Standalone and Hybrid Deep Learning Approaches for Groundwater Level Projection in a Drought-Affected Region of Bangladesh

Accurate forecasting of groundwater level (GWL) fluctuations in drought-prone and data-limited regions remains a major challenge for sustainable groundwater management. The complexity of nonlinear and dynamic groundwater systems, influenced by spatiotemporal variability and limited observational data, further complicates the development of reliable predictive models. Groundwater is a critical resource for irrigation and domestic use in drought-prone northwestern Bangladesh, requiring accurate forecasting of GWL dynamics for sustainable management. To address this challenge, the present study evaluates seven deep learning (DL) approaches: GRU, LSTM, hybrid LSTM–GRU, and their Genetic Algorithm (GA)- and Particle Swarm Optimization (PSO)-variants, using time-series data from nine observation wells. The developed models were benchmarked against the widely used univariate time-series forecasting model, ARIMA. Model performance varied spatially. The GA-LSTM model performed best at Bagha–Arani (R = 0.879, IOA = 0.906, NRMSE = 0.149), while the standalone LSTM achieved superior results at Bagmara–Auchpara (R = 0.940, IOA = 0.958, NRMSE = 0.155). All DL models outperformed the benchmark ARIMA model across all locations. Overall, the best models achieved R = 0.724–0.940, IOA = 0.707–0.958, NRMSE = 0.149–0.285, and MAD = 0.369–1.369 m, indicating strong predictive skill. Optimization (GA, PSO) improved accuracy, particularly for GRU-based models, though LSTM remained competitive in several sites. Hybrid and optimized models required higher computational cost due to iterative tuning but often yielded improved accuracy. A CRITIC–EDAS multi-criteria decision-making framework, based on six statistical metrics, identified no universally superior model; instead, optimal choices varied by location. Selected models successfully forecasted future GWL trends, capturing temporal variability. The integrated modelling–ranking framework provides a robust, scalable approach for groundwater management in data-limited, drought-affected regions.