Assessing the precision and consistency of agroview in orchard management: A multi-temporal analysis

Remote sensing technologies and predictive models have seen significant advancements, yet issues related to data quality, consistency, and accuracy persist. While many studies emphasize model accuracy, the precision and consistency of these technologies are often overlooked. This study addresses that gap by conducting a comprehensive evaluation of Agroview, a cloud-based AI-driven application, assessing its performance in analyzing plant-level data, such as inventory, canopy height, area, and leaf density, across two citrus blocks over four distinct data collection dates. Agroview demonstrated consistent reliability, with low coefficients of variation (CV) across key metrics. For example, tree inventory showed variations of <3 %, with CVs of 2.63 % for Block A and 1.56 % for Block B. Canopy height measurements exhibited CVs below 9 % for most trees, with a slightly higher CV of 12 % for trees over 12 ft in Block B. This analysis highlights the software's precision and identifies areas for potential refinement. The findings of this study highlight the importance of precision in remote sensing, providing valuable insights for users and stakeholders while promoting confidence in the broader adoption of advanced technologies in agriculture.