<![CDATA[Hydro meteorological disasters are common in Indonesia. Rainfall predictions can help mitigate the impact of these disasters. This research aims to compare the accuracy of monthly rainfall prediction models using Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) methods. The input data consists of monthly rainfall records from four locations: Sampali, Kualanamu, Belawan, and Tuntungan, located around Medan, North Sumatra. The dataset spans from 2000 to 2020, with training data from 2000 to 2018 and test data from 2019 to 2020. The accuracy assessment reveals that Belawan has the largest RMSE values for both models, measuring 27.68 mm for LSTM and 28.36 mm for SARIMA. Belawan records the highest MAE values, with LSTM and SARIMA yielding 5.65 mm and 5.79 mm, respectively. SARIMA models effectively capture general trends and seasonality in linear time series data with clear patterns but struggle with extreme changes or sharp fluctuations due to their reliance on linear relationships. In contrast, LSTMs are effective at modeling complex, non-linear relationships, making them suitable for capturing general trends, seasonal patterns, and more complicated variations in the data. Understanding the characteristics of the data is crucial before applying SARIMA or LSTM models.]]>
Copyrights © 2024
