Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco)
Drought forecasting has implications for managing water and irrigation. Currently, with improved technology like artificial intelligence, forecasting can be more accurate. In this research, we chose standardized potential evapotranspiration index (SPEI) to characterize drought pattern. To achieve th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/19/e3sconf_gire3d2024_04015.pdf |
| _version_ | 1797315639371628544 |
|---|---|
| author | Acharki Siham Arjdal Youssef El Mansouri Bouabid |
| author_facet | Acharki Siham Arjdal Youssef El Mansouri Bouabid |
| author_sort | Acharki Siham |
| collection | DOAJ |
| description | Drought forecasting has implications for managing water and irrigation. Currently, with improved technology like artificial intelligence, forecasting can be more accurate. In this research, we chose standardized potential evapotranspiration index (SPEI) to characterize drought pattern. To achieve this, the data used was acquired from five meteorological stations in an irrigated Moroccan perimeter from 1976 to 2015. Besides, we predict SPEI at two scales (SPEI-3 and SPEI-6) with two inputs combination by exploring the capabilities of M5 pruned (M5P) and Light Gradient Boosting Machine (LightGBM), along with their hybrid model (LightGBM-M5P). To assess their effectiveness, we employed three statistical metrics (R2, MAE and RMSE). The findings indicated that using a larger time scale for analysis enhances the ability to forecast SPEI values more accurately. Moreover, the forecasting analysis revealed that M5P model demonstrated superior performance compared to the other studied models. |
| first_indexed | 2024-03-08T03:06:42Z |
| format | Article |
| id | doaj.art-3a156a385d4d482994dd05caf05d7c7c |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-03-08T03:06:42Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-3a156a385d4d482994dd05caf05d7c7c2024-02-13T08:28:20ZengEDP SciencesE3S Web of Conferences2267-12422024-01-014890401510.1051/e3sconf/202448904015e3sconf_gire3d2024_04015Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco)Acharki Siham0Arjdal Youssef1El Mansouri Bouabid2Department of Earth Sciences, Faculty of Sciences and Technologies of Tangier (FSTT), Abdelmalek Essaadi UniversityNatural Resources & Sustainable Development Laboratory, Earth Sciences Department, Faculty of Sciences, Ibn Tofail UniversityNatural Resources & Sustainable Development Laboratory, Earth Sciences Department, Faculty of Sciences, Ibn Tofail UniversityDrought forecasting has implications for managing water and irrigation. Currently, with improved technology like artificial intelligence, forecasting can be more accurate. In this research, we chose standardized potential evapotranspiration index (SPEI) to characterize drought pattern. To achieve this, the data used was acquired from five meteorological stations in an irrigated Moroccan perimeter from 1976 to 2015. Besides, we predict SPEI at two scales (SPEI-3 and SPEI-6) with two inputs combination by exploring the capabilities of M5 pruned (M5P) and Light Gradient Boosting Machine (LightGBM), along with their hybrid model (LightGBM-M5P). To assess their effectiveness, we employed three statistical metrics (R2, MAE and RMSE). The findings indicated that using a larger time scale for analysis enhances the ability to forecast SPEI values more accurately. Moreover, the forecasting analysis revealed that M5P model demonstrated superior performance compared to the other studied models.https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/19/e3sconf_gire3d2024_04015.pdf |
| spellingShingle | Acharki Siham Arjdal Youssef El Mansouri Bouabid Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) E3S Web of Conferences |
| title | Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) |
| title_full | Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) |
| title_fullStr | Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) |
| title_full_unstemmed | Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) |
| title_short | Meteorological drought forecasting via soft computing models in Gharb perimeter (Northwest Morocco) |
| title_sort | meteorological drought forecasting via soft computing models in gharb perimeter northwest morocco |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/19/e3sconf_gire3d2024_04015.pdf |
| work_keys_str_mv | AT acharkisiham meteorologicaldroughtforecastingviasoftcomputingmodelsingharbperimeternorthwestmorocco AT arjdalyoussef meteorologicaldroughtforecastingviasoftcomputingmodelsingharbperimeternorthwestmorocco AT elmansouribouabid meteorologicaldroughtforecastingviasoftcomputingmodelsingharbperimeternorthwestmorocco |