SPATIAL MACHINE LEARNING FOR MONITORING TEA LEAVES AND CROP YIELD ESTIMATION USING SENTINEL-2 IMAGERY, (A Case of Gunung Mas Plantation, Bogor)

Indonesia's tea production and export volume have fluctuated with a downward trend in the last five years, partly due to increasingly competitive world quality. Crop yield estimation is part of management plucking, affecting quality quantity. The constraint estimating crop yields requires technology that can make process more effective efficient. Remote sensing machine learning been widely used precision agriculture. Recently, big data processing, especially remote data, learning, deep carried out using cloud computing platform. Therefore, we propose GeoAI, combination Sentinel-2A imagery, Google Collaboratory, predict ready for plucking leaves at optimal time Gunung Mas Plantation Bogor. We selected bands extracted features (i.e., NDVI) as training set. Then utilized blocks boundary generate labels Random Forest (RF) Support Vector Machine (SVM). classification results were further estimate yield. RF classifier able achieve overall accuracy 51% SVM 54%. Meanwhile, optimally aged 75.62% 52.88% SVM. Thus, better terms accuracy. superior predicting blocks.