<![CDATA[The urgency of this research is based on data from the Pangkalpinang City Population and Civil Registration Service in 2020, the population reached 218,569 people and continued to grow to 232,915 people in 2023. The importance of monitoring vegetation density in the context of green economic growth, which requires careful evaluation of the balance between economic development and environmental conservation. With rapid urban growth, the Pangkalpinang city government requires a variety of approaches to accurately predict vegetation density. By identifying the factors that affect land vegetation density, this study aims to develop a machine learning model that can predict land vegetation density conditions over a certain period of time in the future. This research method involves collecting spatial vegetation density data over a period of 11 years using remote sensing technology or remote monitoring, such as satellite imagery. Furthermore, time series data will be analyzed and modeled using machine learning techniques, focusing on algorithms that can overcome the spatial and temporal dynamics of vegetation density. Machine learning algorithms, especially time series algorithms such as Autoregressive Integrated Moving Average (ARIMA) will be used to build a spatial prediction model for vegetation density. The results of this study indicate that the use of ARIMA is able to produce an accurate prediction model in projecting vegetation density in Pangkalpinang City. The ARIMA model shows strong performance with low error metrics, indicating its effectiveness in making accurate predictions for the given data set. The results of this study are expected to provide valuable information for the Pangkalpinang city government in making decisions related to environmental management and green economic development. By involving collaboration between researchers with three complementary expertise including computer science, civil engineering and natural resource conservation and policy makers.]]>
Copyrights © 2025
