Optimalisasi Prediksi Parameter Lingkungan Menggunakan Model LSTM Multivariat dan Univariat
DOI:
https://doi.org/10.47065/bulletincsr.v5i6.813Keywords:
LSTM; Multivariate; Univariate; PredictionAbstract
Environmental parameter prediction plays an essential role in supporting weather monitoring and data-driven decision-making, particularly in urban areas. However, prediction accuracy is often limited by a model’s ability to capture the interrelationships among environmental parameters. This study aims to analyze and compare the performance of two Long Short-Term Memory (LSTM) approaches Multivariate and Univariate in predicting air temperature as the dependent variable. In the Multivariate model, temperature prediction is influenced by other independent variables such as humidity, pressure, and altitude, whereas in the Univariate model, temperature prediction is based solely on its historical data. The model architecture consists of three main layers an input layer, two hidden layers, and an output layer. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). The experimental results show that the multivariate LSTM model produces lower error values for temperature and pressure parameters, while the univariate LSTM model performs better for humidity and altitude. Therefore, the multivariate model is more suitable when the interrelationships among environmental parameters significantly influence prediction outcomes.
Downloads
References
N. W. Shen, A. A. Bakar, and H. Mohamad, “Univariate and Multivariate Long Short Term Memory (LSTM) Model to Predict Covid-19 Cases in Malaysia Using Integrated Meteorological Data,” Malaysian J. Fundam. Appl. Sci., vol. 19, no. 4, pp. 653–667, 2023, doi: 10.11113/mjfas.v19n4.2814.
V. Domala and T. W. Kim, “A Univariate and multivariate machine learning approach for prediction of significant wave height.,” Ocean. Conf. Rec., vol. 2022-Octob, no. December, 2022, doi: 10.1109/OCEANS47191.2022.9977028.
T. Limouniac, R. Yaagoubib, K. Bouzianec, K. Guissia, and E. H. Baalia, “Univariate and Multivariate LSTM Models for One Step and Multistep PV Power Forecasting | Limouni | International Journal of Renewable Energy Development,” Int. J. Renew. Energy Dev., vol. 11, no. 3, pp. 815-828., 2022, [Online]. Available: https://ijred.cbiore.id/index.php/ijred/article/view/43953
R. A. B. Khalil and A. A. B. U. Bakar, “A Comparative Study of Deep Learning Algorithms in Univariate and Multivariate Forecasting of the Malaysian Stock Market,” Sains Malaysiana, vol. 52, no. 3, pp. 993–1009, 2023, doi: 10.17576/jsm-2023-5203-22.
N. Izzany, M. Masjkur, and A. Rizki, “Application of Univariate and Multivariate Long Short Term Memory for World Crude Palm Oil Price Prediction,” Indones. J. Stat. Its Appl., vol. 9, no. 1, pp. 10–20, 2025, doi: 10.29244/ijsa.v9i1p10-20.
P. Sugiartawan and S. Gusprio Santoso, “Multivariate Forecasting Curah Hujan Menggunakan Algoritma LSTM Di Kota Denpasar,” Semin. Nas. Corisindo, pp. 580–585, 2022.
M. J. Abbass, R. Lis, and W. Rebizant, “A Predictive Model Using Long Short-Time Memory (LSTM) Technique for Power System Voltage Stability,” Appl. Sci., vol. 14, no. 16, 2024, doi: 10.3390/app14167279.
A. Mahmoudi, “Investigating LSTM-based time series prediction using dynamic systems measures,” Evol. Syst., vol. 16, no. 2, pp. 1–18, 2025, doi: 10.1007/s12530-025-09703-y.
X. Song, L. Deng, H. Wang, Y. Zhang, and Y. He, “Deep learning-based time series forecasting,” 2025.
A. A. L. Rahmah, “Analisis Model Multivariate Long Short-Term Memory Untuk Prakiraan Kualitas Udara Dki Jakarta Berdasarkan Data Tahun 2010-2022,” Repository.Uinjkt.Ac.Id, pp. 1–87, 2024
I. F. Efaranti, “Peramalan Data Kualitas Udara Menggunakan Multivariat LSTM di Wilayah Kota Surabaya,” 2024.
A. Kharel, Z. Zarean, and D. Kaur, “Long Short-Term Memory (LSTM) Based Deep Learning Models for Predicting Univariate Time Series Data,” Int. J. Mach. Learn., vol. 14, no. 1, 2024, doi: 10.18178/ijml.2024.14.1.1154.
T. A. Prasetyo et al., “Evaluating the efficacy of univariate LSTM approach for COVID-19 data prediction in Indonesia,” Indones. J. Electr. Eng. Comput. Sci., vol. 34, no. 2, pp. 1353–1366, 2024, doi: 10.11591/ijeecs.v34.i2.pp1353-1366.
O. Assaf, G. Di Fatta, and G. Nicosia, “Multivariate LSTM for Stock Market Volatility Prediction,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 13164 LNCS, no. February, pp. 531–544, 2022, doi: 10.1007/978-3-030-95470-3_40.
R. Tanjung, A. Listiani, and F. Lestari, “Prediksi Multivariate Time Series Parameter Cuaca Menggunakan Long Short - Term Memory (LSTM),” Pros. Semin. Nas. Sains Data, vol. 4, no. 1, pp. 445–456, 2024, doi: 10.33005/senada.v4i1.253.
Furizal, A. Ritonga, A. Ma’arif, and I. Suwarno, “Stock Price Forecasting with Multivariate Time Series Long Short-Term Memory: A Deep Learning Approach,” J. Robot. Control, vol. 5, no. 5, pp. 1322–1335, 2024, doi: 10.18196/jrc.v5i5.22460.
S. Salehi, M. Kavgic, H. Bonakdari, and L. Begnoche, “Comparative study of univariate and multivariate strategy for short-term forecasting of heat demand density: Exploring single and hybrid deep learning models,” Energy AI, vol. 16, no. January, p. 100343, 2024, doi: 10.1016/j.egyai.2024.100343.
G. Davies, “Evaluating the effectiveness of predicting covariates in LSTM Networks for Time Series Forecasting,” ArXiv, 2024, [Online]. Available: http://arxiv.org/abs/2404.18553
A. K. Salem and A. A. Abokifa, “A Multivariate LSTM Model for Short-Term Water Demand Forecasting †,” Eng. Proc., vol. 69, no. 1, pp. 1–4, 2024, doi: 10.3390/engproc2024069167.
E. Yang, H. Zhang, X. Guo, Z. Zang, Z. Liu, and Y. Liu, “A multivariate multi-step LSTM forecasting model for tuberculosis incidence with model explanation in Liaoning Province, China,” BMC Infect. Dis., vol. 22, no. 1, pp. 1–13, 2022, doi: 10.1186/s12879-022-07462-8.
A. W. Saputra, A. P. Wibawa, U. Pujianto, A. B. Putra Utama, and A. Nafalski, “LSTM-based Multivariate Time-Series Analysis: A Case of Journal Visitors Forecasting,” Ilk. J. Ilm., vol. 14, no. 1, pp. 57–62, 2022, doi: 10.33096/ilkom.v14i1.1106.57-62.
M. A. A. Bakar, N. M. Mohd Ariff, M. S. Mohd Nadzir, O. L. Wen, and F. N. A. Suris, “Prediction of Multivariate Air Quality Time Series Data using Long Short-Term Memory Network,” Malaysian J. Fundam. Appl. Sci., vol. 18, no. 1, pp. 52–59, 2022, doi: 10.11113/MJFAS.V18N1.2393.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimalisasi Prediksi Parameter Lingkungan Menggunakan Model LSTM Multivariat dan Univariat
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 Chandra Nilasari Yunantara, April Firman Daru
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
