Implementasi Model LSTM, CNN+LSTM Hybrid, dan Transformer untuk Prediksi Cuaca Harian Berbasis Data Multivariat

Heptyana Sri Wulandari; RZ Abdul Aziz

doi:10.47065/bits.v7i2.7655

Heptyana Sri Wulandari Institut Informatika dan Bisnis Darmajaya, Bandar Lampung, Indonesia
RZ Abdul Aziz * Institut Informatika dan Bisnis Darmajaya, Bandar Lampung, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/bits.v7i2.7655

Keywords: Weather Prediction; Multivariate Meteorology; LSTM; CNN LSTM; Transformer; Deep Learning

Abstract

Global climate change and the increasing frequency of extreme weather events demand more accurate and adaptive weather prediction systems. This study aims to implement and compare three deep learning models, Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN)+LSTM Hybrid, and Transformer for predicting next-day weather events using daily multivariate meteorological data. The dataset was obtained from the Climatology Station Class IV Lampung and includes air temperature, rainfall, humidity, solar radiation, air pressure, wind direction, and wind speed, collected in CSV format from February 2000 to March 2025. The analysis results indicate that the CNN+LSTM Hybrid model achieved the best performance, with an RMSE of 1.158, MAE of 0.521, R² Score of 0.323, accuracy of 75%, and Macro F1 score of 0.75. The LSTM model demonstrated moderate performance, while the Transformer model yielded the lowest results among the three. These findings suggest that combining CNN's spatial feature extraction with LSTM's sequential processing enhances the prediction quality of short-term weather forecasts based on multivariate data. This study is expected to contribute to the development of AI-based weather forecasting systems in Indonesia, particularly for hydrometeorological disaster mitigation.

Downloads

Download data is not yet available.

References

B. R. Reddy, S. Anchuri, K. Santhi, P. Perugu, S. Depuru, and M. S. Kumar, “Enhancing Cloudburst Prediction System Using Bi-LSTM in Realtime: Machine Learning,” Commun. Appl. Nonlinear Anal., vol. 32, no. 1s, pp. 221–231, 2025, doi: 10.52783/cana.v32.2161.

S. Salma and A. Ashwitha, “Hybrid Cnn-Lstm Model: Rainfall Analysis and Prediction for Karnataka Region,” J. Theor. Appl. Inf. Technol., vol. 100, no. 22, pp. 6715–6716, 2022.

C. O. De Burgh-Day and T. Leeuwenburg, “Machine learning for numerical weather and climate modelling: A review,” Geosci. Model Dev., vol. 16, no. 22, pp. 6433–6477, 2023, doi: 10.5194/gmd-16-6433-2023.

H. S. Kim, K. M. Han, J. Yu, J. Kim, K. Kim, and H. Kim, “Development of a CNN+LSTM Hybrid Neural Network for Daily PM2.5 Prediction,” Atmosphere (Basel)., vol. 13, no. 12, 2022, doi: 10.3390/atmos13122124.

X. Kong et al., Deep learning for time series forecasting: a survey, no. 0123456789. Springer Berlin Heidelberg, 2025. doi: 10.1007/s13042-025-02560-w.

M. A. A. Al-qaness et al., “ResInformer: Residual Transformer-Based Artificial Time-Series Forecasting Model for PM2.5 Concentration in Three Major Chinese Cities,” Mathematics, vol. 11, no. 2, pp. 1–17, 2023, doi: 10.3390/math11020476.

O. S. Ojo and S. T. Ogunjo, “Machine learning models for prediction of rainfall over Nigeria,” Sci. African, vol. 16, p. e01246, 2022, doi: 10.1016/j.sciaf.2022.e01246.

W. Wang, T. Ji, and J. Sun, “Prediction of Sea Clutter Based on Recurrent Neural Network,” J. Phys. Conf. Ser., vol. 1735, no. 1, pp. 1–17, 2021, doi: 10.1088/1742-6596/1735/1/012008.

D. Pan, Y. Deng, and S. X. Yang, “Recent Advances in Remote Sensing and Artificial Intelligence for River Water Quality Forecasting: A Review,” Water, vol. 17, no. 1, pp. 23–25, 2025, doi: 10.3390/w17010023.

P. Shu, X. Duan, C. Shao, J. Liu, Y. Tian, and S. Li, “Precipitation Spatio-Temporal Forecasting in China via Deep Learning Approaches,” Water, vol. 17, no. 9, pp. 1–20, 2025, doi: 10.3390/w17091381.

O. Ogunfowora and H. Najjaran, A Transformer-Based Framework for Multi-Variate Time Series: A Remaining Useful Life Prediction Use Case, arXiv, vol. abs/2308.09884, Aug. 2023, doi:10.1109/TMC.2023.3327097.

Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, “A Comprehensive Survey on Graph Neural Networks,” IEEE Trans. Neural Networks Learn. Syst., vol. 32, no. 1, pp. 4–24, 2021, doi: 10.1109/TNNLS.2020.2978386.

S. Li et al., “Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting,” Adv. Neural Inf. Process. Syst., vol. 32, no. NeurIPS, 2019, doi: 10.48550/arXiv.1907.00235

S. Poornima and M. Pushpalatha, “Prediction of rainfall using intensified LSTM based recurrent Neural Network with Weighted Linear Units,” Atmosphere (Basel)., vol. 10, no. 11, 2019, doi: 10.3390/atmos10110668.

B. Ladjal et al., “Hybrid deep learning CNN-LSTM model for forecasting direct normal irradiance: a study on solar potential in Ghardaia, Algeria,” Sci. Rep., vol. 15, no. 1, pp. 1–16, 2025, doi: 10.1038/s41598-025-94239-z.

C. Cambier van Nooten et al., “Improving Precipitation Nowcasting for High-Intensity Events Using Deep Generative Models with Balanced Loss and Temperature Data: A Case Study in the Netherlands,” Artif. Intell. Earth Syst., vol. 2, no. 4, pp. 1–16, 2023, doi: 10.1175/aies-d-23-0017.1.

F. Karim, S. Majumdar, H. Darabi, and S. Chen, “LSTM Fully Convolutional Networks for Time Series Classification,” IEEE Access, vol. 6, pp. 1662–1669, 2017, doi: 10.1109/ACCESS.2017.2779939.

B. Nemade, R. Mishra, P. Jangid, S. Dubal, V. Bharadi, and V. Kaul, “Improving Rainfall Prediction Accuracy Using an LSTM-Driven Model Enhanced by M-PSO Optimization,” J. Electr. Syst., vol. 19, no. 3, pp. 164–180, 2023, doi: 10.52783/jes.664.

S. Tsokov, M. Lazarova, and A. Aleksieva-Petrova, “A Hybrid Spatiotemporal Deep Model Based on CNN and LSTM for Air Pollution Prediction,” Sustain., vol. 14, no. 9, 2022, doi: 10.3390/su14095104.

A. Anshuka, R. Chandra, A. J. V. Buzacott, D. Sanderson, and F. F. van Ogtrop, “Spatio temporal hydrological extreme forecasting framework using LSTM deep learning model,” Stoch. Environ. Res. Risk Assess., vol. 36, no. 10, pp. 3467–3485, 2022, doi: 10.1007/s00477-022-02204-3.

S. Khaki, L. Wang, and S. V. Archontoulis, “A CNN-RNN Framework for Crop Yield Prediction,” Front. Plant Sci., vol. 10, no. January, pp. 1–14, 2020, doi: 10.3389/fpls.2019.01750.

H. Zhou et al., “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. BT - Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, 2021, pp. 11106–11115, doi:10.1609/AAAI.V35I12.17325.

H. Kong, “Preprint not peer reviewed,” "The Lancet Psychiatry", vol. 1, no. 1, pp. 1–35, 2022, doi:10.2139/ssrn.3627326.

A. Casolaro, V. Capone, G. Iannuzzo, and F. Camastra, “Deep Learning for Time Series Forecasting: Advances and Open Problems,” Inf., vol. 14, no. 11, 2023, doi: 10.3390/info14110598.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Implementasi Model LSTM, CNN+LSTM Hybrid, dan Transformer untuk Prediksi Cuaca Harian Berbasis Data Multivariat