Related Experiment Videos
Groundwater level prediction using deep learning algorithms in a drought-prone area in Bangladesh
Md Mahmudul Hasan1, Abul Kashem2, Sourov Paul2
1Department of Geography and Environment, Jagannath University, Dhaka, 1100, Bangladesh.
Scientific Reports
|July 13, 2026
Summary
Accurate groundwater level forecasting in drought-prone Bangladesh is crucial. Bidirectional Long-Short-Term Memory (BiLSTM) deep learning models demonstrated superior accuracy for predicting groundwater levels, aiding sustainable water resource management.
Area of Science:
- Hydrology and Water Resource Management
- Artificial Intelligence in Environmental Science
- Climate Change Adaptation
Background:
- Groundwater is a vital resource for drinking water and agriculture, particularly in drought-prone regions.
- The northwestern region of Bangladesh faces water scarcity due to overuse and lack of accurate forecasting.
- Effective groundwater level (GWL) forecasting is essential for sustainable water resource management.
Purpose of the Study:
- To perform long-term time series forecasting of GWL in the drought-prone northwestern region of Bangladesh.
- To evaluate the performance of three deep learning (DL) algorithms: CNNs, GRU, and BiLSTM.
- To enhance GWL prediction accuracy to support water resource management decisions.
Main Methods:
- Utilized environmental data (temperature, rainfall, humidity) from 1981-2017 for two climate stations (Dinajpur, Bogura).
- Employed three deep learning models: Convolutional Neural Networks (CNNs), Gated Recurrent Unit (GRU), and Bidirectional Long-Short-Term Memory (BiLSTM).
- Evaluated model performance using RMSE, MSE, MAE, d, MAPE, and R² metrics, with a 70% training and 30% testing data split.
Main Results:
- GRU model performed best during training in Dinajpur; BiLSTM excelled in Bogura.
- Bidirectional Long-Short-Term Memory (BiLSTM) demonstrated the highest accuracy during the testing phase across both locations.
- BiLSTM achieved R² scores of 0.89 in Dinajpur and 0.93 in Bogura, indicating strong predictive power.
Conclusions:
- Deep learning models, particularly BiLSTM, show significant potential for accurate long-term GWL forecasting in drought-prone areas.
- The findings provide valuable insights for policymakers and authorities for informed groundwater management strategies.
- Improved GWL prediction accuracy supports sustainable water resource utilization in water-scarce regions like northwestern Bangladesh.
Related Concept Videos
02:41Responses to Drought and Flooding
Water plays a significant role in the life cycle of plants. However, insufficient or excess of water can be detrimental and pose a serious threat to plants.
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
01:29Application of Linearization and Approximation
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
01:19Design Example: Maintaining Level of an Embankment
Constructing a roadway embankment over uneven terrain requires precise leveling to ensure stability and proper drainage. Surveyors use a leveling instrument and staff to calculate ground elevations and determine the required fill material at each point along the embankment alignment.The process begins by positioning a leveling instrument near a benchmark with a known elevation. A backsight reading establishes the instrument height, which serves as a reference for subsequent measurements. A...