A One-Dimensional Light Detection and Ranging Array Scanner for Mapping Turfgrass Quality

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 12; p. 2215
• Main Authors: Rosenfield, Arthur, Ficht, Alexandra, Lyons, Eric M., Gharabaghi, Bahram
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-06-2024
• Subjects: Accuracy; Arrays; Data collection; Data processing; Environmental impact; Golf courses; Grasses; Herbicides; Homogeneity; Kinematics; Landscaping; LiDAR; Machine learning; non-linear regression; precision agriculture; random forest; Remediation; Remote sensing; Scanners; Sensors; sod; Turf; turfgrass; Turfgrasses; Canada; United States > US
• DOI: 10.3390/rs16122215
• EISSN: 2072-4292

The turfgrass industry supports golf courses, sports fields, and the landscaping and lawn care industries worldwide. Identifying the problem spots in turfgrass is crucial for targeted remediation for turfgrass treatment. There have been attempts to create vehicle- or drone-based scanners to predict turfgrass quality; however, these methods often have issues associated with high costs and/or a lack of accuracy due to using colour rather than grass height (R2 = 0.30 to 0.90). The new vehicle-mounted turfgrass scanner system developed in this study allows for faster data collection and a more accurate representation of turfgrass quality compared to currently available methods while being affordable and reliable. The Gryphon Turf Canopy Scanner (GTCS), a low-cost one-dimensional LiDAR array, was used to scan turfgrass and provide information about grass height, density, and homogeneity. Tests were carried out over three months in 2021, with ground-truthing taken during the same period. When utilizing non-linear regression, the system could predict the percent bare of a field (R2 = 0.47, root mean square error < 0.5 mm) with an increase in accuracy of 8% compared to the random forest metric. The potential environmental impact of this technology is vast, as a more targeted approach to remediation would reduce water, fertilizer, and herbicide usage.