Industries / Food, farming and forestry / Agriculture and farming / Produce packing
Receiving from the field
Bringing the harvest in: moving produce from the field in bins, deciding whether a load is ripe and sound enough to accept, and emptying it onto the packing line without bruising it.
5
Milestones achieved, from 1925 to 2017.
1
To watch for: announced, not yet confirmed outside.
2
Open deliverables. Nobody has shipped them.
The road
AchievedWatch forOpen
Achieved
1925
A gauge for ripeness
Joseph R. Magness and George F. Taylor of the US Department of Agriculture published plans for a cheap, portable pressure tester: a spring-loaded plunger pushed into the peeled flesh of a fruit to a set depth, with the force read in pounds. They wrote that judging ripeness by "the unsupported judgment of an individual" had led to rejected shipments and price disputes. By 1963 USDA's marketing service was making attachments for the Magness-Taylor tester so that fruit inspectors could measure firmness without cutting the fruit, and testers reading to 30 pounds were the ones used for apples.
LessonDisputes over a load shrink once buyer and seller read the same number.
Credit
J. R. Magness and G. F. Taylor, USDA Bureau of Plant Industry; their circular credits the idea of a mechanical tester to O. M. Morris of the Washington Agricultural Experiment Station and an earlier pear tester to A. E. Murneek in Oregon
1958
Bins replace field boxes
A pallet box, or bulk bin, is a large wooden box for carrying fruit from the orchard that is moved by forklift. A USDA study drawing on Washington orchards and packhouses found that fruit in pallet boxes had fewer bruises than fruit in field boxes, cooled as well or better, and fitted about 20% more fruit into the same cold room, and it put the saving at $70 to $85 per 1,000 standard boxes' worth of fruit. The change came partly because packers were moving from wooden shipping boxes to fibreboard cartons, so the wooden boxes no longer doubled as field boxes.
LessonA change in the shipping carton changed how fruit came in from the field.
Credit
Joseph F. Herrick, S. W. McBirney and Earl W. Carlsen, USDA Agricultural Marketing Service and Agricultural Research Service
1966
Bins emptied under water
Apples float, so packhouses empty bins by lowering them into a tank and letting the fruit float out, instead of tipping them onto a belt. A USDA and Michigan State University study of handling apples in water called the flotation dumpers already in commercial use adequate. It also found that water pressure forced water into submerged apples and damaged tissue, and judged 6 feet (about 1.8 m) of depth for up to 15 minutes to be safe.
LessonThe water that cushions fruit can also push water into it.
Credit
D. H. Dewey, B. A. Stout and colleagues, USDA Agricultural Research Service and Michigan State University
1997
A sensor ball maps drops
An instrumented sphere is a ball about the size of a fruit that carries an accelerometer and a recorder. Sent down a packing line with the fruit, it logs every impact. In seven grapefruit packing sheds in Texas, Krista C. Shellie found that four steps gave the most high impacts: the sizer, hand separation at the grading table, the dump from the harvest bin onto the line, and the drop into the collection bin at the end. She found the severity of impacts comparable to that reported for 39 Florida packinghouses.
Credit
Krista C. Shellie; earlier sphere studies by W. M. Miller and C. Wagner (Florida citrus, 1991) and others
2017
Light reads mango maturity
Dry matter, the share of a fruit that is not water, tracks its starch and sugar and so how it will taste once ripe. A Hort Innovation project in Australia, run from 2016 to 2017, trained mango growers to measure it with Felix F-750 meters, handheld near-infrared scanners that read the fruit without cutting it. It visited 61 farms in Queensland, New South Wales and the Northern Territory, made more than 6,000 scans across five varieties, and found the meters useful for timing harvest "in conjunction with other indicators". The Australian Mango Industry Association has since set dry matter specifications for eating quality.
LessonThe meter needed a calibration for each variety, and it was used beside other maturity checks, not in place of them.
Credit
Hort Innovation, which funded the project; Kerry Walsh of CQUniversity Australia, who leads later work combining the meters with satellite images
Watch for
AI berry checks at intake
The berry company Wish Farms says that Clarifresh's AI platform, which finds defects in images of the fruit, has cut its berry inspection times by 70% and its rejections of produce by up to 50%.
Achieved whenan outside party compares the software's defect calls with trained inspectors' calls on the same lots, publishes the agreement rate, and measures the time saved over a season.
Claimed by
Wish Farms and Clarifresh, September 2026
Open
01
Bin photos against the grader
A public test of whether photos of the top of a bin, taken at receiving, predict what the packing line's optical grader later finds in the whole bin: the spread of sizes, the colour and the defects. Photograph each bin, run it through the grader on its own, and release the images, the grader's results for each bin and an open sizing model.
The briefCredit · unclaimed02
A clock on every bin
A season-long, public record of how long harvested produce waits before it is cooled. Print a QR code on each bin or pallet tag, scan it with a phone when the crop is picked, when it reaches the packhouse dock and when it goes into the cooler, and take a probe reading of pulp temperature at the dock. Hold samples from bins with short and long waits in a cold room and record how much is still saleable after set days.
The briefCredit · unclaimed
Open 01 · the brief
Bin photos against the grader
The first to publish is credited on this line, and the deliverable moves from Open to Achieved.
What to build
A public test of whether photos of the top of a bin, taken at receiving, predict what the packing line's optical grader later finds in the whole bin: the spread of sizes, the colour and the defects. Photograph each bin, run it through the grader on its own, and release the images, the grader's results for each bin and an open sizing model.
Why it is still open
Sizing fruit from bin photos is already sold. Hectre's Spectre app sizes and colours fruit from iPad or iPhone photos and is meant for use "in the packhouse for storage, packing and sales decisions". A photo shows only the top layer, and searches in November 2026 found no outside test of how well the top layer stands for the bin, and no accuracy figure except the seller's own.
Built with what exists
Phones or a fixed camera over the receiving line; the packhouse's existing optical grader; an open object-detection or segmentation model such as Ultralytics YOLO or Meta's Segment Anything 2 for finding and measuring each visible fruit; Python for the comparison; any commercial bin-sizing app the packhouse already uses, tested the same way.
First step
Agree with one packhouse to run 20 bins one at a time through its grader at the end of a shift, photographing the top of each bin at receiving.
Done looks like
At least 300 bins of two varieties, each with its photos and grader results, published; for each bin, the error between the photo estimate and the grader in the share of fruit in each size class, reported as a mean absolute error in percentage points for the open model and for any app tested.
Open 02 · the brief
A clock on every bin
The first to publish is credited on this line, and the deliverable moves from Open to Achieved.
What to build
A season-long, public record of how long harvested produce waits before it is cooled. Print a QR code on each bin or pallet tag, scan it with a phone when the crop is picked, when it reaches the packhouse dock and when it goes into the cooler, and take a probe reading of pulp temperature at the dock. Hold samples from bins with short and long waits in a cold room and record how much is still saleable after set days.
Why it is still open
The rule growers work to rests on old curves. A May 2025 post by the Cal Poly Strawberry Center repeats the 1996 University of California advice that strawberries be cooled within one hour of harvest, and reads from the 1996 curve that losses grow by about 8 to 10% for each hour after that. It adds that growers often speak of a two-hour window and that keeping pick-to-cool times under an hour is hard at peak harvest. Searches in November 2026 found measured waits only in research trials of particular loads, and no public season-long record across farms.
Built with what exists
Printed QR bin tags; a phone form app such as ODK Collect or KoboToolbox, which time-stamps each scan; a food probe thermometer; two or three small temperature loggers riding in bins as checks; a walk-in cooler for the shelf-life samples; Python or R for the analysis.
First step
Tag one day's strawberry harvest at one farm and time every pallet from picking to the cooler.
Done looks like
At least 2,000 bins or pallets from at least three farms and two crops, each with its pick, dock and cooler times and dock pulp temperature, published as an open dataset; the share of bins cooled within one hour and within two; and, for 200 or more held samples, saleable fruit after set days plotted against the delay and compared with the 1996 curve.