Performance Analysis of LSTM Vs GRU in Predicting Weather Patterns For Climate Change Models
E Pavithra, M Mayuri Reddy, Suresh Bhukya
This study presents a comparative analysis of Long Short-Term Memory (LSTM) and Gated Recurrent
Unit (GRU) networks in predicting weather patterns, a critical task for climate change models. Utilizing
a comprehensive dataset of historical weather data, we trained both models to forecast key weather
parameters such as temperature, humidity, and wind speed. The results demonstrate that the LSTM model
consistently outperforms the GRU model across all evaluated metrics, including Root Mean Squared
Error (RMSE), Mean Absolute Error (MAE), and R² score. The LSTM model’s superior ability to capture
long-term dependencies in the data suggests it may be better suited for complex time-series forecasting
tasks in climate modeling. These findings provide valuable insights for researchers and practitioners in
selecting appropriate deep learning models for accurate and reliable weather prediction.
