Virtual Orchard (VO) is a technology to describe canopy geometry for individual trees in an orchard using 3D reconstruction of tree canopies. The 3D model in VO is created by photogrammetry using a series of aerial images of orchards acquired from different angles and heights. Orchard topography, individual canopy cover, volume, height, size, spacing, etc., can be estimated by VO technology. This information can be further analyzed and interpreted by prediction models to generate useful and timely knowledge such as water/nutrient requirement and yield forecast that will help growers conduct better orchard management, improve yield, decrease waste, and maintain the quality of the environment.
Some examples of Virtual Orchard applications are:
- Estimating PAR (canopy light interception)
- Simulate shadow on tree crown
- Yield forecasting
- Blossom mapping
- Robotic pruning/thinning
Virtual Orchard can also be developed in non-visible bands such as near-infrared (NIR) and red edge. NIR imagery indicates plant vigor; a lower NIR value usually means the plant is under stress. NIR can also be used to normalize chlorophyll-sensitive bands such as Red and create vegetation indices such as NDVI. Red-edge is another non-visible band that includes important information about plant stress, chlorophyll, and nitrogen content. Lower values in the red-edge band usually indicated nitrogen stress.
We currently use this technology to forecast the yield in Almond and Citrus, map yield in alfalfa, and conduct phenotyping in walnut and Pistachio.