<![CDATA[Aren palm (Arenga pinnata) plays a significant role as an economic commodity and a renewable energy source in West Java, Indonesia. However, fluctuations in plantation areas caused by land use change, climate variability, and socio-economic factors have created challenges for sustainable management. Accurate prediction of aren plantation area dynamics is required to support decision-making and policy design for renewable energy development and environmental sustainability.This study aims to predict changes in aren plantation areas in West Java using a combination of Autoregressive Integrated Moving Average (ARIMA) for time-series forecasting and Machine Learning algorithms for enhanced prediction accuracy. Historical data of aren plantation areas from 2013 to 2023 were collected from official government databases. ARIMA was applied to model temporal trends, while Machine Learning approaches such as Random Forest and Long Short-Term Memory (LSTM) were employed to capture non-linear relationships and integrate external factors such as rainfall, soil characteristics, and urbanization patterns. In addition, a geospatial approach using Geographic Information System (GIS) was adopted to visualize spatial changes in plantation areas.Preliminary results indicate that ARIMA successfully models short-term trends with relatively low forecasting errors (RMSE < 15%). Machine Learning models demonstrate the potential to improve robustness and predictive accuracy by incorporating multidimensional variables. The integration of spatial visualization enables stakeholders to identify high-risk regions for land conversion and areas with strong potential for sustainable aren cultivation. The findings of this research provide a foundation for developing a decision support system to enhance sustainable plantation management and bioethanol policy planning in West Java. The proposed predictive framework contributes not only to the field of computational forecasting but also to the strategic alignment of renewable energy development with local socio-economic priorities. Keywords: ARIMA, Machine Learning, Geospatial, Aren Plantation, Forecasting ]]>
Copyrights © 2026
