CanopyCAM – an edge-computing sensing unit for continuous measurement of canopy cover percentage of dry edible beans

Canopy cover (CC) is an important indicator for crop development. Currently, CC can be estimated indirectly by measuring leaf area index (LAI) using commercially available hand-held meters. However, it does not capture the dynamics of CC. Continuous monitoring essential dry edible beans production since affect water use, weed, and disease control. It also helps growers to closely monitor “yellowness”, or senescence decide proper irrigation cutoff timing allow down harvest. Therefore, goal this study was develop a device – CanopyCAM, containing software hardware that bean continuously. CanopyCAM utilized in-house developed image-based algorithm, edge-computing, Internet Things (IoT) telemetry process transmit in real-time. In 2021 growing season, six CanopyCAMs were with three installed fully irrigated research plots at commercial farm fields, respectively. measurements recorded 15 min interval from 7:00 am pm each day. Initially, overall trend development increased over time but fluctuations daily readings noticed due changing lighting conditions which caused some overexposed images. A simple filtering algorithm remove “noisy images”. measured (CCCanopyCAM) compared obtained LI-COR Plant Analyzer (CCLAI). The average error between CCCanopyCAM CCLAI 2.3 %, RMSE R2 2.95 % 0.99, addition, maximum (CCmax) duration (tmax_canopy) identified installation location generalized reduced gradient (CRG) nonlinear optimization. An improvement correlation found yield combination CCmax tmax_canopy (R2 = 0.77, Adjusted 0.62) as versus 0.58) 0.45) only. This IoT enabled provided accurate continuous could used researchers different purposes.