Harnessing smartphone RGB imagery and LiDAR point cloud for enhanced leaf nitrogen and shoot biomass assessment - Chinese spinach as a case study.

Accurate estimation of leaf nitrogen concentration and shoot dry-weight biomass in leafy vegetables is crucial for crop yield management, stress assessment, and nutrient optimization in precision agriculture. However, obtaining this information often requires access to reliable plant physiological and biophysical data, which typically involves sophisticated equipment, such as high-resolution sensors and cameras. In contrast, smartphone-based sensing provides a cost-effective, manual alternative for gathering accurate plant data. In this study, we propose an innovative approach to estimate leaf nitrogen concentration and shoot dry-weight biomass by integrating smartphone-based RGB imagery with Light Detection and Ranging (LiDAR) data, using (Chinese spinach) as a case study. Specifically, we derive spectral features from the RGB images and structural features from the LiDAR data to predict these key plant parameters. Furthermore, we investigate how plant traits, modeled using smartphone data based indices, respond to varying nitrogen dosing, enabling the identification of the optimal nitrogen dosage to maximize yield in terms of shoot dry-weight biomass and vigor. The performance of crop parameter estimation was evaluated using three regression approaches: support vector regression, random forest regression, and lasso regression. The results demonstrate that combining smartphone RGB imagery with LiDAR data enables accurate estimation of leaf total reduced nitrogen concentration, leaf nitrate concentration, and shoot dry-weight biomass, achieving best-case relative root mean square errors as low as 0.06, 0.15, and 0.05, respectively. This study lays the groundwork for smartphone-based estimate leaf nitrogen concentration and shoot biomass, supporting accessible precision agriculture practices.