Our Smart Orchard Pilot
Washington State's Tree Fruit Research Commission asked innov8.ag to lead a smart orchard project in collaboration with researchers from WSU & OSU at Chiawana Orchards. Our goal is to "sensorize" a orchard from multiple hardware providers, bringing together growers, data, and researchers to create a sustainable, "smart" orchard with insights that impact growers' bottom lines.
As we head into 2021 growing season, we've been commissioned to expand to a second Smart Orchard site, while also introducing our base crop count imaging capabilities to orchard & vineyard growers.
• Learn capabilities of modern orchard decision making with basic AI and Data Analytics
• Shift grower decision making process to enable management decisions based on unified data, and 'smart management'
• Help growers better manage their water usage, labor, equipment, and chemical usage
• Enable growers to better understand weather and climate change to make precise, informed decisions.
• Integrating data provided by a ecosystem sensors and data providers
• Provide consolidated data warehousing to collect & consolidate data, leveraging Microsoft Farmbeats for efficiencies thru API data interchanges
• Provide regular insights and analyses of integrated data
• Provide consolidated raw access to data
In collaboration with the WSU AgWeatherNet Team we found not only the orchard-specific climate, but the difference between in-canopy and outside canopy of about 4 degree differences which has implications for growing degree days (GDD).
Irrigation Planning Optimization
We consolidated the variables used by the area manager to plan weekly irrigation sets into a irrigation planning dashboard. Subsequently he has all of his data in one place in order to further optimize his planning and make efficient decisions.
In collaboration with WSU’s Dr. Lav Khot & PhD candidate Abhilash Chandel, we utilized drone imagery to determine evapotranspiration requirements throughout an orchard block with implications to define irrigation zones that again should enable more uniform crop distribution and fruit quality. This validated the importance and capability of apple counting through imaging technology with implications for growers on planning pruning, thinning, harvest, chemical applications, and labor. Subsequently, in 2021 the Smart Orchard Project will expand to incorporate GreenAtlas ATV-Based imaging as a foundational data source.
We confirmed the effectiveness of multiple soil moisture probes from Meter Group, Sentek, and AquaSpy with strong correlation between measurements.
We identified previously unidentified areas of stress in parts of the orchard block due to soil variation. With implications on how the grower can supplement nutrients and watering to obtain more uniform results.
We utilized multiple forms of connectivity from LoRa to traditional mobile connectivity to private 900MHz connectivity to optimize use cases that best align with each of these technologies.
Through WSU and Microsoft hackathons we determined and defined management zones based on nutrient distribution while enabling WSU’s Bernadita Sallato to establish a relationship between fruit quality and soil nutrient availability.
Spatiotemporal water use mapping of a commercial apple orchard using UAS based spectral imagery
Crop water use estimation at high geospatial resolution is critical for site-specific irrigation management of perennial specialty crops. This study aims to map actual evapotranspiration (ETa) of a commercial apple orchard using unmanned aerial system (UAS) based thermal and multispectral imagery and a widely adopted METRIC (Mapping Evapotranspiration at High Resolution with Internalized calibration) energy balance model (UASM). Four imaging campaigns were conducted during the 2020 growth season and weather data for pertinent days was downloaded from the nearest WSU-AgWeatherNet network station. 24-h ET a was also calculated from the soil water balance (SWB) approach that used soil moisture data from sensors installed at three locations and down to depth of 111 cm. A high linear correlation (r) of 0.84 and non-significant difference (p = 0.5) was observed between UASM derived ET a (5.05 ± 0.8 [Mean ± Std. Dev.] mm day -1 ) and SWB calculated ET a (5.44 ± 1.81 mm day -1 ). Notable differences in spatiotemporal water use and crop-coefficients were observed within the orchard. A moderately strong correlation was also observed between the UASM derived crop-coefficients and multispectral imagery derived Normalized Difference Vegetation Index (r = 0.69) that may also be used for estimating actual crop water use. Overall, approach presented in this study may help identify under or over-irrigated areas within the orchard. It may also assist in developing site-specific irrigation prescription maps and schedules.