Table 1.
Hyperparameters of the LSTM Model.
Fig 1.
Adaptive dynamic algorithm for Australia rainfall.
Fig 2.
The AD-PSO-Guided WOA LSTM framework.
Table 2.
Metrics for evaluating the performance of the proposed model.
Table 3.
Performance of the bAD-PSO-Guided WOA algorithm compared with another algorithm.
Table 4.
Prediction results of individual models.
Table 5.
Performance of the proposed AD-PSO-Guided WOA-LSTM algorithm compared with another algorithm.
Table 6.
Descriptive analysis of the outcomes by the optimized LSTM using several optimization algorithms.
Table 7.
The outcomes of the ANOVA results for the proposed AD-PSO-Guided WOA-LSTM algorithm for rainfall prediction.
Fig 3.
The AD-PSO-Guided WOA LSTM algorithm RMSE is based on the objective function compared to different algorithms.
Fig 4.
Analysis plots of the obtained results using the proposed AD-PSO-Guided WOA LSTM algorithm.
Table 8.
Hyperparameter settings for the optimization algorithms.
Table 9.
Total computational cost of the proposed AD-PSO-Guided WOA-LSTM algorithm compared with another algorithm.