One of the bottlenecks in the development of UAV-based crop growth estimation models has been the need for ground-truth data collection through plant sampling in a field, which required a great deal of effort. Thus, we investigated the viability of utilizing datasets derived from reduced sampling size for the development of growth estimation models, with the aim of enhancing the efficiency of ground-truth data collection. Koshihikari, a japonica rice variety, was grown at a planting spacing of 15 × 30 cm with various fertilizer conditions and transplanting dates. Once a week from transplanting to the heading date, aerial RGB and multispectral images were collected with a UAV. Subsequently, four adjacent hills from each plot were harvested, and above-ground biomass (AGB) and leaf area index (LAI) measurements were taken for each hill. For each hill, the ground-measured data was linked to the features (plant height, vegetation indices, and texture indices) derived from corresponding UAV images. Three datasets were compiled using the values of single hills (15 × 30 cm), the average values of two adjacent hills (30 × 30 cm), and those of four adjacent hills (60 × 60 cm). Models estimating AGB and LAI from UAV-derived features were developed with each dataset using single regression and machine learning (ML) algorithms, and the prediction accuracy was compared among the three datasets. The prediction accuracy of the single regression models was similar across all datasets. In addition, it was demonstrated that the dataset based on single-harvested hills can contribute to improving the prediction accuracy of the ML models. In previous studies, datasets were generally developed by aggregating data from multiple harvested hills, yet our results indicated that the dataset based on single-harvested hills was sufficiently reliable for model development and can be utilized, consequently allowing for more efficient ground-truth data collection.
