-04-11T21:39:32Z |
| format | Article |
| id | doaj.art-8692a18cedd842448173c922dd10d0a6 |
| institution | Directory Open Access Journal |
| issn | 2414-6064 2663-8754 |
| language | English |
| last_indexed | 2024-04-11T21:39:32Z |
| publishDate | 2022-06-01 |
| publisher | Union of Iraqi Geologists (UIG) |
| record_format | Article |
| series | Iraqi Geological Journal |
| spelling | doaj.art-8692a18cedd842448173c922dd10d0a62022-12-22T04:01:39ZengUnion of Iraqi Geologists (UIG)Iraqi Geological Journal2414-60642663-87542022-06-01551F10212110.46717/igj.55.1F.9Ms-2022-06-24Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern IraqEhsan Ali Al-ZubaidiAhmed H. Al-Sulttani Furkan Rabee Monitoring the propagation of dunes is essential for natural hazard management. Accurate dunes mapping is critical in this situation. Landscape elements such as vegetation, water, dunes, and built-up are commonly separated using spectral indices. The discovery of dune features using a spectral index is one of the most significant achievements in earth observation. In this research, it was suggested Drifting Sand Index (DSI) is a newly created index that can be used to extract the land of dunes. The DSI is calculated using the normalized difference between six Landsat-8 bands (B, R, G, NIR, SWIR-1, SWIR-2). The linear SVM algorithm was implemented using library (LibLINEAR) in the R software to calculate a new linear equation. Two versions of the index have been proposed, the first is the complete version (DSI-C), and the second is the reduced version (DSI-R). The suggested indices results were compared to four previously proposed spectral indices (NDSI-1, NDSI-2, CI, and NDSLI). The acquired results demonstrated that the DSI-C and DSI-R had a high ability to distinguish between sand and different land covers, such as vegetation, water bodies, and various soil types. The average overall accuracy for all levels of the DSI-R, DSI-C, NDSI-1, NDSI-2, CI, and NDSLI was 88.59%, 83.43%, 78.030%, 68.52%, 65.98%, and 56.490%, respectively. The average Kappa Coefficient for DSI-R, DSI-C NDSI-1, NDSI-2, CI, and NDSLI was 77.20%, 66.87%, 56.076%, 37.073%, 31.978%, and 13.011%, respectively.https://igj-iraq.org/igj/index.php/igj/article/view/1027 |
| spellingShingle | Ehsan Ali Al-Zubaidi Ahmed H. Al-Sulttani Furkan Rabee Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq Iraqi Geological Journal |
| title | Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq |
| title_full | Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq |
| title_fullStr | Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq |
| title_full_unstemmed | Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq |
| title_short | Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq |
| title_sort | sand dunes spectral index determination using machine learning model case study of baiji sand dunes field northern iraq |
| url | https://igj-iraq.org/igj/index.php/igj/article/view/1027 |
| work_keys_str_mv | AT ehsanalialzubaidi sanddunesspectralindexdeterminationusingmachinelearningmodelcasestudyofbaijisanddunesfieldnortherniraq AT ahmedhalsulttani sanddunesspectralindexdeterminationusingmachinelearningmodelcasestudyofbaijisanddunesfieldnortherniraq AT furkanrabee sanddunesspectralindexdeterminationusingmachinelearningmodelcasestudyofbaijisanddunesfieldnortherniraq |