What question did this study set out to answer?

The central aim is to develop an efficient drought forecasting framework using optimized LSTM models in Kuwait.

March 6, 2026Open Access

Complexity-efficiency dynamics of metaheuristic-optimized recurrent neural network models for drought forecasting in hyper-arid Kuwait

Key Points

The central aim is to develop an efficient drought forecasting framework using optimized LSTM models in Kuwait.
Developed a drought-forecasting framework using LSTM with optimized hyperparameters.
Applied Bat Algorithm, Ant Colony Optimization, and Grey Wolf Optimization for tuning.
Compared performance against non-optimized LSTM and GRU models.
Evaluated models using RMSE, MAE, and R² metrics with long-term precipitation data.
Analyzed computational complexity through trainable parameters and training time.
Optimized LSTM models achieved accuracy comparable to baseline models at the PI24 scale.
Demonstrated that compact GRU architectures offered an efficient accuracy trade-off.
The PI24 scale showed improved stability and reduced error variability in drought forecasting.

Abstract

Kuwait, Arabian Peninsula, Western Asia This study develops an optimization-based drought-forecasting framework in which LSTM hyperparameters are optimized using Bat Algorithm (BA), Ant Colony Optimization (ACO), and Grey Wolf Optimization (GWO) to predict the Precipitation Index at 12- and 24-month scales (PI12 and PI24). To benchmark the computational efficiency of the proposed optimization framework, a non-optimized baseline LSTM and a Gated Recurrent Unit (GRU) model were also implemented under identical data partitions and training configurations. Unlike conventional models relying on probabilistically normalized indices, the framework utilizes the deterministic and distribution-free PI index, which is well-suited for zero-inflated, data-scarce conditions in hyper-arid regions. This study benchmarks multiple metaheuristically optimized LSTM configurations for drought forecasting in hyper-arid Kuwait using the Precipitation Index. Model training relied on long-term monthly precipitation data, with performance evaluated using RMSE, MAE, and R ², and computational complexity quantified by the number of trainable parameters. At the PI24 scale, optimized LSTMs achieve accuracy comparable to that of the baseline model, indicating the dominance of long-term precipitation accumulation in regional drought dynamics. Compact architectures, such as the GRU, further demonstrate the efficiency–accuracy trade-off relevant for operational drought monitoring. • Dual-scale PI12–PI24 drought forecasting with LSTM and GRU. • Bounded metaheuristic tuning of LSTM (ACO, BA, GWO). • Complexity–efficiency analysis using parameters and epoch time. • Compact models matched larger networks in accuracy. • PI24 demonstrated improved stability and reduced error variability.

Read Full Paperexternally

AI에게 질문

Bookmark

View Full Paper