Forecasting Patchouli (Pogostemon Cabin Benth) Production in North Kolaka Using ARIMA, LSTM and Hybrid ARIMA-LSTM
Abstract
Patchouli (Pogostemon cablin Benth.) is one of Indonesia’s most economically valuable essential oil commodities. This study forecasts patchouli production using ARIMA, LSTM, and a hybrid ARIMA–LSTM model, emphasizing the novelty of applying machine learning techniques to essential oil production forecasting, an understudied area. Weekly production data from ARS Atsiri North Kolaka (January 2022–July 2025, 187 records) were analyzed. ARIMA was applied to capture linear patterns, LSTM to model nonlinear dynamics, and the hybrid model to combine both characteristics. Model performance was evaluated using MSE, RMSE, and MAPE. The ARIMA (2,1,1) model performed best among the linear approaches, while LSTM with normalization, windowing, and 50 hidden units achieved the highest overall accuracy (MSE = 251.22, RMSE = 321.67, MAPE = 0.238%). The hybrid model did not outperform LSTM, likely due to the limited dataset and the dominance of nonlinear patterns, thus confirming LSTM as the most effective model.
Keywords
References
P. Astuti, K. Khairan, M. Marthoenis, and K. Hasballah, “Identification of Several Fractions of Patchouli Alcohol from Patchouli Oil (Pogostemon cablin Benth.) using Combination Method of Infrared Spectroscopy and Principal Component Analysis,” Sains Malaysiana, vol. 51, no. 10, pp. 3203–3214, 2022, doi: 10.17576/jsm-2022-5110-08.
H. N. Bhandari, B. Rimal, N. R. Pokhrel, R. Rimal, K. R. Dahal, and R. K. C. Khatri, “Predicting stock market index using LSTM,” Mach. Learn. with Appl., vol. 9, no. February, p. 100320, 2022, doi: 10.1016/j.mlwa.2022.100320.
D. Xu, Q. Zhang, Y. Ding, and D. Zhang, “Application of a hybrid ARIMA-LSTM model based on the SPEI for drought forecasting,” Environ. Sci. Pollut. Res., vol. 29, no. 3, pp. 4128–4144, 2022, doi: 10.1007/s11356-021-15325-z.
M. Taufik et al., “The Therapeutic Potential of Aceh Patchouli Oil (Pogostemon cablin Benth.) in Enhancing Full-Thickness Wound Healing in Mice,” Trop. J. Nat. Prod. Res., vol. 8, no. 1, pp. 5840–5844, 2024, doi: 10.26538/tjnpr/v8i1.19.
T. L. Mardiningsih and Rohimatun, “Evaluation of persistence, phytotoxicity, and biosafety of insecticide based on cajuput and patchouli oils,” IOP Conf. Ser. Earth Environ. Sci., vol. 1133, no. 1, 2023, doi: 10.1088/1755-1315/1133/1/012003.
M. Megawati, W. G. Abdullah, and W. O. Yusria, “Feasibility Analysis and Risk of Patchouli Farming Production in Aladadio Village Aere District East Kolaka Regency,” Int. J. Agric. Soc. Econ. Rural Dev., vol. 3, no. 2, pp. 65–73, 2023, doi: 10.37149/ijaserd.v3i2.1035.
A. K and D. C. K, “Demand Forecasting for Agro Tech Technical Textiles,” Int. J. Adv. Res. Sci. Commun. Technol., pp. 24–27, 2024, doi: 10.48175/ijarsct-22506.
M. Yusup, S. Y. J. Prasetyo, and T. Wellem, “Evaluation of Prediction Accuracy in ARIMA and LSTM Algorithms for Agricultural Commodity Prices,” in 2024 3rd International Conference on Creative Communication and Innovative Technology (ICCIT), 2024, pp. 1–7. doi: 10.1109/ICCIT62134.2024.10701123.
A. Mahawan, S. Jaiteang, K. Srijiranon, and N. Eiamkanitchat, “Hybrid ARIMAX and LSTM Model to Predict Rice Export Price in Thailand,” in 2022 International Conference on Cybernetics and Innovations (ICCI), 2022, pp. 1–6. doi: 10.1109/ICCI54995.2022.9744161.
T. Lin, “Comparison Between ARIMA and LSTM models in Stock Price Forecast,” Sci. Technol. Eng. Chem. Environ. Prot., vol. 1, no. 10, pp. 1859–1865, 2024, doi: 10.61173/ycyqxh68.
B.Rebecca, P. S. Padmini, V.Dhanakodi, and M.Gayathri, “A Novel Hybrid Method for Predicting Specific Crop Yield,” Int. J. Sci. Methods Comput. Sci. Eng., vol. 01, no. 01, pp. 32–38, 2024, doi: 10.58599/ijsmcse.2024.1109.
D. G. Taslim and I. M. Murwantara, “A Comparative Study of ARIMA and LSTM in Forecasting Time Series Data,” in 2022 9th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), 2022, pp. 231–235. doi: 10.1109/ICITACEE55701.2022.9924148.
P. Das, “Time Series Forecasting BT - Econometrics in Theory and Practice: Analysis of Cross Section, Time Series and Panel Data with Stata 15.1,” P. Das, Ed., Singapore: Springer Singapore, 2019, pp. 439–453. doi: 10.1007/978-981-32-9019-8_14.
A. Luceño and D. Peña, “ Autoregressive Integrated Moving Average ( ARIMA ) Modeling ,” Encycl. Stat. Qual. Reliab., no. 2, 2007, doi: 10.1002/9780470061572.eqr276.
Melina et al., “Comparative Analysis of Time Series Forecasting Models Using Arima and Neural Network Autoregression Methods,” Barekeng, vol. 18, no. 4, pp. 2563–2576, 2024, doi: 10.30598/barekengvol18iss4pp2563-2576.
D. R. Sanjaya, B. Surarso, and T. Tarno, “Stock Price Forecasting on Time Series Data Using the Long Short-Term Memory (LSTM) Model,” Int. J. Curr. Sci. Res. Rev., vol. 07, no. 12, pp. 8866–8875, 2024, doi: 10.47191/ijcsrr/v7-i12-26.
D. S. M. -, “An International Study of Application of Long Short-Term Memory (LSTM) Neural Networks for the prediction of stock and forex markets,” Int. J. Multidiscip. Res., vol. 5, no. 3, pp. 1–9, 2023, doi: 10.36948/ijfmr.2023.v05i03.3345.
K. Kashif and R. Ślepaczuk, “LSTM-ARIMA as a hybrid approach in algorithmic investment strategies,” Knowledge-Based Syst., vol. 320, pp. 1–44, 2025, doi: 10.1016/j.knosys.2025.113563.
D. G. Taslim and I. M. Murwantara, “Comparative analysis of ARIMA and LSTM for predicting fluctuating time series data,” Bull. Electr. Eng. Informatics, vol. 13, no. 3, pp. 1943–1951, 2024, doi: 10.11591/eei.v13i3.6034.
T. A. van Beek and D. Joulain, “The essential oil of patchouli, Pogostemon cablin: A review,” Flavour Fragr. J., vol. 33, no. 1, pp. 6–51, 2018, doi: 10.1002/ffj.3418.
A. K. Rajeevan, P. V. Shouri, and U. Nair, “Arima based wind speed modeling for wind farm reliability analysis and cost estimation,” J. Electr. Eng. Technol., vol. 11, no. 4, pp. 869–877, 2016, doi: 10.5370/JEET.2016.11.4.869.
A. R. Garcia, S. B. Filipe, C. Fernandes, C. Estevão, and G. Ramos, Time Series Analysis Forecasting and control.
D. K. Yadav, K. S., and L. Goswami, “Autoregressive Integrated Moving Average Model for Time Series Analysis,” in 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC), 2024, pp. 1–6. doi: 10.1109/ICOCWC60930.2024.10470488.
F. Shahid, A. Zameer, and M. Muneeb, “Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM,” Chaos, Solitons and Fractals, vol. 140, p. 110212, 2020, doi: 10.1016/j.chaos.2020.110212.
D. I. Puteri, “Implementasi Long Short Term Memory (LSTM) dan Bidirectional Long Short Term Memory (BiLSTM) Dalam Prediksi Harga Saham Syariah,” Euler J. Ilm. Mat. Sains dan Teknol., vol. 11, no. 1, pp. 35–43, 2023, doi: 10.34312/euler.v11i1.19791.
S. Ray, A. Lama, P. Mishra, T. Biswas, S. Sankar Das, and B. Gurung, “An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique Image 1,” Appl. Soft Comput., vol. 149, p. 110939, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110939.
O. S. Jadhav, S. P. Dhokare, S. Mote, P. Nistane, and P. G. School, “Estimation of Market Price through LSTM Model,” in 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), 2024, pp. 1148–1152. doi: 10.1109/IC2PCT60090.2024.10486384.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
X. Zhang, X. Liang, A. Zhiyuli, S. Zhang, R. Xu, and B. Wu, “AT-LSTM: An Attention-based LSTM Model for Financial Time Series Prediction,” IOP Conf. Ser. Mater. Sci. Eng., vol. 569, no. 5, 2019, doi: 10.1088/1757-899X/569/5/052037.
R. A. Fasha Dewatri and R. Eka Putra, “Implementasi Long Short-Term Memory dalam Mendeteksi Kesalahan Pronunciation Bahasa Inggris Berbasis Audio,” J. Informatics Comput. Sci., vol. 6, no. 03, pp. 747–754, 2025, doi: 10.26740/jinacs.v6n03.p747-754.
J. Zhou, X. Tong, J. Zhou, S. Bai, R. Liu, and H. Zhao, “Application of a hybrid ARIMA-LSTM model based on the LightGBM in grid frequency prediction,” in 2024 3rd Asian Conference on Frontiers of Power and Energy (ACFPE), 2024, pp. 409–413. doi: https://doi.org.10.1109/ACFPE63443.2024.10800878.
L. X. Lim, T. Connie, and M. K. O. Goh, “Enhancing Traffic Analysis and Prediction through A Hybrid LSTM-ARIMA Model,” in 2024 International Conference on Information Management and Technology (ICIMTech), 2024, pp. 672–677. doi: 10.1109/ICIMTech63123.2024.10780834.
S. Kim and H. Kim, “A new metric of absolute percentage error for intermittent demand forecasts,” Int. J. Forecast., vol. 32, no. 3, pp. 669–679, 2016, doi: 10.1016/j.ijforecast.2015.12.003.
DOI: http://dx.doi.org/10.30829/zero.v9i2.25920
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Publisher : Department of Mathematics Faculty of Science and Technology Universitas Islam Negeri Sumatera Utara Medan | |
✉️ Email: zero_journal@uinsu.ac.id 📱 WhatsApp:085270009767 (Admin Official) | |
 |  |  |  |  |