The Assessment of Random Forest Algorithm in Identifying Paddy Growth Stage in Karawang, West Java

Abstract

This study tried to estimate distribution and area of land cover by focusing on the area of the paddy growing phase using the Random Forest model on Sentinel 1A data and Area Frame Sample (Kerangka Sampling Area or KSA) observation data as reference data. Sentinel-1 data from Karawang Regency, West Java was taken monthly for a one-year period starting from January 2020 to December 2020. It was found that the results of extrapolation with the Random Forest algorithm have similar trends and patterns to the results of the KSA. Still, compared to the Cropping Calendar (KATAM) model of the Agricultural Research and Development Agency, the initial planting period of paddy in Karawang Regency, the results of the identification of the Random Forest algorithm appeared two months earlier.