Enhanced Rainfall Forecasting Through Deep Learning Optimization Using Long Short-Term Memory Networks

Ade May Luky Harefa; Robin Antoni; Andri Ismail Sitepu; Yohannes France Limbong; Muhammad Syahputra Novelan

doi:10.31004/riggs.v4i2.487

Authors

Ade May Luky Harefa Universitas Pembangunan Panca Budi
Robin Antoni Universitas Pembangunan Panca Budi
Andri Ismail Sitepu Universitas Pembangunan Panca Budi
Yohannes France Limbong Universitas Pembangunan Panca Budi
Muhammad Syahputra Novelan Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.31004/riggs.v4i2.487

Keywords:

Rainfall, Deep Learning, LSTM, Prediction, MSE

Abstract

This study aims to develop a rainfall prediction system using Deep Learning with the Long Short-Term Memory (LSTM) method to improve prediction accuracy and efficiency. The model was built using rainfall data from Gunung Sitoli, covering the period from October 16 to December 14, 2004. The dataset was divided into 90% for training and 10% for testing. The LSTM model was configured with 1 hidden layer and trained for 50 epochs. To evaluate its performance, the Mean Squared Error (MSE) metric was applied. The model achieved an MSE of 0.03 on the test data, indicating a low prediction error and good accuracy. This result shows that LSTM is capable of learning rainfall patterns over time and producing reliable forecasts. Furthermore, the model was integrated into a system to streamline the forecasting and evaluation process. This integration provides an efficient alternative to manual calculations, offering users faster and more accessible predictions. The implementation of this system is especially beneficial for early warning and decision-making processes in regions like Gunung Sitoli, where rainfall patterns can significantly impact on daily activities and disaster preparedness.

Downloads

Download data is not yet available.

References

A. Wahyudi, M. B. T. Assyamiri, W. Al Aluf, M. R. Fadhillah, S. Yolanda, and M. I. Anshori, “Dampak transformasi era digital terhadap manajemen sumber daya manusia,” J. Bintang Manaj., vol. 1, no. 4, pp. 99–111, 2023.

L. Ahmad Gunawan, Digital Leadership for Industry 5.0: Integrasi Manusia, Teknologi dan Industri. Takaza Innovatix Labs, 2025.

M. Hasan, S. Kom, M. Kom, S. Serwin, and M. Kom, Penerapan Sistem Informasi Berbasis AI untuk Analisis Data Real-time. Takaza Innovatix Labs, 2024.

S. Rifky et al., Artificial Intelligence: Teori dan Penerapan AI di Berbagai Bidang. PT. Sonpedia Publishing Indonesia, 2024.

M. S. Novelan, S. Efendi, P. Sihombing, and H. Mawengkang, “VEHICLE ROUTING PROBLEM OPTIMIZATION WITH MACHINE LEARNING IN IMBALANCED CLASSIFICATION VEHICLE ROUTE DATA.,” Eastern-European J. Enterp. Technol., vol. 125, no. 3, 2023.

D. Sawitri, “PERAN DEEP LEARNING DAN BIG DATA DALAM MENDEKTEKSI MASALAH KEUANGAN,” Djtechno J. Teknol. Inf., vol. 6, no. 1, pp. 193–207, 2025.

H. Alizadegan, B. Rashidi Malki, A. Radmehr, H. Karimi, and M. A. Ilani, “Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction,” Energy Explor. Exploit., vol. 43, no. 1, pp. 281–301, 2025.

Y. A. Susetyo, H. A. Parhusip, S. Trihandaru, and B. Susanto, “LSTM-IOT (LSTM-based IoT) untuk Mengatasi Kehilangan Data Akibat Kegagalan Koneksi,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 1, pp. 175–186, 2025.

V. Shatravin, D. Shashev, and S. Shidlovskiy, “Sigmoid activation implementation for neural networks hardware accelerators based on reconfigurable computing environments for low-power intelligent systems,” Appl. Sci., vol. 12, no. 10, p. 5216, 2022.

A. Sepas-Moghaddam, A. Etemad, F. Pereira, and P. L. Correia, “Long short-term memory with gate and state level fusion for light field-based face recognition,” IEEE Trans. Inf. Forensics Secur., vol. 16, pp. 1365–1379, 2020.