Assimilating a soil sample into a digital nutrient model
In an embodiment, agricultural intelligence computer system stores a digital model of nutrient content in soil which includes a plurality of values and expressions that define transformations of or relationships between the values and produce estimates of nutrient content values in soil. The agricultural intelligence computer receives nutrient content measurement values for a particular field at a particular time. The agricultural intelligence computer system uses the digital model of nutrient content to compute a nutrient content value for the particular field at the particular time. The agricultural intelligence computer system identifies a modeling uncertainty corresponding to the computed nutrient content value and a measurement uncertainty corresponding to the received measurement values. Based on the identified uncertainties, the modeled nutrient content value, and the received measurement values, the agricultural intelligence computer system computes an assimilated nutrient content value.
1. A computer-implemented method comprising:
storing, in digital memory of a computer system, a digital model of one or more properties of soil of one or more fields over a particular period of time;
receiving, at the computer system over one or more networks from a client computing device, one or more digital measurement values specifying measurements of one or more properties of soil at a particular field of the one or more fields at a particular time within the particular period of time;
identifying a modeled property value representing an estimate of the one or more properties of the soil at the particular field at the particular time;
identifying one or more parameter uncertainties in one or more parameters of the digital model;
perturbing the one or more parameters based on the one or more parameter uncertainties to produce one or more perturbed modeling results;
identifying, based, at least in part, on the one or more perturbed modeling results, a modeling uncertainty value for the modeled property value of the digital model wherein the modeling uncertainty value represents a magnitude of error in the digital model;
generating and displaying, based, at least in part, on the modeling uncertainty value and the one or more digital measurement values, an assimilated property value representing an improved estimate of the one or more properties of the soil at the particular field at the particular time.
2. The computer-implemented method of claim 1 , further comprising:
calibrating one or more parameters of the digital model to create a calibrated model of one or more properties of soil based on the assimilated property value.
3. The computer-implemented method of claim 1 , further comprising:
generating a plurality of combinations of a plurality of perturbed parameters from the one or more parameters and the one or more parameter uncertainties;
for each combination of perturbed parameters, computing the one or more properties of the soil from the digital model with the perturbed parameters;
identifying the modeling uncertainty value for the digital model based, at least in part, on the computed one or more properties of the soil for each combination of perturbed parameters.
4. The computer-implemented method of claim 3 , further comprising:
receiving, for a plurality of fields, field data comprising a plurality of values representing crop data, soil data, and weather data for the plurality of fields;
computing, for each combination of perturbed parameters, for each field of the plurality of fields, the one or more properties of the soil from the digital model;
computing, for each field of the plurality of fields, a sensitivity of the digital model to perturbations of the one or more parameters;
computing, based, at least in part, on the sensitivity of the digital model to perturbations of the one or more parameters for each field of the plurality of fields and the received field data for the plurality of fields, a relationship between sensitivity of the digital model to perturbations of the one or more parameters and one or more values of the plurality of values representing crop data, soil data, and weather data for the plurality of fields;
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
computing, for the particular field, a particular sensitivity of the digital model to perturbations of the one or more parameters based, at least in part, on the field data and the relationship between sensitivity of the digital model and the one or more values of the plurality of values;
computing, for the particular field, the modeling uncertainty value for the digital model based, at least in part, on the particular sensitivity of the digital model and the one or more parameter uncertainties.
5. The method of claim 1 further comprising:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
creating one or more stabilizer recommendations based, at least in part, on the assimilated property value and the plurality of values representing crop data, soil data, and weather data for one or more fields;
using a mobile device interface module, sending the one or more stabilizer recommendations to a field manager computing device.
6. The method of claim 1 , further comprising:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
creating one or more nutrient recommendations;
generating instructions for an application controller based on the one or more nutrient recommendations and sending the instructions to the application controller;
wherein the instructions cause the application controller to control an operating parameter of an agricultural vehicle to implement the one or more nutrient recommendations.
7. The method of claim 1 , further comprising:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
identifying one or more input uncertainties associated with one or more values of the plurality of values representing crop data, soil data, and weather data for the particular field;
identifying the modeling uncertainty value for the digital model based, at least in part, on the one or more input uncertainties.
8. The method of claim 7 , further comprising:
wherein the weather data for the particular field includes radar based precipitation estimates;
computing a precipitation estimate error for the radar based precipitation estimates;
identifying the one or more input uncertainties based, at least in part, on the precipitation estimate error.
9. The computer-implemented method of claim 1 , further comprising:
identifying one or more modeled property values representing one or more estimates of the one or more properties of the soil at one or more locations across the particular field at the particular time;
identifying one or more modeling uncertainty values for the one or more modeled property values for the one or more locations across the particular field;
identifying, based, at least in part, on the one or more modeling uncertainty values for the one or more locations, one or more different modeling uncertainty values for one or more different locations;
generating and displaying, based, at least in part, on the one or more different modeling uncertainty values, the assimilated property value.
10. A data processing system comprising:
one or more processors;
a memory storing instructions which, when executed by the or more processors, cause:
storing a digital model of one or more properties of soil of one or more fields over a particular period of time;
receiving, from a client computing device, one or more digital measurement values specifying measurements of one or more properties of soil at a particular field of the one or more fields at a particular time within the particular period of time;
identifying a modeled property value representing an estimate of the one or more properties of the soil at the particular field at the particular time;
identifying one or more parameter uncertainties in one or more parameters of the digital model;
perturbing the one or more parameters based on the one or more parameter uncertainties to produce one or more perturbed modeling results;
identifying, based, at least in part, on the one or more perturbed modeling results, a modeling uncertainty value for the modeled property value of the digital model wherein the modeling uncertainty value represents a magnitude of error in the digital model;
generating and displaying, based, at least in part, on the modeling uncertainty value and the one or more digital measurement values, an assimilated property value representing an improved estimate of the one or more properties of the soil at the particular field at the particular time.
11. The data processing system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause:
calibrating one or more parameters of the digital model to create a calibrated model of one or more properties of soil based on the assimilated property value.
12. The data processing system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause:
generating a plurality of combinations of a plurality of perturbed parameters from the one or more parameters and the one or more parameter uncertainties;
for each combination of perturbed parameters, computing the one or more properties of the soil from the digital model with the perturbed parameters;
identifying the modeling uncertainty value for the digital model based, at least in part, on the computed one or more properties of the soil for each combination of perturbed parameters.
13. The data processing system of claim 12 , wherein the instructions, when executed by the one or more processors, further cause:
receiving, for a plurality of fields, field data comprising a plurality of values representing crop data, soil data, and weather data for the plurality of fields;
computing, for each combination of perturbed parameters, for each field of the plurality of fields, the one or more properties of the soil from the digital model;
computing, for each field of the plurality of fields, a sensitivity of the digital model to perturbations of the one or more parameters;
computing, based, at least in part, on the sensitivity of the digital model to perturbations of the one or more parameters for each field of the plurality of fields and the received field data for the plurality of fields, a relationship between sensitivity of the digital model to perturbations of the one or more parameters and one or more values of the plurality of values representing crop data, soil data, and weather data for the plurality of fields;
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
computing, for the particular field, a particular sensitivity of the digital model to perturbations of the one or more parameters based, at least in part, on the field data and the relationship between sensitivity of the digital model and the one or more values of the plurality of values;
computing, for the particular field, the modeling uncertainty value for the digital model based, at least in part, on the particular sensitivity of the digital model and the one or more parameter uncertainties.
14. The data processing system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
creating one or more stabilizer recommendations based, at least in part, on the assimilated property value and the plurality of values representing crop data, soil data, and weather data for one or more fields;
using a mobile device interface module, sending the one or more stabilizer recommendations to a field manager computing device.
15. The data processing system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
creating one or more nutrient recommendations;
generating instructions for an application controller based on the one or more nutrient recommendations and sending the instructions to the application controller;
wherein the instructions cause the application controller to control an operating parameter of an agricultural vehicle to implement the one or more nutrient recommendations.
16. The data processing system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause:
receiving, for the particular field, field data comprising a plurality of values representing crop data, soil data, and weather data for the particular field;
identifying one or more input uncertainties associated with one or more values of the plurality of values representing crop data, soil data, and weather data for the particular field;
identifying the modeling uncertainty value for the digital model based, at least in part, on the one or more input uncertainties.
17. The data processing system of claim 16 , wherein the instructions, when executed by the one or more processors, further cause:
wherein the weather data for the particular field includes radar based precipitation estimates;
computing a precipitation estimate error for the radar based precipitation estimates;
identifying the one or more input uncertainties based, at least in part, on the precipitation estimate error.
18. The data processing system of claim 10 , wherein the instructions when executed by the one or more processors, further cause:
identifying one or more modeled property values representing one or more estimates of the one or more properties of the soil at one or more locations across the particular field at the particular time;
identifying one or more modeling uncertainty values for the one or more modeled property values for the one or more locations across the particular field;
identifying, based, at least in part, on the one or more modeling uncertainty values for the one or more locations, one or more different modeling uncertainty values for one or more different locations;
generating and displaying, based, at least in part, on the one or more different modeling uncertainty values, the assimilated property value.
19. A computer-implemented method comprising:
storing, in digital memory of a computer system, a digital model of one or more properties of soil of one or more fields over a particular period of time;
receiving, at the computer system over one or more networks from a client computing device, one or more digital measurement values specifying measurements of one or more properties of soil at a particular field of the one or more fields at a particular time within the particular period of time;
identifying one or more modeled property values representing one or more estimates of the one or more properties of the soil at one or more locations across the particular field at the particular time;
identifying one or more modeling uncertainty values for the one or more modeled property values for the one or more locations across the particular field, wherein the one or more modeling uncertainty values represent one or more magnitudes of errors in the digital model;
identifying, based, at least in part, on the one or more modeling uncertainty values for the one or more locations, one or more different modeling uncertainty values for one or more different locations;
generating and displaying, based, at least in part, on the one or more different modeling uncertainty values and the one or more digital measurement values, an assimilated property value representing an improved estimate of the one or more properties of the soil at the particular field at the particular time.