Prediksi Perubahan Luas Perkebunan Aren di Jawa Barat Berbasis Geospasial dengan Algoritma ARIMA dan Machine Learning

Dadan Zaliluddin; Asep Dian  Heryadiana; Dimar  Pateman

doi:10.30656/djx30932

Authors

Dadan Zaliluddin Universitas Majalengka https://orcid.org/0000-0001-5916-6142
Asep Dian Heryadiana Universitas Majalengka
Dimar Pateman Universitas Majalengka

DOI:

https://doi.org/10.30656/djx30932

Abstract

Aren palm (Arenga pinnata) is an important plantation commodity in West Java with high potential as a renewable bioethanol source. However, fluctuations in plantation area due to land conversion, climate variability, and socio-economic factors create challenges for sustainable plantation management. Previous studies mostly focus on production analysis without integrating time-series forecasting, machine learning, and spatial analysis.This study aims to predict changes in aren plantation areas in West Java using a hybrid approach combining ARIMA, Random Forest, and Long Short-Term Memory (LSTM) models, integrated with Geographic Information System (GIS) for spatial visualization. Historical plantation data from 2013–2023 were analyzed and evaluated using MAE, RMSE, and MAPE metrics. The ARIMA model achieved a MAPE of 0.94% and RMSE of 88.30 Ha, indicating strong short-term forecasting performance. Machine learning models demonstrated improved robustness when incorporating environmental variables. Spatial visualization further highlights regions with high risk of land conversion. The proposed framework provides a spatial-temporal prediction model that supports data-driven decision-making for sustainable plantation management and renewable energy development in West Java.

Author Biography

Dadan Zaliluddin, Universitas Majalengka

Dadan Zaliluddin, ST., M.Kom. adalah Dosen Tetap pada Program Studi Informatika, Fakultas Teknologi Informasi, Universitas Majalengka. Beliau memperoleh gelar Sarjana Teknik dari Universitas Komputer Indonesia dan Magister Komputer dari Universitas Budi Luhur. Sejak tahun 2015 aktif sebagai akademisi, peneliti, dan pengabdi masyarakat di bidang Komputasi Visual, Multimedia, Data Science, serta Sistem Informasi Geospasial. Bidang penelitian yang saat ini difokuskan adalah integrasi machine learning, analisis spasial-temporal, dan visualisasi data untuk mendukung pengambilan keputusan berbasis teknologi informasi.

References

[1] A. Maidangkay and E. Dosoputranto, “Pengaruh Lamanya Fermentasi dan Temperatur Destilasi Nira Aren (Saguer) Terhadap Kualitas Bioetanol,” Jurnal Masina Nipake, vol. 1, no. 1, 2021.

[2] D. S. Effendi, “Prospek Pengembangan Tanaman Aren (Arenga pinnata Merr) Mendukung Kebutuhan Bioetanol di Indonesia,” Perspektif: Review Penelitian Tanaman Industri, vol. 9, no. 1, 2010.

[3] A. Latara, M. Mustofa, and S. Botutihe, “Destilasi Bioetanol dari Nira Aren dengan Variasi Waktu Pengadukan pada Proses Fermentasi,” Jurnal Teknologi Pertanian Gorontalo (JTPG), vol. 6, no. 2, 2021, doi: 10.30869/jtpg.v6i2.809.

[4] J. Fattah, L. Ezzine, Z. Aman, H. El Moussami, and A. Lachhab, “Forecasting of demand using ARIMA model,” International Journal of Engineering Business Management, vol. 10, 2018, doi: 10.1177/1847979018808673.

[5] K. Kashif and R. Ślepaczuk, “LSTM-ARIMA as a hybrid approach in algorithmic investment strategies,” Knowl. Based. Syst., vol. 320, Jun. 2025, doi: 10.1016/j.knosys.2025.113563.

[6] K. Albeladi, B. Zafar, and A. Mueen, “Time Series Forecasting using LSTM and ARIMA.” [Online]. Available: www.ijacsa.thesai.org

[7] M. K. MASDARI, “Pemetaan perkebunan warga desa teluk sungka berbasis web GIS,” Jurnal Karya Abdi, vol. 4, no. 1, 2023, doi: 10.32520/karyaabdi.v4i1.2395.

[8] R. Ospina, J. A. M. Gondim, V. Leiva, and C. Castro, “An Overview of Forecast Analysis with ARIMA Models during the COVID-19 Pandemic: Methodology and Case Study in Brazil,” Jul. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/math11143069.

[9] A. Oussous, F. Z. Benjelloun, A. Ait Lahcen, and S. Belfkih, “Big Data technologies: A survey,” 2018. doi: 10.1016/j.jksuci.2017.06.001.

[10] X. Wu, X. Zhu, G. Q. Wu, and W. Ding, “Data mining with big data,” IEEE Trans. Knowl. Data Eng., vol. 26, no. 1, 2014, doi: 10.1109/TKDE.2013.109.

[11] E. M. Tumanggor, “Analisa Dan Implementasi Data Mining Untuk Memprediksi Jumlah Material Bangunan Menggunakan Algoritma Autoreggresive Intergrated Moving Average (ARIMA),” 2021.

[12] S. Tanwar, “Machine Learning,” in Computational Science and Its Applications, 2024. doi: 10.1201/9781003347484-2.

[13] A. Sutanto and T. Aditya, “Pendekatan Otomatisasi Evaluasi Kualitas Kelengkapan Pada Informasi Geospasial,” Jurnal Geosaintek, vol. 7, no. 1, 2021, doi: 10.12962/j25023659.v7i1.8478.

[14] H. Hassyddiqy and H. Hasdiana, “Analisis Peramalan (Forecasting) Penjualan Dengan Metode ARIMA (Autoregressive Integrated Moving Average) Pada Huebee Indonesia,” Data Sciences Indonesia (DSI), vol. 2, no. 2, pp. 92–100, Jan. 2023, doi: 10.47709/dsi.v2i2.2022.

[15] Okpatrioka Okpatrioka, “Research And Development (R&D) Penelitian Yang Inovatif Dalam Pendidikan,” Dharma Acariya Nusantara: Jurnal Pendidikan, Bahasa dan Budaya, vol. 1, no. 1, 2023, doi: 10.47861/jdan.v1i1.154.