The Application of Unmanned Aerial Vehicles (UAVs) and Extreme Gradient Boosting (XGBoost) to Crop Yield Estimation: A Case Study of Don Tum District, Nakhon Pathom, Thailand

Abstract

Rice (Oryza sativa L.) is a staple food for more than half of the global population. This research, therefore, aims to explore the estimation of crop yields towards the application of unmanned aerial vehicles (UAVs). The research areas are the sample rice fields owned by Sam Ngam Large-Scale Rice Production Community Enterprise in Don Tum District, Nakhon Pathom. The data collected by both RGB and multispectral UAVs was used for estimating the crop yields of Rice Department 41 (RD41), a rice variety, and then analyzed by a geographic information system (GIS). Multiple Linear Regression was applied to factor analysis for the purpose of crop yield estimation based on the factors investigated and obtained by the UAVs. These factors included vegetation indexes (i.e. Normalized Difference Vegetation Index, Green Normalized Difference Vegetation Index, and Triangular Greenness Index), plant height, and canopy coverage. The prediction of the analysis model was proved to be valid (R2 = 0.99; RMSE = 2.506 g.). Extreme Gradient Boosting (XGBoost) was applied to increase the accuracy of the estimation (RMSE = 0.557 g.; MAE = 0.364). The findings of study showed that the utilization of UAVs could contribute to the estimation of crop yield in the research areas.