Agricultural management recommendations based on blended model

1. A computer-implemented method, comprising:

receiving, using one or more computing devices, a request for a suggested distribution rate of a particular field-distributed commodity in a particular geographical area;

determining, using the one or more computing devices, two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area, each rate model including a numeric distribution, wherein one rate model of the two or more rate models is a user-tolerance model for application of the particular field-distributed commodity in the particular geographical area that includes a lower bound, and upper bound and a distribution between the lower bound and the upper bound;

determining, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area by performing Bayesian updating where the user-tolerance model is treated as a prior distribution and distributions for each of the other rate models of the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area are treated as input data in the Bayesian updating;

providing, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area in response to the received request.

2. The method of claim 1 , further comprising:

causing distribution of the particular field-distributed commodity in the particular geographical area based on the suggested distribution rate of the particular field-distributed commodity in the particular geographical area.

3. The method of claim 1 , further comprising:

determining the numeric distribution of each model in the two or more rate models based on confidence in the rate model, with a wider distribution being associated with a lower confidence and a narrower distribution being associated with a higher confidence.

4. The method of claim 1 , wherein receiving the request for the suggested distribution rate of the particular field-distributed commodity in the particular geographical area comprises receiving the request for the suggested rate for the particular geographical area for a field-distributed commodity selected from a list of field-distributed commodities comprising: nitrogen, potassium, phosphorus, seeds, sulfur, calcium, magnesium, copper, zinc, boron, molybdenum, iron, and manganese.

5. The method of claim 1 , wherein determining, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area by performing Bayesian updating, which comprises determining a suggested rate distribution model for distribution of the particular field-distributed commodity in the particular geographical area that is zero below the lower bound of the user-tolerance model and zero above the upper bound of the user-tolerance model.

6. The method of claim 1 , wherein a rate model in the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area is selected from the list consisting of a process model, an observational model, an Iowa State maximum return to nitrogen model, and a pre-sidedress soil nitrate test.

7. The method of claim 1 , further comprising determining the user-tolerance model based on the lower bound of the user-tolerance model, the upper bound of the user-tolerance model, and an expected value of the user-tolerance model.

8. The method of claim 7 , wherein determining the user-tolerance model comprises determining a rescaled beta distribution based on lower bound of the user-tolerance model, the upper bound of the user-tolerance model, and the expected value of the user-tolerance model.

9. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause performance of a method comprising the steps of:

receiving, using the one or more computing devices, a request for a suggested distribution rate of a particular field-distributed commodity in a particular geographical area;

determining, using the one or more computing devices, two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area, each rate model including a numeric distribution, wherein one rate model of the two or more rate models is a user-tolerance model for application of the particular field-distributed commodity in the particular geographical area that includes a lower bound, and upper bound and a distribution between the lower bound and the upper bound;

determining, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area by performing Bayesian updating with the user-tolerance model treated as a prior distribution and distributions for each of the other rate models of the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area are treated as input data in the Bayesian updating;

providing, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area in response to the received request.

10. The one or more non-transitory storage media of claim 9 , the steps further comprising:

causing distribution of the particular field-distributed commodity in the particular geographical area based on the suggested distribution rate of the particular field-distributed commodity in the particular geographical area.

11. The one or more non-transitory storage media of claim 9 , the steps further comprising:

determining the numeric distribution of each model in the two or more rate models based on confidence in the rate model, with a wider distribution being associated with a lower confidence and a narrower distribution being associated with a higher confidence.

12. The one or more non-transitory storage media of claim 9 , wherein receiving the request for the suggested distribution rate of the particular field-distributed commodity in the particular geographical area comprises receiving the request for the suggested rate for the particular geographical area for a field-distributed commodity selected from a list of field-distributed commodities comprising: nitrogen, potassium, phosphorus, seeds, sulfur, calcium, magnesium, copper, zinc, boron, molybdenum, iron, and manganese.

13. The one or more non-transitory storage media of claim 9 , wherein determining, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area by performing Bayesian updating, which comprises determining a suggested rate distribution model for distribution of the particular field-distributed commodity in the particular geographical area that is zero below the lower bound of the user-tolerance model and zero above the upper bound of the user-tolerance model.

14. The one or more non-transitory storage media of claim 9 , wherein a rate model in the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area is selected from the list consisting of a process model, an observational model, an Iowa State maximum return to nitrogen model, and a pre-sidedress soil nitrate test.

15. The one or more non-transitory storage media of claim 9 , the steps further comprising:

determining the user-tolerance model based on the lower bound of the user-tolerance model, the upper bound of the user-tolerance model, and an expected value of the user-tolerance model.

16. The one or more non-transitory storage media of claim 15 , wherein determining the user-tolerance model comprises determining a rescaled beta distribution based on lower bound of the user-tolerance model, the upper bound of the user-tolerance model, and the expected value of the user-tolerance model.

17. A system, comprising one or more computing devices containing instructions, which, when executed, cause performance of the steps:

receiving, using one or more computing devices, a request for a suggested distribution rate of a particular field-distributed commodity in a particular geographical area;

determining, using the one or more computing devices, two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area, each rate model including a numeric distribution, wherein one rate model of the two or more rate models is a user-tolerance model for application of the particular field-distributed commodity in the particular geographical area that includes a lower bound, and upper bound and a distribution between the lower bound and the upper bound;

determining, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area by performing Bayesian updating with the user-tolerance model treated as a prior distribution and distributions for each of the other rate models of the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area are treated as input data in the Bayesian updating;

providing, using the one or more computing devices, the suggested distribution rate of the particular field-distributed commodity in the particular geographical area in response to the received request.

18. The system of claim 17 , the steps further comprising:

causing distribution of the particular field-distributed commodity in the particular geographical area based on the suggested distribution rate of the particular field-distributed commodity in the particular geographical area.

19. The system of claim 17 , the steps further comprising:

determining the numeric distribution of each model in the two or more rate models based on confidence in the rate model, with a wider distribution being associated with a lower confidence and a narrower distribution being associated with a higher confidence.

20. The system of claim 17 , wherein receiving the request for the suggested distribution rate of the particular field-distributed commodity in the particular geographical area comprises receiving the request for the suggested rate for the particular geographical area for a field-distributed commodity selected from a list of field-distributed commodities comprising: nitrogen, potassium, phosphorus, seeds, sulfur, calcium, magnesium, copper, zinc, boron, molybdenum, iron, and manganese.