UAV-based individual Chinese cabbage weight prediction using multi-temporal data

• Published in: Scientific reports Vol. 13; no. 1; p. 20122
• Main Authors: Aguilar-Ariza, Andrés, Ishii, Masanori, Miyazaki, Toshio, Saito, Aika, Khaing, Hlaing Phyoe, Phoo, Hnin Wint, Kondo, Tomohiro, Fujiwara, Toru, Guo, Wei, Kamiya, Takehiro
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 17.11.2023; Nature Portfolio
• Subjects: Brassica oleracea; Harvesting; Plant extracts; Predictions; Regression analysis; Temporal variations; Unmanned aerial vehicles; Weight
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-47431-y

The use of unmanned aerial vehicles (UAVs) has facilitated crop canopy monitoring, enabling yield prediction by integrating regression models. However, the application of UAV-based data to individual-level harvest weight prediction is limited by the effectiveness of obtaining individual features. In this study, we propose a method that automatically detects and extracts multitemporal individual plant features derived from UAV-based data to predict harvest weight. We acquired data from an experimental field sown with 1196 Chinese cabbage plants, using two cameras (RGB and multi-spectral) mounted on UAVs. First, we used three RGB orthomosaic images and an object detection algorithm to detect more than 95% of the individual plants. Next, we used feature selection methods and five different multi-temporal resolutions to predict individual plant weights, achieving a coefficient of determination (R ) of 0.86 and a root mean square error (RMSE) of 436 g/plant. Furthermore, we achieved predictions with an R greater than 0.72 and an RMSE less than 560 g/plant up to 53 days prior to harvest. These results demonstrate the feasibility of accurately predicting individual Chinese cabbage harvest weight using UAV-based data and the efficacy of utilizing multi-temporal features to predict plant weight more than one month prior to harvest.