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 for one or more properties of one or more fields over a period of time;
receiving one or more digital measurement values specifying measurement of one or more properties at a particular field of the one or more fields at a particular time within the period of time;
identifying, using the digital model and the one or more digital measurement values, a modeled property value representing a first estimate of the one or more properties of the particular field at the particular time;
identifying one or more input uncertainties associated with the one or more digital measurement values;
producing one or more perturbed modeling results by perturbing the one or more digital measurement values;
identifying, based at least in part on the one or more input uncertainties and the one or more perturbed modeling results, an uncertainty value for the modeled property value, wherein the uncertainty value represents a magnitude of error in the digital model; and
generating, based at least in part on the uncertainty value, an assimilated property value representing a second estimate of the one or more properties of the particular field at the particular time.
2. The computer-implemented method of claim 1 , further comprising displaying the assimilated property value.
3. The computer-implemented method of claim 1 , further comprising:
identifying one or more parameter uncertainties in one or more parameters of the digital model; and
wherein identifying the uncertainty value includes identifying the uncertainty value for the modeled property value further based at least in part on the one or more parameter uncertainties.
4. The computer-implemented method of claim 3 , further comprising:
producing the one or more perturbed modeling results by further perturbing the one or more parameters of the digital model based on the one or more parameter uncertainties.
5. The computer-implemented method of claim 1 , further comprising:
identifying one or more structural uncertainties associated with physical interactions between one or more field properties and the modeled property value; and
wherein identifying the uncertainty value includes identifying the uncertainty value for the modeled property value further based at least in part on the one or more structural uncertainties.
6. The computer-implemented method of claim 1 , further comprising calibrating, using the assimilated property value, the digital model to create a calibrated model of the one or more properties of one or more fields.
7. The computer-implemented method of claim 6 , further comprising identifying a set of perturbations of one or more of parameters or inputs to the digital model, the set of perturbations associated with a modeled property value that is closest to the assimilated property value.
8. The computer-implemented method of claim 7 , further comprising calibrating the digital model to the identified set of perturbations.
9. 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 for one or more properties of one or more fields over a period of time;
receiving one or more digital measurement values specifying measurement of one or more properties at a particular field of the one or more fields at a particular time within the period of time;
identifying, using the digital model and the one or more digital measure values, a modeled property value representing a first estimate of the one or more properties of the particular field at the particular time;
identifying one or more input uncertainties associated with the one or more digital measurement values;
producing one or more perturbed modeling results by perturbing the one or more digital measurement values;
identifying, based at least in part on the one or more input uncertainties and the one or more perturbed modeling results, an uncertainty value for the modeled property value, wherein the uncertainty value represents a magnitude of error in the digital model; and
generating, based at least in part on the uncertainty value, an assimilated property value representing a second estimate of the one or more properties of the particular field at the particular time.
10. The data processing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause displaying the assimilated property value.
11. The data processing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause:
identifying one or more parameter uncertainties in one or more parameters of the digital model; and
identifying the uncertainty value for the modeled property value further based on the one or more parameter uncertainties.
12. The data processing system of claim 11 , wherein the instructions, when executed by the one or more processors, further cause:
producing the one or more perturbed modeling results by further perturbing the one or more parameters of the digital model based on the one or more parameter uncertainties.
13. The data processing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause:
identifying one or more structural uncertainties associated with physical interactions between one or more field properties and the modeled property value; and
identifying the uncertainty value for the modeled property value further based on the one or more structural uncertainties.
14. The data processing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause calibrating, using the assimilated property value, the digital model to create a calibrated model of the one or more properties of one or more fields.
15. The data processing system of claim 14 , wherein the instructions, when executed by the one or more processors, further cause identifying a set of perturbations of one or more of parameters or inputs to the digital model, the set of perturbations associated with a modeled property value that is closest to the assimilated property value.
16. The data processing system of claim 15 , wherein the instructions, when executed by the one or more processors, further cause calibrating the digital model to the identified set of perturbations.