An improved adaptive neuro-fuzzy inference system for hydrological drought prediction in Algeria
(2023) In Physics and Chemistry of the Earth 131.- Abstract
Drought has negative impacts on water resources, food security, soil degradation, desertification and agricultural productivity. The meteorological and hydrological droughts prediction using standardized precipitation/runoff indices (SPI/SRI) is crucial for effective water resource management. In this study, we suggest ANFISWCA, an adaptive neuro-fuzzy inference system (ANFIS) optimized by the water cycle algorithm (WCA), for hydrological drought forecasting in semi-arid regions of Algeria. The new model was used to predict SRI at 3-, 6-, 9-, and 12-month accumulation periods in the Wadi Mina basin, Algeria. The results of the model were assessed using four criteria; determination coefficient, mean absolute error, variance accounted... (More)
Drought has negative impacts on water resources, food security, soil degradation, desertification and agricultural productivity. The meteorological and hydrological droughts prediction using standardized precipitation/runoff indices (SPI/SRI) is crucial for effective water resource management. In this study, we suggest ANFISWCA, an adaptive neuro-fuzzy inference system (ANFIS) optimized by the water cycle algorithm (WCA), for hydrological drought forecasting in semi-arid regions of Algeria. The new model was used to predict SRI at 3-, 6-, 9-, and 12-month accumulation periods in the Wadi Mina basin, Algeria. The results of the model were assessed using four criteria; determination coefficient, mean absolute error, variance accounted for, and root mean square error, and compared with those of the standalone ANFIS model. The findings suggested that throughout the testing phase at all the sub-basins, the proposed hybrid model outperformed the conventional model for estimating drought. This study indicated that the WCA algorithm enhanced the ANFIS model's drought forecasting accuracy. The proposed model could be employed for forecasting drought at multi-timescales, deciding on remedial strategies for dealing with drought at study stations, and aiding in sustainable water resources management.
(Less)
- author
- Achite, Mohammed ; Gul, Enes ; Elshaboury, Nehal ; Jehanzaib, Muhammad ; Mohammadi, Babak LU and Danandeh Mehr, Ali
- organization
- publishing date
- 2023-10
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- ANFIS, Hybrid model, Hydrological drought, Water cycle algorithm
- in
- Physics and Chemistry of the Earth
- volume
- 131
- article number
- 103451
- publisher
- Elsevier
- external identifiers
-
- scopus:85166481383
- ISSN
- 1474-7065
- DOI
- 10.1016/j.pce.2023.103451
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2023 The Author(s)
- id
- 38daa750-68ee-48e5-adae-c9016ee2355f
- date added to LUP
- 2023-10-25 15:34:20
- date last changed
- 2024-01-24 11:00:59
@article{38daa750-68ee-48e5-adae-c9016ee2355f, abstract = {{<p>Drought has negative impacts on water resources, food security, soil degradation, desertification and agricultural productivity. The meteorological and hydrological droughts prediction using standardized precipitation/runoff indices (SPI/SRI) is crucial for effective water resource management. In this study, we suggest ANFISWCA, an adaptive neuro-fuzzy inference system (ANFIS) optimized by the water cycle algorithm (WCA), for hydrological drought forecasting in semi-arid regions of Algeria. The new model was used to predict SRI at 3-, 6-, 9-, and 12-month accumulation periods in the Wadi Mina basin, Algeria. The results of the model were assessed using four criteria; determination coefficient, mean absolute error, variance accounted for, and root mean square error, and compared with those of the standalone ANFIS model. The findings suggested that throughout the testing phase at all the sub-basins, the proposed hybrid model outperformed the conventional model for estimating drought. This study indicated that the WCA algorithm enhanced the ANFIS model's drought forecasting accuracy. The proposed model could be employed for forecasting drought at multi-timescales, deciding on remedial strategies for dealing with drought at study stations, and aiding in sustainable water resources management.</p>}}, author = {{Achite, Mohammed and Gul, Enes and Elshaboury, Nehal and Jehanzaib, Muhammad and Mohammadi, Babak and Danandeh Mehr, Ali}}, issn = {{1474-7065}}, keywords = {{ANFIS; Hybrid model; Hydrological drought; Water cycle algorithm}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Physics and Chemistry of the Earth}}, title = {{An improved adaptive neuro-fuzzy inference system for hydrological drought prediction in Algeria}}, url = {{http://dx.doi.org/10.1016/j.pce.2023.103451}}, doi = {{10.1016/j.pce.2023.103451}}, volume = {{131}}, year = {{2023}}, }