Rice Phenology Classification Model Based on Sentinel-1 Using Machine Learning Method on Google Earth Engine

Abstract

Rice phenology information is important in supporting planning systems, land management, and making the right decisions to sustainably carry out rice production. This study aimed to determine the best rice phenology classification model by combining VV and VH polarizations on Sentinel-1 images, which produce polarization indices such as the ratio polarization index (RPI), normalized different polarization index (NDPI), and average polarization index (API) using the ensemble random forest (RF) using the Google Earth Engine (GEE) application. This research was conducted in the rice fields of PT Sang Hyang Seri, Subang Regency, West Java. The research data comprised Sentinel-1 SAR GRD satellite imagery data with acquisition modes interferometric wide swath (IW) for 2021–2022 obtained from the GEE platform. In this study, the performance of two machine learning methods for classification was compared: classification and regression trees (CART) and RF. This study found that the best rice phase classification model could be acquired from the RF method with four predictors, namely, API, RPI, NDPI, and slope, with a statistical value of kappa of 98.22%. The RF classification model has better accuracy than the CART classification model.