<![CDATA[Rainfall is one of the important factors in the agricultural sector and water resource management especially in Lamongan Regency, which has a seasonal rainfall pattern. Variability and uncertainty of rainfall can affect agricultural activities as well as water availability for irrigation needs and water resource management. As an effort to minimise crop failure, an accurate prediction method is needed to support future planning. This study aims to predict rainfall using Backpropagation Neural Network and Long Short-Term Memory (LSTM) methods, as well as to compare the performance of both methods to determine the most optimal method in rainfall prediction to support planting time planning and water management. The data used are historical rainfall data, particularly from areas known as rice production centres in Lamongan Regency. The data underwent preprocessing stages, including data cleaning, normalisation, and time series data formation. The models were trained using three data splitting scenarios, namely 70:30, 80:20, and 90:10, and were then evaluated using the Root Mean Square Error (RMSE). The best model was determined based on the smallest RMSE value and subsequently used to predict rainfall for the next year. The results show that the best model was obtained using the LSTM method, with RMSE values of 24.70 mm for Lamongan, 26.74 mm for Kembangbahu, 44.77 mm for Tikung, 33.12 mm for Sugio, and 33.67 mm for Sukodadi. Therefore, the LSTM method is considered more optimal than the Backpropagation method in predicting rainfall in Lamongan Regency. The effective rice planting period occurs from May to July, as rainfall during this period is relatively sufficient and stable to support crop growth. In addition, planting activities can be carried out two to three times in a year.]]>
