Methods, systems and computer program products for generating weather forecasts from a multi-model superensemble
First Claim
1. A method for generating an accurate weather forecast model, comprising:
- collecting historical forecast information from a plurality of weather models, wherein the historical forecast information includes at least one predicted weather component, and wherein the historical forecast information corresponds to a past period of time;
accumulating observed weather data, wherein the observed weather data corresponds to a plurality of known weather values, wherein at least one known weather value of the plurality of known weather values corresponds to the at least one predicted weather component, and wherein the observed weather data corresponds to the past period of time;
comparing the historical forecast information to the observed weather data to determine the historical performance of each weather model of the plurality of weather models, and generating a multi-model superensemble of the weather models, wherein the multi-model superensemble is based upon the historical performance of each weather model of the plurality of weather models.
1 Assignment
0 Petitions
Accused Products
Abstract
A superensemble is developed using a plurality of forecasts from a variety of weather and climate models. Along with observed analysis fields, these forecasts are used to derive statistics on the past behavior of the models. These statistics, combined with future forecasts of the models, enables the construction of a superensemble forecast. More specifically, given a set of past model forecasts, the present invention uses a multiple regression technique to regress the model forecasts against observed fields. Least-squares minimization of the difference between the model and the analysis field is used to determine the weights of each model component at any geographic location and vertical level. Therefore, the superensemble generates a model that combines the historical performance of forecasting data from multiple models at a large number of geographic areas or regions. Furthermore, the superensemble model can combine the historical performance of multiple models in forecasting one weather condition at any geographic location.
104 Citations
29 Claims
-
1. A method for generating an accurate weather forecast model, comprising:
-
collecting historical forecast information from a plurality of weather models, wherein the historical forecast information includes at least one predicted weather component, and wherein the historical forecast information corresponds to a past period of time;
accumulating observed weather data, wherein the observed weather data corresponds to a plurality of known weather values, wherein at least one known weather value of the plurality of known weather values corresponds to the at least one predicted weather component, and wherein the observed weather data corresponds to the past period of time;
comparing the historical forecast information to the observed weather data to determine the historical performance of each weather model of the plurality of weather models, and generating a multi-model superensemble of the weather models, wherein the multi-model superensemble is based upon the historical performance of each weather model of the plurality of weather models. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method for generating accurate weather forecasts, comprising:
-
collecting historical forecast information from a plurality of weather models, wherein the historical forecast information includes at least one predicted weather component, and wherein the historical forecast information corresponds to a past period of time;
accumulating observed weather data corresponding to a plurality of known weather values, wherein at least one known weather value of the plurality of known weather values corresponds to the at least one predicted weather component, and wherein the observed weather data corresponds to the period of time;
comparing the historical forecast information to the observed weather data to determine the historical performance of each weather model of the plurality of weather models;
calculating at least one weight for each weather model, based at least in part upon the historical performance of each weather model in forecasting the at least one predicted weather component;
combining the weights for each weather model with future forecast information from the plurality of weather models, wherein the future forecast information corresponds to a future period of time, to generate a multi-model superensemble forecast. - View Dependent Claims (10, 11, 12, 13)
-
-
14. A method for generating accurate weather forecasts, comprising:
-
accumulating historical forecast information from a plurality of weather models, where the historical forecast information is derived prior to the occurrence of weather forecasted by the plurality of weather models, and wherein the historical forecast information includes a plurality of predicted weather components related to expected weather conditions;
collecting observed weather data after the occurrence of the weather forecasted by the plurality of weather models, wherein the observed weather data includes known weather values corresponding to at least some of the plurality of predicted weather components;
weighting the historical performance of each weather model in predicting the plurality of predicted weather components by comparing the accumulated historical forecast information to the observed weather data, and generating a superensemble weather model based upon a combination of each weighted weather model. - View Dependent Claims (15, 16)
-
-
17. A system for generating an accurate weather forecasting model, comprising:
-
a plurality of weather models, wherein the weather models include historical forecasts for past weather conditions and prospective forecasts for future weather conditions;
observed weather data corresponding to the past weather conditions, and a superensemble generator, in communication with the plurality of weather models and observed weather data, for producing a superensemble forecast, wherein the superensemble generator determines the historical performance of the plurality of weather models based on a comparison of the historical forecasts for past weather conditions to the observed weather data, and wherein the superensemble forecast is based at least in part upon the historical performance of the plurality of weather models and the prospective forecasts for future weather conditions. - View Dependent Claims (18, 19, 20, 21)
a processor, and a superensemble module in communication with said processor, wherein the superensemble module and processor operate to compare the historical forecasts to the observed weather data to determine the historical performance of the plurality of weather model.
-
-
22. A computer program product for generating an accurate weather forecast model, comprising:
-
a computer readable storage medium having computer-readable program code means embodied in said medium, said computer-readable program code means comprising;
computer-readable program code means for collecting historical forecast information from a plurality of weather models, wherein the historical forecast information includes at least one predicted weather component, and wherein the historical forecast information corresponds to a past period of time;
computer-readable program code means for accumulating observed weather data, wherein the observed weather data corresponds to a plurality of known weather values, wherein at least one known weather value of the plurality of known weather values corresponds to the at least one predicted weather component, and wherein the observed weather data corresponds to the past period of time;
computer readable program code means for comparing the historical forecast information to the observed weather data to determine the historical performance of each weather model of the plurality of weather models, and computer-readable program code means for generating a multi-model superensemble of the weather models, wherein the multi-model superensemble is based upon the historical performance of each weather model of the plurality of weather models. - View Dependent Claims (23, 24, 25, 26, 27, 28, 29)
-
Specification