Year: 2022

Show and tell progress towards Precision Apple Crop load MANagement

3 Thursdays via Zoom beginning January 12

12 PM (Eastern) / 9 AM (Pacific)

JAN 12 – How can PACMAN help you make more money?

JAN 19 – Innovative new technology to implement PACMAN (Part 1)

JAN 26 – Innovative new technology to implement PACMAN (Part 2)   & How’s your adoption going?

Please join us for a series of Briefings by the PACMAN Research and Extension teams to update you on what we see as the current state of precision crop load management of apples. We are entering our third year of the USDA/NIFA/SCRI funded research and Extension project titled “Precision Crop Load Management for Apples” and we have interesting insights to share with on you vision based technologies and potential management implications! In addition, industry partners have been hard at work developing “turnkey” solutions to assessing your apple crop load management efforts and are invited to participate in a “show and tell.” (Barring any hard sales pitch of course!)

REGISTRATION

http://bit.ly/3B14LS7

Brought to you by the PACMAN Extension team

-Jon Clements (UMass Amherst)

-Karen Lewis (WSU) and Tory Schmidt (WTFRC)

-Mario Miranda & Craig Kahlke (Cornell University)

-Anna Wallis (MSU) & Phil Schwallier Long He/Daniel Weber (PSU)

Terence Robinson, Yu Jiang, Luis Gonzalez, Mario Miranda Sazo, and Craig Kahlke

Posted with permission, Fruit Notes, Volume 22 Issue 14 September 12, 2022 (Cornell Cooperative Extension Lake Ontario Fruit Program)

In the last two growing seasons and in a few orchards in the Lake Ontario Fruit region and at Cornell AgriTech in Geneva, the testing of several digital technologies has been taking place to help improve the accuracy and labor efficiency of precision crop load management. Our final goal is to automate fruit, bud, and flower counting using computer vision technologies. We envision the use of autonomous or driven vehicles with computer vision capabilities to geo-reference each tree in a high-density orchard, either a 2-D or a 3-D canopy system, and then count/measure, very accurately:
• Trunk diameter
• Dormant flower buds
• Floral buds at green tip to pink
• Flowers at bloom
• Fruitlets at 10-20 mm size
• Fruits at 25-35mm size
• Fruits pre-harvest

Read the full article below…

T.L. Robinson, L. Gonzalez, L. Cheng, Y. Ziang, G. Peck, B. Arnoldson, M. Gomez, M. Guerra, Mario Miranda Sazo, C. Kahlke, T. Einhorn, A. Wallis, S. Musacchi, S. Serra, K. Lewis, T. Schmidt, P. Heinemann, L. He, T. Kon, S. Sherif10, J. Clements1, and C. Layer

IHC 2022, 31st International Horticultural Congress, 14-20 August, 2022, Angers, France. https://www.ihc2022.org/

“We are conducting a USA national SCRI project to develop precision crop load management strategies and machines to manage the number of fruits per tree to exactly the economic optimum. We have done physiological experiments to define the biological potential of yield and fruit size of ‘Gala’ and ‘Honeycrisp’ apple cultivars in four climates (West, Mid-West, North-East and South-East USA) to estimate the economic optimum number of fruits per tree. Our results show that the dry, high light climate of WA generally can support a higher crop load than the eastern USA growing regions. Our multi-location experiments have shown that leaving too many flower buds during pruning results in lower crop value than the optimum flower bud number. Optimum flower bud number in our studies of ‘Gala’ and ‘Honeycrisp’ was between 1.5-2.0 flower buds per final target fruit number. To achieve the optimum fruit number per tree we
employ: 1) precision pruning to remove flower buds to a pre determined flower bud load; 2) precision chemical thinning through sequential chemical thinning sprays guided by the use of computer models to adjust the dose and timing of chemical
application and to assess the effect of the chemical sprays shortly after application to inform re-application; and 3) precision hand thinning to guide human workers to leave an exact number of fruits per tree. We are developing computer vision to streamline the counting of buds, lowers and fruitlets. The information from each tree is georeferenced and is uploaded to the cloud and then can be communicated to human workers to guide their work in reducing crop load to the optimum level.”

 ” The Fruitlet Growth Rate Model is a powerful model for predicting fruit set, but adoption of the model has been limited due to real or perceived time constraints and/or a measurement-intensive procedure. We have developed a simplified procedure based on sampling and weighing fruitlets from harvested spurs which generates accurate, real-time predictions of fruit set in apple that were comparable to those achieved with the FGM.“

 L. Hillmann, L. Gonzalez Nieto, T. Kon, S. Musacchi, T. Robinson, S. Serra, and T. Einhorn 

Read full article here, Fruit Quarterly (New York State Horticultural Society), Volume 30, Number 2, Summer 2022.

“Are we finally starting to see the adoption of labor-saving robots in agriculture? The short and unfulfilling summary answer is “It depends”. Undeniably, we are seeing clear signs of progress yet, simultaneously, we see clear signs of more progress needed.”

https://www.forbes.com/sites/themixingbowl/2022/10/15/crop-robotics-2022-beyond-the-valley-of-death/?sh=31ed82913816

Elizabeth Higgins, CCE ENYCHP

Reprinted with permission from TREE FRUIT NEWS, July 2022, Volume 10, Issue 4. Cornell Cooperative Extension Eastern NY Commercial Horticulture Program

Are you concerned about crop load management on your farm?
Industry has taken note and you may have more tools for making
management decisions in the future. “One of the challenges
expressed by growers is that there still is a lot of manual time
measuring and counting blossoms, fruitlets and apples, which is not only time-consuming, but it is subject to inconsistencies and
different views depending on the staff input,” said Jenny Lemieux,
CEO of Vivid Machines, one of three companies trialing precision
mapping and remote sensing tools this summer in New York. In
addition to Vivid Machines, Farm Vision and Fruit Scout are also
conducting on-farm trials.

Vivid Machines, founded in Toronto in 2020, has developed a system they call “X-Vision” which captures the quantity and quality of fruit crops from blossom to harvest. The X-Vision system has three components: a high-speed multispectral camera with a vehicle mounted housing system, a camera control and real-time analytics app, and a cloud-based analytics platform. Mounted on a tractor or ATV, the camera captures images as it moves through the row, and the data can be viewed in real time via mobile device. The X-Vision system can get accurate crop counts moving at a speed of up to 7 miles per hour, according to Vivid Machines CEO Jenny Lemieux. The system can examine trees, review blossom clusters, and measure apples, Lemieux said in a company press release. “Growers can see this information and filter the data by variety, block, date, and other factors to get a very granular view of their orchards and how they may change over time.” Vivid’s first paid trials started this season, with six growers in Ontario and New York. According to Produce News United Apple is one of the New York growers in a beta test.

Farm Vision Technologies, founded in Minnesota in 2017, has been testing and refining a handheld crop load management tool for the past few years. It is now commercially available to growers, said CEO and co-founder Patrick Plonski in an article in Good Fruit Grower. The handheld Farm Vision tool contains a Samsung phone with computer vision software, attached to a more sensitive GPS sensor, he said. We view it as the simplest possible system that can get good accuracy.” For thinning decisions, the grower marks off a section of about five trees, or roughly 15 feet long. The grower then faces the canopy, pushes record and moves the camera in an up-and down motion while walking along the row sample. It takes about a minute to get the data needed to use the fruitlet growth model. For estimating harvest yield, the grower faces the camera toward the fruiting wall at about eye level, so the whole tree is in view, pushes record and walks or drives the length of the row. If the unit is mounted on a vehicle, speeds of up to 10 miles per hour work fine, depending on the terrain and vehicle suspension. Anna Wallis of Michigan State and Craig Kahlke of the Lake Ontario Fruit Team are working with Farm Vision Technologies on on-farm trials.

The final company is FruitScout, which launched in 2021 with a
handful of pilot customers and plans a wider rollout later this year
and next. Like Farm Vision Technologies, FruitScout uses a
smartphone with an app. The FruitScout app guides users as they
walk down an orchard row, taking a picture of each tree. How many trees should be sampled to get a representative sample depends on variety. According to the company highly variable Honeycrisp may need 15 percent of the block sampled, while Gala just needs 5 percent, but the company is fine-tuning these recommendations based on field trials according to an article in Good Fruit Grower. From the images collected, the technology counts buds, then blooms, and finally fruitlets to help growers optimize crop load management strategies. Growers set targets in the app, and Fruit Scout’s dashboard tells them how close they are through each step of the season. It also suggests a target fruit count based on the size of the trunk. The Lake Ontario Fruit Team is also working with FruitScout on on-farm trials and FruitScout is currently commercially available to growers.

You can learn more about both Farm Vision and FruitScout at the
Lake Ontario Fruit tour on August 9, 2022 in Orleans County. For
more information and a registration link, go to: lof.cce.cornell.edu/
event.php?id=1669.

Company websites

• Farm Vision Technologies https://www.farm-vision.com/
• Fruit Scout https://fruitscout.ai/
• Vivid Machines https://www.vivid-machines.com/

Recent Articles with More Information

Produce News (May 3, 2022) “Favorable weather, new technologies
open season for United Apple” https://theproducenews.com/apples/
favorable-weather-new-technologies-open-season-united-apple

Tom Karst (May 5, 2022) “With a bigger crop expected this year,
technology aids New York apple grower” The Packer https://
www.thepacker.com/news/packer-tech/bigger-crop-expected-yeartechnology-aids-new-york-apple-grower

Matt Milkovich (March 21, 2022) “A Vision in Hand” Good Fruit
Grower https://www.goodfruit.com/a-vision-in-hand/

Mat Milkovich (March 21, 2022) “Computer eyes” Good Fruit Grower
https://www.goodfruit.com/computer-eyes/

Kate Pregnaman (March 21, 2022) “Phoning in Precision” Good Fruit Grower https://www.goodfruit.com/phoning-in-precision/

University research and R&D from ag tech companies converge on the practice of precision crop load management…

Optimized crop load delivers optimum profitability. 

Even the researchers and extension specialists who have promoted precision crop load management for the past decade agree that is far easier said than done.

“To do that, we’ve developed manual approaches that are time-consuming, and no one likes to do them,” said Terence Robinson, applied fruit crop physiologist at Cornell University. “Growers love the information but hate to do it for their farm.”

Read more at goodfruit.com

Cornell University tree fruit physiologist Terence Robinson said precision crop load management is critical to orchard profitability, and he hopes to see developing technology that will eventually help growers do it on a tree-by-tree basis.

Peru, New York; February 11, 2022  The 2021 results of precision apple orchard management research funded by the Northern New York Agricultural Development Program are now posted under the Research: Horticulture and Local Foods tab at nnyagdev.org (see About Us: NNYADP Projects tab).

The research, aimed at fully understanding how to best incorporate the use of computer-based fruit physiology modeling into timing orchard thinning practices to achieve optimal crop load and quality, includes data on the use of alternative thinning products and evaluates the economic impact. Read more here at Northern New York Agricultural Development Program…

Basedow will present the results of these in-orchard thinning trials in more detail as part of a “What’s New in Crop Load Management” webinar via Zoom from 1:30 to 4:45 pm on March 18, 2022. To register, go here…