Yield data calibration methods
Embodiments relate to calibrating yield data points. A calibration system receives a plurality of groups of yield data points. Each group is associated with an attribute, such as, a machine identifier, a zone identifier, a localized zone identifier, and/or a moisture identifier. The system calculates a grand aggregate yield based on the yield data points of the plurality of groups. The system calculates a group aggregate yield based on yield data points of each group. The system subtracts the group aggregate yield from each yield data point of the group producing adjusted yield data points. The system adds the grand aggregate yield to each of the adjusted yield data points producing calibrated yield data points.
1. A method comprising:
receiving, from multiple harvesting machines, a plurality of groups of yield data points recorded by uncalibrated sensors mounted to each machine of the multiple harvesting machines as the multiple harvesting machines harvest plants in a field, the yield data points representing uncalibrated data recorded by the multiple harvesting machines and corresponding to a yield harvested from the plants by each respective machine of the multiple harvesting machines;
associating each group of yield data points with a machine identifier indicating the machine of the multiple harvesting machines used to record the group of yield data points;
calculating a grand aggregate yield for the field based on yield data points of the plurality of groups received from the plurality of machines;
for each group of the plurality of groups:
calculating a group aggregate yield based on yield data points of the group associated with each machine identifier;
subtracting the group aggregate yield from each yield data point of the group producing adjusted yield data points;
producing calibrated yield data points for each of the harvesting machines by adding the grand aggregate yield to each of the adjusted yield data points; and
storing, in computer memory, the calibrated yield data points in place of returning the initially received yield data points.
2. The method of claim 1 , wherein the grand aggregate yield is a grand mean yield and the group aggregate yield is a group mean yield.
3. The method of claim 1 , wherein the grand aggregate yield is a grand median yield and the group aggregate yield is a group median yield.
4. The method of claim 1 , further comprising:
for each yield data point:
determining a set of yield data points including yield data points within a threshold distance of the yield data point; and
calibrating the yield data point based on the set of yield data points producing a neighbor-calibrated yield data point.
5. The method of claim 1 , further comprising:
for each group of the plurality of groups:
receiving a confidence parameter associated with the attribute; and
calibrating yield data points of the group based on the confidence parameter producing confidence-calibrated yield data points.
6. The method of claim 1 , further comprising:
for each group of the plurality of groups:
accessing a predetermined adjustment value for the group, the predetermined adjustment value associated with the attribute; and
adjusting each of the calibrated yield data points by the predetermined adjustment value.
7. A system comprising:
a non-transitory computer-readable storage medium storing executable computer instructions that, when executed, perform steps comprising:
receiving, from multiple harvesting machines, a plurality of groups of yield data points recorded by uncalibrated sensors mounted to each machine of the multiple harvesting machines as the multiple harvesting machines harvest plants in a field, the yield data points representing uncalibrated data recorded by the multiple harvesting machines and corresponding to a yield harvested from the plants by each respective machine of the multiple harvesting machines;
associating, each group of yield data points with a machine identifier indicating the machine of the multiple harvesting machines used to record the group of yield data points;
calculating a grand aggregate yield for the field based on yield data points of the plurality of groups received from the plurality of machines;
for each group of the plurality of groups:
calculating a group aggregate yield based on yield data points of the group associated with each machine identifier;
subtracting the group aggregate yield from each yield data point of the group producing adjusted yield data points;
producing calibrated yield data points for each of the harvesting machines by adding the grand aggregate yield to each of the adjusted yield data points; and
storing, in computer memory, the calibrated yield data points in place of returning the initially received yield data points;
a processor configured to execute the computer instructions.
8. The system of claim 7 , wherein the grand aggregate yield is a grand mean yield and the group aggregate yield is a group mean yield.
9. The system of claim 7 , wherein the grand aggregate yield is a grand median yield and the group aggregate yield is a group median yield.
10. The system of claim 7 , wherein the instructions, when executed, perform further steps comprising:
for each yield data point:
determining a set of yield data points including yield data points within a threshold distance of the yield data point; and
calibrating the yield data point based on the set of yield data points producing a neighbor-calibrated yield data point.
11. The system of claim 7 , wherein the instructions, when executed, perform further steps comprising:
for each group of the plurality of groups:
receiving a confidence parameter associated with the attribute; and
calibrating yield data points of the group based on the confidence parameter producing confidence-calibrated yield data points.
12. The system of claim 7 , wherein the instructions, when executed, perform further steps comprising:
for each group of the plurality of groups:
accessing a predetermined adjustment value for the group, the predetermined adjustment value associated with the attribute; and
adjusting each of the calibrated yield data points by the predetermined adjustment value.
13. A non-transitory computer-readable storage medium storing executable computer instructions that, when executed by a processor, perform steps comprising:
receiving, from multiple harvesting machines, a plurality of groups of yield data points recorded by uncalibrated sensors mounted to each machine of the multiple harvesting machines as the multiple harvesting machines harvest plants in a field, the yield data points representing uncalibrated data recorded by the multiple harvesting machines and corresponding to a yield harvested from the plants by each respective machine of the multiple harvesting machines;
associating, each group of yield data points with a machine identifier indicating the machine of the multiple harvesting machines used to record the group of yield data points;
calculating a grand aggregate yield for the field based on yield data points of the plurality of groups received from the plurality of machines;
for each group of the plurality of groups:
calculating a group aggregate yield based on yield data points of the group associated with each machine identifier;
subtracting the group aggregate yield from each yield data point of the group producing adjusted yield data points;
producing calibrated yield data points for each of the harvesting machines by adding the grand aggregate yield to each of the adjusted yield data points; and
storing, in computer memory, the calibrated yield data points in place of returning the initially received yield data points.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the grand aggregate yield is a grand mean yield and the group aggregate yield is a group mean yield.
15. The non-transitory computer-readable storage medium of claim 13 , wherein the grand aggregate yield is a grand median yield and the group aggregate yield is a group median yield.
16. The non-transitory computer-readable storage medium of claim 13 , wherein the instructions, when executed by the processor, perform further steps comprising:
for each yield data point:
determining a set of yield data points including yield data points within a threshold distance of the yield data point; and
calibrating the yield data point based on the set of yield data points producing a neighbor-calibrated yield data point.
17. The non-transitory computer-readable storage medium of claim 13 , wherein the instructions, when executed by the processor, perform further steps comprising:
for each group of the plurality of groups:
receiving a confidence parameter associated with the attribute; and
calibrating yield data points of the group based on the confidence parameter producing confidence-calibrated yield data points.
18. The non-transitory computer-readable storage medium of claim 13 , wherein the instructions, when executed by the processor, perform further steps comprising:
for each group of the plurality of groups:
accessing a predetermined adjustment value for the group, the predetermined adjustment value associated with the attribute; and
adjusting each of the calibrated yield data points by the predetermined adjustment value.
19. The method of claim 1 , wherein the grand aggregate yield for the field is determined over a defined period of time during which the harvesting machines harvested plants in a field.
20. The system of claim 7 , wherein the grand aggregate yield for the field is determined over a defined period of time during which the harvesting machines harvested plants in a field.
21. The non-transitory computer-readable storage medium of claim 13 , wherein the grand aggregate yield for the field is determined over a defined period of time during which the harvesting machines harvested plants in a field.