| dc.description.abstract |
Dams are essential to Myanmar's energy and water supply sectors because they
support irrigation, flood control, hydropower generation, and the transport of water for
homes and farms. To operate these reservoirs efficiently, an accurate forecasting of
water availability in the future is necessary. Accurate dam inflow forecast is also crucial
for reservoir operation, flood mitigation, hydropower generation and sustainable water
resource management.
This system aimed to implement an effective deep learning daily inflow
forecasting model at Lower Paunglaung Dam, Myanmar, using the catchment area
rainfall and relevant hydrological data. Daily time-series historical data from 1 January
2015 to October 15 2026 were used to develop and evaluate the models. Three types of
experiments were conducted to assess the contribution of Long Short-Term Memory
(LSTM) model and the performance of the proposed model. The first experiment used
conventional LSTM and Gated Recurrent Unit (GRU) models without rainfall
information. The second experiment was conducted to evaluate the effect of rainfall as
additional information for inflow prediction and the third experiment utilized the
proposed Rainfall-Guided Forget Gate LSTM (RGF-LSTM) model, where the rainfall
information is integrated directly into the forget gate of a standard LSTM cell. The
proposed system aims to predict the inflow of Lower Paunglaung Dam over a seven-
day forecasting period using historical inflow, rainfall, and other relevant hydrological
data. The predicted inflow will support water resource management for hydropower
generation by providing information for reservoir water management and electricity
generation planning. The system is designed to help dam operators make informed
decisions regarding water utilization for hydropower generation.
The models' performance was examined using Root Mean Square Error
(RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2). The
experimental results showed that the RGF-LSTM model obtained the best overall
performance for the daily dam inflow forecasting. |
en_US |