Machine learning in an online agricultural system

1. A method for training and applying a machine-learned model in an online agricultural system comprising:

receiving, from a first crop producer, a first request to list a first crop product within an online agricultural system, the first request identifying a reported first quality specification of the first crop product and a first crop product type and at least one of: a first quantity of the first crop product, a first crop product price, and a first location of the first crop product;

receiving, from a second crop producer, a second request to list a second crop product having the same crop product type as the first request within an online agricultural system, the second request identifying a reported second quality specification of the second crop product and at least one of: a second quantity of the second crop product, a second crop product price, and a second location of the second crop product;

generating a training set of data comprising remote sensor data corresponding to the crop product type of the first crop product and associated historic quality specification data corresponding to the crop product type of the first crop product;

training a machine-learned model configured to predict a quality specification for the first crop product based on remote sensor data corresponding to the first crop product using the training set of data;

receiving, from a first prospective acquiring entity, a third request to acquire a third crop product, the third request identifying a third crop product type, a third quantity of the third crop product, a third crop product price, a quality requirement of the third crop product, and a third location to which the third crop product is to be delivered;

in response to 1) the first quality specification failing to satisfy the quality requirement, 2) the second quality specification failing to satisfy the quality requirement, and 3) a combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product satisfying the quality requirement:

accessing remote sensing data from one or more remote sensors corresponding to the first and second locations;

applying the trained machine-learned model to the accessed remote sensing data to verify the first and second quality;

calculating a supplier trustworthiness score for the first and second producer based on a difference between the reported qualities and verified qualities; and

in response to the supplier trustworthiness score for both the first and second producers being above a threshold score, modifying an interface of a device of the first prospective acquiring entity to display the combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product.

2. The method of claim 1 , further comprising:

automatically arranging for a transfer of possession of the fourth quantity of first crop product and the fifth quantity of the second crop product crop product to the first prospective acquiring entity.

3. The method of claim 2 , wherein arranging for the transfer of possession of the fourth quantity of first crop product and the fifth quantity of the second crop product crop product to the first prospective acquiring entity comprises one of: automatically sending transportation instructions to a transportation entity, confirming that the first crop producer and the second crop product are responsible for the transfer of possession, and confirming that the first prospective acquiring entity is responsible for the transfer of possession.

4. The method of claim 3 , wherein the transportation instructions include the first location, the second location, the third location, and a delivery window.

5. The method of claim 1 , wherein the first quality specification, the second quality specification, and the quality requirement identify one or more physical or chemical attributes of a crop product comprising one or more of: a variety, a genetic trait or lack thereof, a genetic modification or lack thereof, a genomic edit or lack thereof, an epigenetic signature or lack thereof, a moisture content, a protein content, a carbohydrate content, an ash content, a fiber content, a fiber quality, a fat content, an oil content, a color, a whiteness, a weight, a transparency, a hardness, a percent chalky grains, a proportion of corneous endosperm, a presence or absence of foreign matter, a number or percentage of broken kernels, a number or percentage of kernels with stress cracks, a falling number, a farinograph, an adsorption of water, a milling degree, an immature grains, a kernel size distribution, an average grain, a length, an average grain breadth, a kernel volume, a density, an L/B ratio, a wet gluten, a sodium dodecyl, a sulfate sedimentation, toxin levels (for example, mycotoxin levels, including vomitoxin, fumonisin, ochratoxin, or aflatoxin levels), and damage levels (for example, mold, insect, heat, cold, frost or other material damage).

6. The method of claim 1 , wherein the first quality specification, the second quality specification, and the quality requirement identify one or more attributes of a production method of a crop product or an environment in which the crop product was produced comprising one or more of: a soil type, a soil chemistry, a soil structure, a climate, weather, a magnitude or frequency of weather events, a soil or air temperature, a soil or air moisture, degree days, a measure of rain, an irrigation type, a tillage frequency, a cover crop (present and/or historical), a crop rotation, organic grown, shade grown, greenhouse grown, levels and types of fertilizer use, levels and types of chemical use, levels and types of herbicide use, pesticide-free grown, levels and types of pesticides use, no-till grown, fair wage grown, a geography of production (for example, country of origin, American Viticultural Area, mountain grown), pollution-free grown, and carbon neutral grown.

7. The method of claim 1 , wherein the first quality specification, the second quality specification, and the quality requirement identify one or more attributes of how the crop product is stored comprising one or more of: a type of storage, environment conditions of the storage, a preservation type, and a length of time of storage.

8. The method of claim 1 , wherein the first quality specification, the second quality specification, and the quality requirement identify a grading or certification by an organization or agency.

9. The method of claim 1 , wherein the third crop product price is a price ladder.

10. The method of claim 9 , wherein the price ladder is a quality based price ladder.

11. The method of claim 1 , wherein the first request identifies the first location of the first crop product and wherein the second request identifies the location of the second crop product.

12. The method of claim 11 , wherein the first location and the second location comprise one or more of: a field boundary, a production location, and a storage location.

13. The method of claim 1 , wherein the first crop product and the second crop product comprise one or more of: an unprocessed crop, a crop that has not been harvested, or a crop that has been harvested.

14. The method of claim 1 , wherein the first crop product is a crop that has not been harvested.

15. The method of claim 14 , wherein one or more of the first crop product type, the first quantity of the first crop product, and the first quality specification of the first crop product is inferred from the remote sensing data.

16. The method of claim 1 , wherein the third quantity of the third crop product comprises a number of units of transportation selected from: truck loads, train car loads, and barge loads.

17. The method of claim 1 , further comprising:

displaying, by the online agricultural system within the interface of the device of the first prospective acquiring entity, an expected distribution of prices or an expected average price of the third crop product for the first prospective acquiring entity to acquire the third quantity of the third crop product.

18. The method of claim 1 , further comprising:

displaying, by the online agricultural system within the interface of the device of the first prospective acquiring entity, a distribution of geographic locations from which the third crop product is expected to be acquired for the first prospective acquiring entity to acquire the third quantity of the third crop product.

19. The method of claim 18 , wherein the interface comprises a map.

20. The method of claim 1 , wherein the first crop product type, the second crop product type, and the third crop product type are the same.

21. The method of claim 1 , wherein the first crop product type, the second crop product type, and the third crop product type are different.

22. A system for training and applying a machine-learned model in an online agricultural system comprising:

a non-transitory computer-readable storage medium storing executable instructions that, when executed, cause the system to perform steps comprising:

receiving, from a first crop producer, a first request to list a first crop product within an online agricultural system, the first request identifying a reported first quality specification of the first crop product and a first crop product type and at least one of: a first quantity of the first crop product, a first crop product price, and a first location of the first crop product;

receiving, from a second crop producer, a second request to list a second crop product having the same crop product type as the first request within an online agricultural system, the second request identifying a reported second quality specification of the second crop product and at least one of: a second quantity of the second crop product, a second crop product price, and a second location of the second crop product;

 generating a training set of data comprising remote sensor data corresponding to the crop product type of the first crop product and associated historic quality specification data corresponding to the crop product type of the first crop product;

 training a machine-learned model configured to predict a quality specification for the first crop product based on remote sensor data corresponding to the first crop product using the training set of data;

receiving, from a first prospective acquiring entity, a third request to acquire a third crop product, the third request identifying a third crop product type, a third quantity of the third crop product, a third crop product price, a quality requirement of the third crop product, and a third location to which the third crop product is to be delivered;

in response to 1) the first quality specification failing to satisfy the quality requirement, 2) the second quality specification failing to satisfy the quality requirement, and 3) a combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product satisfying the quality requirement:

accessing remote sensing data from one or more remote sensors corresponding to the first and second locations;

applying the trained machine-learned model to the accessed remote sensing data to verify the first and second quality;

calculating a supplier trustworthiness score for the first and second producer based on a difference between the reported qualities and verified qualities; and

in response to the supplier trustworthiness score for both the first and second producers being above a threshold score, modifying an interface of a device of the first prospective acquiring entity to display the combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product; and

a hardware processor configured to execute the instructions.

23. A non-transitory computer-readable storage medium storing executable instructions for training and applying a machine-learned model in an online agricultural system, the instructions, when executed by a hardware processor, configured to cause the hardware processor to perform steps comprising:

receiving, from a first crop producer, a first request to list a first crop product within an online agricultural system, the first request identifying a reported first quality specification of the first crop product and a first crop product type and at least one of: a first quantity of the first crop product, a first crop product price, and a first location of the first crop product;

receiving, from a second crop producer, a second request to list a second crop product having the same crop product type as the first request within an online agricultural system, the second request identifying a reported second quality specification of the second crop product and at least one of: a second quantity of the second crop product, a second crop product price, and a second location of the second crop product;

generating a training set of data comprising remote sensor data corresponding to the crop product type of the first crop product and associated historic quality specification data corresponding to the crop product type of the first crop product;

training a machine-learned model configured to predict a quality specification for the first crop product based on remote sensor data corresponding to the first crop product using the training set of data;

receiving, from a first prospective acquiring entity, a third request to acquire a third crop product, the third request identifying a third crop product type, a third quantity of the third crop product, a third crop product price, a quality requirement of the third crop product, and a third location to which the third crop product is to be delivered;

in response to 1) the first quality specification failing to satisfy the quality requirement, 2) the second quality specification failing to satisfy the quality requirement, and 3) a combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product satisfying the quality requirement:

accessing remote sensing data from one or more remote sensors corresponding to the first and second locations;

applying the trained machine-learned model to the accessed remote sensing data to verify the first and second quality;

calculating a supplier trustworthiness score for the first and second producer based on a difference between the reported qualities and verified qualities; and

in response to the supplier trustworthiness score for both the first and second producers being above a threshold score, modifying an interface of a device of the first prospective acquiring entity to display the combination of a fourth quantity of the first crop product and a fifth quantity of the second crop product.