A comprehensive comparison of recent developed meta-heuristic algorithms for streamflow time series forecasting problem
- Code https://github.com/aiir-team/physics_MLP-monthly-streamflow-code
- Paper: https://doi.org/10.1016/j.asoc.2021.107282
- MLP (Streamflow forecasting using artificial neural network and support vector machine models)
- RNN (https://doi.org/10.1007/s11600-019-00330-1)
- GA-MLP (Predicting monsoon floods in rivers embedding wavelet transform, genetic algorithm and neural network)
- DE-MLP (Differential evolution algorithms applied to neural network training suffer from stagnation)
- FPA-MLP (Not found yet, you can check again)
- PSO-MLP (Hybrid particle swarm and neural network approach for streamflow forecasting)
- WOA-MLP (Annual Rainfall Forecasting Using Hybrid Artificial Intelligence Model: Integration of Multilayer Perceptron with Whale Optimization Algorithm)
- GWO-MLP (Improving artificial intelligence models accuracy for monthly streamflow forecasting using grey Wolf optimization (GWO) algorithm)
- SpaSA-MLP (No one - A novel swarm intelligence optimization approach: sparrow search algorithm)
- WDO-MLP (Wind Driven Optimization - No one use it yet, but this algorithm is old - 2010)
- MVO-MLP (Multi-Verse Optimization - No one use it yet, 2016)
- EO-MLP (Equilibrium optimizer: A novel optimization algorithm - No one use it yet, 2019)
- NRO-MLP (Nuclear Reaction Optimization: A novel and powerful physics-based algorithm for global optimization - No one use it yet, 2019)
- HGSO-MLP (Henry gas solubility optimization: A novel physics-based algorithm, 2019)
- Run MLP model by: mlp.py
- Run Rnn-based model (RNN, LSTM) by: script_traditional_rrn_based.py (multiprocessing)
- All hybrid-MLP model by: script_hybrid_mlp.py (multiprocessing also)
- Get the results table mean, std, cv by: get_table_results.py
- Results saved in folder: history/results/ based on daily or weekly datatype
- Convergence errors of models in docs/results_of_paper/final_results_from_Thieu.xlsx
- Stability figures in the paper in docs/results_of_paper/images/...