'Fun' with Outfield 2024

 My second year working with Oli Hilbourne and Jim McDougall from Outfield using my DJI Air 2S UAV (drone) to do blossom density, fruit variability, and – although not officially sanctioned – yield estimate ‘heat’ maps. (See my 2023 Outfield post.) My intent here is to just highlight some of my observations using this particular PACMAN (Precision Apple Cropload MANagement) tool in 2024. Although, I did have a specific applied research objective too, that is/was to compare the Outfield product to Vivid-Machines results, who I also worked with in 2024, but that will be a separate post.

So, regarding Outfield:

• I/we actually mapped a total of thirteen different apple blocks across five orchards in three different states (MA, NJ, and NY). Wow. Not all orchard blocks were mapped for all three Outfield products – blossom density, fruit variability, and yield estimates – but still, wow. Going forward, however, I am not going to bring up yield estimates because Outfield is not ready to roll this feature out yet. It’s kind of in Beta testing still, TBD?
• Two orchards in Massachusetts, the UMass Orchard in Belchertown and Tougas Family Farm in Northboro were included in flyovers and mapping. I also had the opportunity to demonstrate Outfield at a meeting of the New Jersey State Horticultural Society at Wightman’s Orchard in Morristown, NJ in June. See this Fruit Notes article. Plus in August did a demo at Crist Brothers Orchards in Walden, NY and Once Munsee Orchard in Wallkill, NY.
• When I say we, I mean I had help, Liam Ouelette who was a UMass CAFE summer scholar I was lucky to have help me out. Brain works much faster in young folks (Liam) than old folks (me), and he was a natural at flying the drone (Figure 1). As part of his summer scholar work, Liam produced a nice poster (Figure 2).
• In general, using the drone along with the Outfield Dashboard and Litchi app was pretty easy. File management got a bit tricky, however,  as the number of blocks we flew over increased. Flights typically averaged five minutes or so to complete, but it depended a bit on block size, which ranged from one-half an acre (< 3 minutes) to approximately nine acres (10+ minutes). One notable ‘incident’ occurred when Jon did not check a particular block perimeter closely, so the drone and an oak tree had a ‘meeting’ which resulted in the drone getting stuck about 30 feet up in the tree canopy. Fortunately, someone with an adept throwing arm was able to knock it out of the tree using – what else? – apples as the dislodging projectile. The drone was undamaged, amazing.
• Uploading picture files taken by the drone during the largely hands-off, programmed block flyovers resulted – within 24 hours usually – the Outfield ‘heat’ maps in their Dashboard. Examples of bloom density and fruit variability maps, as well as sample region/image locations are pictured in Figures 3 - 6. They are pretty self-explanatory.

OK, the “so what?”

• As I alluded, I was hoping to eventually compare the Outfield ‘heat’ maps to those produced by Vivid-Machines. I will have to dig into that more extensively, but it’s kind of like comparing apples to oranges so I will have to re-think that.
• Anyone can do this, i.e., buy a $1,000 drone, get your FAA Part 107 license (preferably), pay Outfield for their Dashboard and flight plans (rack rate circa $100 an acre in 2024), outline your orchard blocks of interest, and fly and make maps until your heart's content. Typically during full bloom (blossom density map), then once the fruits reach one inch diameter in mid-late June (fruit variability map), again in July, again in August (fruit variability maps).
• What’s actionable? Ideally variable rate sprayer to apply bloom and fruitlet thinners, or maybe you can just have the map in your tractor and speed up/slow down? The whole variable rate sprayer thing is coming, trust me. Hand thinning, give a map to the crew supervisor to make sure time is well spent, hand thinning where most needed? Pre-plan harvest operations, but really need a yield estimate from Outfield for that, hint 🙂. What about variable rate ReTain spraying? What am I missing? Please leave a comment!

Figure 1 - Liam piloting drone over Royal Red Honeycrisp block at Tougas Family Farm, July 3, 2024

Figure 2 - Liam presenting poster at UMass CAFE Summer Scholar Symposium, September 9, 2024

Figure 3 - Blossom variability map from Royal Red Honeycrisp block at Tougas Family Farm, May 9, 2024

Figure 4 - Example image regions/location during bloom in 'Royal Red' Honeycrisp block at Tougas Family Farm, May 9, 2024 

Figure 5 - Fruit variability map of 'Royal Red' Honeycrisp block at Tougas Family Farm, September 7, 2024

Figure 6 - Example image regions/location pre-harvest in 'Royal Red' Honeycrisp block at Tougas Family Farm, September 7, 2024

The Fruitlet Size Distribution (FSD) Model, my 2024 experience…

As an introduction – why reinvent the wheel? – per LAURA HILLMANN AND TODD EINHORN, Michigan State University:

“Fruit set prediction models aim to produce timely estimates of fruitlet abscission after thinner applications to guide precision crop load management. The time to generate a prediction after an application is important to facilitate grower decisions to re-apply thinners while they are still efficacious, avoiding expensive hand thinning operations. The fruitlet growth rate (FGR) model, developed by Dr. Duane Greene, is a powerful tool that can accurately predict the percentage of fruitlets that will set in an orchard. Although an Excel data template and App are available to run the FGR model via computer and smartphone, respectively, adoption has been limited by the measurement-intensive procedure. A new approach, termed the ‘Fruitlet Size Distribution (FSD) Model’, described herein, was developed to produce predictions of apple fruit set comparable to the FGR model but achievable with less time investment. The principle underlying both models is the same: the relative growth rate or size of a fruitlet is compared to the most rapidly growing or largest fruitlet within the sample date to determine if it will abscise. Most predictions can be made within 8 days from thinner applications, though the duration of time depends on climatic, biological and horticultural factors. To optimize the FSD model we suggest beginning the model three days after the average fruitlet diameter of the orchard is 6 mm. Thus, the model partners well with thinning applications between bloom and 6 mm. For example, if a prediction can be achieved by 8 days, assuming an average growth of ~0.8 mm per day, then fruitlets will be ~ 12 mm if another application is needed; 12 mm fruitlets are very sensitive to many thinning chemistries.”

https://pacman.extension.org/2024/03/28/the-fruitlet-size-distribution-fsd-model-a-how-to-guide-2024-update/ Including a complete HOW-TO guide.

Let’s see if I followed the instructions?

✔ At the UMass Orchard in Belchertown, MA, in 2024 I tried the FSD model in two tall-spindle apple blocks, one Ambrosia, the other Cripps Pink ‘Maslin’ cv. Both were on G.41 rootstock. I flagged 8 representative trees in each block at bloom. 

✔ Marked five representative flowering spurs (clusters) per tree for a total of 40 clusters per block.

✔ Oh yea, I counted the total number of flower clusters on five of the marked trees, which ranged from 50 to 80 in Ambrosia, 90 to 170 (a lot) in Cripps Pink. 

✔ Over the course of three “sample” dates – May 22, 26, and 30 – in each block I collected – by either snipping, or pulling off, fruitlet stem included, see Figure ? – the fruitlets from each cluster, brought them inside, and weighed them, sitting down, nice. More on that in a minute.

✔ Data went right into the FSD Excel spreadsheet – can download from above link, have to enable Macros, it’s easier to do on a Mac than a PC, but that is another story  – and Voila! %FRUIT SET predicted in a nice chart! Figure 1 and 2.

Figure 1 - FSD prediction results for Cripps Pink

Figure 2 - FSD prediction results for Ambrosia

Humph. In terms of so “what good is it?,” if assuming a good bloom, I want the fruit set to be in the 10% range, equivalent to one apple for every two clusters? Right? That is up to you to set that target fruit set. From what I could see, we were on the right track, but I could also see for Ambrosia at least (Figure 2) it might be wise to put another chemical thinner spray on? Not sure if that happened, both blocks had a good (too many?) apples at the end. Yea, my follow through could use help. 🙂

Now for the minute I mentioned above, I was kind of impressed, particularly no measuring fruitlets in the orchard in the hot sun and bugs, just collect, and bring them into the comfort of air conditioning (no bugs if you keep the doors closed) where you individually (sitting down) throw them on an accurate scale (down to 0.01 grams accuracy), record, and hit ‘Start Calculations’ in the XLS FSD spreadsheet. Now, you can do this manually, but I had some money so I bought an Ohaus 'Scout' (STX222 AM) scale, and the USB interface, about $550. After some serious digging around in the PC (no Mac here, sorry) system and application settings, I got it to work! I had a little help from Laura in Einhorn’s MSU lab too. Put the fruitlet on scale, hit the scale enter button, and automatically record it in the spreadsheet. Figures 3 & 4. How cool! I was pretty psyched!

Figure 3 - Collected fruitlets (note with stems), scale, USB interface, and computer for fast weighing and recording of fruitlets

Figure 4 - Close up of OHAUS scale and Excel spreadsheet data entry

“Less time investment?” Yea, maybe, between collecting the fruitlets and weighing them, probably took 30 minutes. But I could do it by myself, two people not needed as with measuring and recording, so in terms of people hours, yes, definitely less. Did I mention the personal discomfort index was less too! That’s important to me… 🙂

So, I proposed MARKUSIM previously and now FSD to achieve one level – precision pruning, precision chemical thinning actually USING the FSD model, and hand thinning being other levels – of precision apple crop load management (PACMAN) for mere mortals! Me, not being one to leave it alone of course, and have to try it myself, also worked with OUTFIELD and VIVID-MACHINES in 2024, that’s upcoming. If you are thinking I will tie it all together at the end, dream on…I will leave it up to you to decide what you can do in terms of precision apple cropload management, one size does not fit all.