Weather model predictor

• US 7,844,427 B1
• Filed: 07/28/2008
• Issued: 11/30/2010
• Est. Priority Date: 07/28/2006
• Status: Active Grant

• Current Assignee: DTN, LLC (TBG AG)
• Original Assignee: WSI Incorporated
• Inventors: Neilley, Peter P., Crawford, Todd
• Primary Examiner(s): Rodriguez; Paul L
• Assistant Examiner(s): Kim; Eunhee
• Application Number:
  US12/220,750
• Time in Patent Office: 855 Days
• Field of Search: 703/6, 702/2, 702/3, 706/62
• US Class Current: 703/6
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09

Abstract

A computer-implemented method of predicting an output of a model includes receiving output data from a first run of a target predictive model. One or more additional sets of output data is received from runs of one or more alternate predictive model. The alternate predictive models predict parameters that relate to the output data of the first predictive model. A future output of a second run of the target predictive model is predicted based on the output data from the first run of the target predictive model and one or more sets of additional output data from runs of the alternate prediction model.

Claims

1. A computer-implemented method of anticipating by a first computer results of a target weather model, the method comprising:

(a) receiving, by the first computer, from a target weather model data source maintained by a second computer different than the first computer, one or more sets of first output data produced as a result of at least one previous run of the target weather model, and receiving, by the first computer, from an alternate weather model data source maintained by a third computer different than the first computer, at least one set of additional output data produced as a result of runs of at least one alternate weather model;

(b) predicting, by the first computer, one or more sets of second output data expected to be produced as a result of a current run of the target weather model prior to the completion of the current run of the target weather model using the one or more sets of the first output data and the at least one set of additional output data, wherein the predicting occurs without the first computer performing runs of the target weather model and the at least one alternate weather model, and without observable weather data being used by the first computer in the predicting; and

(c) providing a visual representation including the one or more sets of first and second output data corresponding to the at least one previous run of the target weather model and the current run of the target weather model, respectively.

2. The method of claim 1, wherein the predicting in step (b) includes utilizing a subset of actual output data produced as a result of the current run of the target weather model that is available during the current run of the target weather model prior to the completion of the current run of the target weather model.

3. The method of claim 1, wherein the one or more sets of second data in step (b) is a prediction of actual one or more sets of second data expected to be produced as a result of the current run of the target weather model at the completion of the current run of the target weather model.

4. The method of claim 1, wherein the one or more sets of second output data include a prediction of an expected direction of change of the output data expected to be produced as a result of the at least one previous run of the target weather model.

5. The method of claim 1, wherein the one or more sets of second output data are obtained using a statistical model based on predictive patterns and statistical relationships between the output data from the target and alternate weather models derived from output data produced as a result of previous runs of the target and alternate weather models, the statistical model tracking an accuracy for each of the at least one alternate weather models in predicting the output of a future run of the target weather model by comparing previous outputs of the at least one alternate weather model with previous outputs of the target weather model.

6. The method of claim 1, wherein each set of first and second output data corresponds to predicted future weather conditions at a different time after the initialization of the previous and current runs of the target weather model, respectively.

7. The method of claim 1, wherein the visual representation is a graphical display of the time evolution of a weather system corresponding to the sets of first and second output data.

8. The method of claim 7, wherein the weather system is a cyclone.

9. The method of claim 8, wherein the sets of first and additional output data represent actual forecast tracks for the cyclone and the set of second output data represents a future predicted forecast track for the cyclone.

10. The method of claim 9, wherein the predicted future forecast track is a prediction of an actual forecast track expected to be produced as a result of the current run of the target weather model at the completion of the current run of the target weather model.

11. The method of claim 9, wherein the visual representation indicates a prediction of an expected direction of change of the predicted future forecast track corresponding to the current run of the target model in comparison with at least one of the actual forecast tracks produced as a result of the at least one previous run of the target weather model.

12. The method of claim 1, wherein the visual representation is used in evaluating a change in at least one of a future price for a financial instrument and a future demand for a commodity.

13. The method of claim 1, wherein the visual representation is used to facilitate a business transaction prior to the completion of the current run of the target weather model for a least one of a financial instrument and a commodity.

14. The method of claim 1, wherein the target weather model is the Global Forecast System model, and the current run of the target weather model is a 1200 UTC morning operational run of the Global Forecast System model.

15. A method of utilizing by a first computer predictive results corresponding to a target weather model, the method comprising:

(a) obtaining a visual representation of one or more sets of second output data expected to be produced as a result of a current run of the target weather model and one or more sets of first output data produced as a result of at least one previous run of the target weather model, wherein the one or more sets of the second output data are predicted prior to completion of the current run of the target weather model using the one or more sets of first output data received by the first computer from a target weather model data source maintained by a second computer different than the first computer, and at least one set of additional output data from runs of at least one alternate weather model received by the first computer from an alternate weather model data source maintained by a third computer different than the first computer, wherein the predicting occurs without the first computer performing runs of the target weather model and the at least one alternate weather model, and without observable weather data being used by the first computer in the predicting; and

(b) evaluating a change in at least one of a future demand for a commodity and a future price for a financial instrument based on the visual representation.

16. The method of claim 15, further comprising:

(c) initiating a business transaction based on the evaluated change in step (b), wherein the business transaction is initiated prior to the completion of the current run of the target weather model.

17. The method of claim 15, wherein commodities include at least one of oil, natural gas, and electricity.

18. The method of claim 15, wherein the one or more sets of second output data include a prediction of an expected direction of change of the output data produced as a result of the at least one previous run of the target weather model.

19. The method of claim 15, wherein each set of first and second output data corresponds to predicted future weather conditions at a different time after the initialization of the previous and current runs of the target weather model, respectively.

20. The method of claim 15, wherein the visual representation is a graphical display of the time evolution of a weather system corresponding to the sets of first and second output data.

21. The method of claim 15, wherein the weather system is a cyclone.

22. The method of claim 21, wherein the sets of first and additional output data represent actual forecast tracks for the cyclone and the set of second output data represents a future predicted forecast track for the cyclone.

23. The method of claim 22, wherein the predicted future forecast track is a prediction of an actual forecast track expected to be produced as a result of the current run of the target weather model at the completion of the current run of the target weather model.

24. The method of claim 22, wherein the visual representation indicates a prediction of an expected direction of change of the predicted future forecast track corresponding to the current run of the target model in comparison with at least one of the actual forecast tracks produced as a result of the at least one previous run of the target weather model.

25. An article of manufacture for anticipating by a first computer results of a target weather model, the article of manufacture comprising a computer-readable medium holding computer-executable instructions for performing a method comprising:

(a) receiving, by the first computer, from a target model data source maintained by a second computer different than the first computer, one or more sets of first output data produced as a result of at least one previous run of the target weather model, and receiving, by the first computer, from an alternate weather model data source maintained by a third computer different than the first computer, at least one set of additional output data produced as a result of runs of at least one alternate weather model;

(b) predicting, by the first computer, one or more sets of second output data expected to be produced as a result of a current run of the target weather model prior to the completion of the current run of the target weather model using the one or more sets of the first output data and the at least one set of additional output data, wherein the predicting occurs without the first computer performing runs of the target weather model and the at least one alternate weather model, and without observable weather data being used by the first computer in the predicting; and

(c) providing a visual representation including the one or more sets of first and second output data corresponding to the at least one previous run of the target weather model and the current run of the target weather model, respectively.

26. The article of manufacture of claim 25, wherein the one or more sets of second output data are obtained using a statistical model based on predictive patterns and statistical relationships between the output data from the target and alternate weather models derived from output data produced as a result of previous runs of the target and alternate weather models, the statistical model tracking an accuracy for each of the at least one alternate weather models in predicting the output of a future run of the target weather model by comparing previous outputs of the at least one alternate weather model with previous outputs of the target weather model.

27. The article of manufacture of claim 25, wherein the visual representation is a graphical display of the time evolution of a weather system corresponding to the sets of first and second output data.

28. The article of manufacture of claim 27, wherein the weather system is a cyclone.

29. The article of manufacture of claim 28, wherein the sets of first and additional output data represent actual forecast tracks for the cyclone and the set of second output data represents a future predicted forecast track for the cyclone, the predicted future forecast track being a prediction of an actual forecast track expected to be produced as a result of the current run of the target weather model at the completion of the current run of the target weather model.

30. The article of manufacture of claim 29, wherein the visual representation indicates a prediction of an expected direction of change of the predicted future forecast track corresponding to the current run of the target model in comparison with at least one of the actual forecast tracks produced as a result of the at least one previous run of the target weather model.

31. A system comprising a first computer for anticipating results of a target weather model, the system comprising:

means for receiving, from a target model data source maintained by a second computer different than the first computer, one or more sets of first output data produced as a result of at least one previous run of the target weather model, and from an alternate model data source maintained by a third computer different than the first computer, at least one set of additional output data produced as a result of runs of at least one alternate weather model;

means for predicting one or more sets of second output data expected to be produced as a result of a current run of the target weather model prior to the completion of the current run of the target weather model using the one or more sets of the first output data and the at least one set of additional output data, wherein the predicting occurs without the first computer performing runs of the target weather model and the at least one alternate weather model, and without observable weather data being used by the first computer in the predicting; and

means for providing a visual representation including the one or more sets of first and second output data corresponding to the at least one previous run of the target weather model and the current run of the target weather model, respectively.

32. The system of claim 31, wherein the one or more sets of second output data are obtained using a statistical model based on predictive patterns and statistical relationships between the output data from the target and alternate weather models derived from output data produced as a result of previous runs of the target and alternate weather models, the statistical model tracking an accuracy for each of the at least one alternate weather models in predicting the output of a future run of the target weather model by comparing previous outputs of the at least one alternate weather model with previous outputs of the target weather model.

33. The system of claim 31, wherein the visual representation is a graphical display of the time evolution of a weather system corresponding to the sets of first and second output data.

34. The system of claim 33, wherein the weather system is a cyclone.

35. The system of claim 34, wherein the sets of first and additional output data represent actual forecast tracks for the cyclone and the set of second output data represents a future predicted forecast track for the cyclone, the predicted future forecast track being a prediction of an actual forecast track expected to be produced as a result of the current run of the target weather model at the completion of the current run of the target weather model.

36. The system of claim 35, wherein the visual representation indicates a prediction of an expected direction of change of the predicted future forecast track corresponding to the current run of the target model in comparison with at least one of the actual forecast tracks produced as a result of the at least one previous run of the target weather model.