Journal
IEEE ACCESS
Volume 8, Issue -, Pages 15210-15222Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2964584
Keywords
Hydrological drought; precipitation; machine learning; hydrology; SPI; PSO; SSA; BBO; GOA
Categories
Funding
- European Union [EFOP-3.6.1-16-2016-00010]
Ask authors/readers for more resources
Hydrological drought forecasting plays a substantial role in water resources management. Hydrological drought highly affects the water allocation and hydropower generation. In this research, short term hydrological drought forecasted based on the hybridized of novel nature-inspired optimization algorithms and Artificial Neural Networks (ANN). For this purpose, the Standardized Hydrological Drought Index (SHDI) and the Standardized Precipitation Index (SPI) were calculated in one, three, and six aggregated months. Then, three states where proposed for SHDI forecasting, and 36 input-output combinations were extracted based on the cross-correlation analysis. In the next step, newly proposed optimization algorithms, including Grasshopper Optimization Algorithm (GOA), Salp Swarm algorithm (SSA), Biogeography-based optimization (BBO), and Particle Swarm Optimization (PSO) hybridized with the ANN were utilized for SHDI forecasting and the results compared to the conventional ANN. Results indicated that the hybridized model outperformed compared to the conventional ANN. PSO performed better than the other optimization algorithms. The best models forecasted SHDI1 with R2 & x003D; 0.68 and RMSE & x003D; 0.58, SHDI3 with R-2 & x003D; 0.81 and RMSE & x003D; 0.45 and SHDI6 with R-2 & x003D; 0.82 and RMSE & x003D; 0.40.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available