Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq
Desertification is a major environmental issue all over the world, and Al-Khidhir district, Al-Muthanna, in the south of Iraq is no exception. In mapping, assessing, and predicting desertification, remote sensing and geospatial solutions (spatial analysis, machine learning) are crucial. During 1998–...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Springer Nature
2022
|
| _version_ | 1825938454411739136 |
|---|---|
| author | Aldabbagh, Yasir Abdulameer Nayyef Mohd Shafri, Helmi Zulhaidi Mansor, Shattri Ismail, Mohd Hasmadi |
| author_facet | Aldabbagh, Yasir Abdulameer Nayyef Mohd Shafri, Helmi Zulhaidi Mansor, Shattri Ismail, Mohd Hasmadi |
| author_sort | Aldabbagh, Yasir Abdulameer Nayyef |
| collection | UPM |
| description | Desertification is a major environmental issue all over the world, and Al-Khidhir district, Al-Muthanna, in the south of Iraq is no exception. In mapping, assessing, and predicting desertification, remote sensing and geospatial solutions (spatial analysis, machine learning) are crucial. During 1998–2018, this study employed satellite images from Landsat TM, ETM + , and OLI to map and predict desertification in the Al-Khidhir district. The year 2028 was chosen as the target date. Prediction models were constructed using a 3D convolutional neural network (3D CNN) and cellular automata (CA) techniques. In addition to the historical land cover maps, the model incorporated desertification indicators identified as important in the study, including geology, soil type, distance from waterways, elevation, population density, and Normalized Difference Vegetation Index (NDVI). Several accuracy metrics were used to evaluate the models, including overall accuracy (OA), average accuracy (AA), and the Kappa index (K). The simulated and actual land cover maps from 1998 and 2008 were used to evaluate the desertification prediction models. The 3D CNN model outperforms the typical 2D CNN for both the 2008 and 2018 images, according to the results. For the 2008 image, the 3D CNN model achieved 89.675 OA, 69.946 AA, and 0.781 K, while the 2018 image achieved 91.494 OA, 75.138 AA, and 0.770 K. The 2D CNN model performed a little worse than the 3D CNN model. The results of the change assessment showed that between 1998 and 2008, agricultural land was the dominant class (39%, 47.4%, respectively). The bare land, however, was the most dominant class in 2018, accounting for 46.6% of the total, compared to 26.2% for agricultural land. The spatial distribution characteristics of desertification in the Al-Khidhir, in the year 1998, were prevalent in the area’s south (25.9%). In the following 10 years, desertification has spread to the surrounding territories. In the year 2008, desertification increased in the north of the study area (50.8%). Unless the local administration of Al-Khidhir district establishes desertification control strategies, this study suggests that the extent of bare land could expand in 2028 (54.1%). |
| first_indexed | 2024-03-06T11:14:07Z |
| format | Article |
| id | upm.eprints-100896 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T11:14:07Z |
| publishDate | 2022 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | upm.eprints-1008962023-08-15T08:42:34Z http://psasir.upm.edu.my/id/eprint/100896/ Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq Aldabbagh, Yasir Abdulameer Nayyef Mohd Shafri, Helmi Zulhaidi Mansor, Shattri Ismail, Mohd Hasmadi Desertification is a major environmental issue all over the world, and Al-Khidhir district, Al-Muthanna, in the south of Iraq is no exception. In mapping, assessing, and predicting desertification, remote sensing and geospatial solutions (spatial analysis, machine learning) are crucial. During 1998–2018, this study employed satellite images from Landsat TM, ETM + , and OLI to map and predict desertification in the Al-Khidhir district. The year 2028 was chosen as the target date. Prediction models were constructed using a 3D convolutional neural network (3D CNN) and cellular automata (CA) techniques. In addition to the historical land cover maps, the model incorporated desertification indicators identified as important in the study, including geology, soil type, distance from waterways, elevation, population density, and Normalized Difference Vegetation Index (NDVI). Several accuracy metrics were used to evaluate the models, including overall accuracy (OA), average accuracy (AA), and the Kappa index (K). The simulated and actual land cover maps from 1998 and 2008 were used to evaluate the desertification prediction models. The 3D CNN model outperforms the typical 2D CNN for both the 2008 and 2018 images, according to the results. For the 2008 image, the 3D CNN model achieved 89.675 OA, 69.946 AA, and 0.781 K, while the 2018 image achieved 91.494 OA, 75.138 AA, and 0.770 K. The 2D CNN model performed a little worse than the 3D CNN model. The results of the change assessment showed that between 1998 and 2008, agricultural land was the dominant class (39%, 47.4%, respectively). The bare land, however, was the most dominant class in 2018, accounting for 46.6% of the total, compared to 26.2% for agricultural land. The spatial distribution characteristics of desertification in the Al-Khidhir, in the year 1998, were prevalent in the area’s south (25.9%). In the following 10 years, desertification has spread to the surrounding territories. In the year 2008, desertification increased in the north of the study area (50.8%). Unless the local administration of Al-Khidhir district establishes desertification control strategies, this study suggests that the extent of bare land could expand in 2028 (54.1%). Springer Nature 2022-08-31 Article PeerReviewed Aldabbagh, Yasir Abdulameer Nayyef and Mohd Shafri, Helmi Zulhaidi and Mansor, Shattri and Ismail, Mohd Hasmadi (2022) Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq. Environmental Monitoring and Assessment, 194. art. no. 715. pp. 1-20. ISSN 0167-6369; ESSN: 1573-2959 https://link.springer.com/article/10.1007/s10661-022-10379-z 10.1007/s10661-022-10379-z |
| spellingShingle | Aldabbagh, Yasir Abdulameer Nayyef Mohd Shafri, Helmi Zulhaidi Mansor, Shattri Ismail, Mohd Hasmadi Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title | Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title_full | Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title_fullStr | Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title_full_unstemmed | Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title_short | Desertification prediction with an integrated 3D convolutional neural network and cellular automata in Al-Muthanna, Iraq |
| title_sort | desertification prediction with an integrated 3d convolutional neural network and cellular automata in al muthanna iraq |
| work_keys_str_mv | AT aldabbaghyasirabdulameernayyef desertificationpredictionwithanintegrated3dconvolutionalneuralnetworkandcellularautomatainalmuthannairaq AT mohdshafrihelmizulhaidi desertificationpredictionwithanintegrated3dconvolutionalneuralnetworkandcellularautomatainalmuthannairaq AT mansorshattri desertificationpredictionwithanintegrated3dconvolutionalneuralnetworkandcellularautomatainalmuthannairaq AT ismailmohdhasmadi desertificationpredictionwithanintegrated3dconvolutionalneuralnetworkandcellularautomatainalmuthannairaq |