Al-Biruni Based Optimization of Rainfall Forecasting in Ethiopia

Rainfall plays a significant role in managing the water level reservoir. The unpredictable amount of rainfall due to climate change can cause either overflow or dry Many individuals, especially those agricultural sector, rely on rain forecasts. Forecasting is challenging because changing nature weather. area Jimma southwest Oromia, Ethiopia subject this research, which aims develop forecasting model. To estimate Jimma’s daily rainfall, we propose novel approach based optimizing parameters long short-term memory (LSTM) using Al-Biruni earth radius (BER) optimization algorithm for boosting accuracy. Nash–Sutcliffe model efficiency (NSE), mean square error (MSE), root MSE (RMSE), absolute (MAE), and R2 were all used conducted experiments assess proposed approach, with final scores (0.61), (430.81), (19.12), (11.09), respectively. Moreover, compared current machine-learning regression models; such as non-optimized LSTM, bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), convolutional (ConvLSTM). It was found that achieved lowest RMSE (19.12). In addition, experimental results show has value outperforming other models, confirms superiority approach. On hand, statistical analysis performed measure significance stability recorded proved expected performance.