Identification of Sugarcane Fields and Classification of Their Growth Stages using Random Forest on Google Earth Engine

SARI, DEWI KANIA
NOVAL, MUHAMMAD SAPUTRA

ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika
Vol 13, No 3: Published July 2025

Remote sensing technology, particularly Sentinel-2 imagery, offers an efficient and large-scale solution for monitoring sugarcane crop growth phases. This study aims to identify sugarcane fields and classify their growth phases in Jatitujuh District, Majalengka Regency, using the Random Forest algorithm on the Google Earth Engine (GEE) platform. Three vegetation indices—NDVI, NDRE, and CIRE—were used as input variables in the classification process. The results indicate that the stem elongation phase is the most dominant, followed by the maturation, fallow, and sprouting phases. The developed classification model achieved an overall accuracy of 80%, with a Kappa coefficient of 65% and an F1-Score of 68%. This study is expected to contribute to the optimization of sugarcane production in Indonesia and serve as a reference for more effective land management and planning.