Meteorological parameter forecasting

• US 9,229,132 B2
• Filed: 07/05/2011
• Issued: 01/05/2016
• Est. Priority Date: 07/05/2011
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Guha, Supratik, Hamann, Hendrik F., Klein, Levente
• Primary Examiner(s): Charioui, Mohamed
• Assistant Examiner(s): Kuan, John
• Application Number:
  US13/176,099
• Publication Number:
  US 20130013206A1
• Time in Patent Office: 1,645 Days
• US Class Current: 1/1
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G01W 2001/006 Main server receiving weather information from several sub-stations
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

A method, an apparatus and an article of manufacture for forecasting a meteorological parameter. The method includes analyzing geographically distributed sensor network data to assess spatial and temporal variation of a meteorological parameter in real-time, correlating at least two portions of data from the sensor network to identify a temporal and spatial evolution of the meteorological parameter, and forecasting the meteorological parameter based on the temporal and spatial evolution of the meteorological parameter.

Claims

1. An article of manufacture tangibly embodying computer readable instructions which, when implemented, cause a computer to carry out a plurality of method steps comprising:

analyzing geographically distributed sensor network data across two sensors within a first geographic region to assess spatial and temporal variation of cloud movement in real-time, wherein said sensor network data comprise solar panel power output;

determining a correlation across the two sensors by identifying a temporal and spatial evolution of the cloud movement across the two sensors via;

associating a decrease in solar panel power output from each of the two sensors with a time stamp;

determining cloud movement speed corresponding to the decrease in solar panel power output based on (i) a predetermined distance between the two sensors and (ii) the difference between the time stamp associated with the decrease in solar panel power output from each of the two sensors; and

determining a directional pattern of the cloud movement based on (i) a predetermined geographic location of each of the two sensors and (ii) the time stamp associated with the decrease in solar panel power output from each of the two sensors;

determining a strength of the correlation across the two sensors;

determining an extension of the correlation to one or more additional sensors within the first geographic region via;

associating a decrease in solar panel power output from each of the three or more sensors with a time stamp;

determining cloud movement speed corresponding to the decrease in solar panel power output based on (i) a predetermined distance between the three or more sensors and (ii) the difference between the time stamp associated with the decrease in solar panel power output from each of the three or more sensors; and

determining a directional pattern of the cloud movement based on (i) a predetermined geographic location of each of the three or more sensors and (ii) the time stamp associated with the decrease in solar panel power output from each of the three or more sensors;

determining a strength of the extension of the correlation;

forecasting the cloud movement across the first geographic region based on (i) each determined correlation and (ii) the determined strength of each determined correlation;

updating, in real-time, a model comprising satellite data for forecasting weather across a second geographic region based on said forecasting of the cloud movement across the first geographic region, wherein said second geographic region encompasses the first geographic region and one or more additional geographic regions; and

outputting the forecasted cloud movement to at least one of a user and a display;

wherein the plurality of method steps are carried out by the computer linked to the geographically distributed sensor network.

2. The article of manufacture of claim 1, wherein determining the correlation comprises correlating data obtained from a near neighbor sensor with data obtained from at least one farther-positioned sensor to determine a pattern that is shifted in time.

3. The article of manufacture of claim 1, wherein forecasting the cloud movement comprises training a physical model for a cloud movement prediction based on data from at least one sensor.

4. The article of manufacture of claim 3, wherein the computer readable instructions which, when implemented, further cause a computer to carry out a method step comprising predicting an event at a sensor located in a block neighboring an analyzed region based on the physical model.

5. A system for forecasting a meteorological parameter, comprising:

a memory; and

at least one processor coupled to the memory and operative for steps comprising;

analyzing geographically distributed sensor network data across two sensors within a first geographic region to assess spatial and temporal variation of cloud movement in real-time, wherein said sensor network data comprise solar panel power output;

determining a correlation across the two sensors by identifying a temporal and spatial evolution of the cloud movement across the two sensors via;

associating a decrease in solar panel power output from each of the two sensors with a time stamp;

determining cloud movement speed corresponding to the decrease in solar panel power output based on (i) a predetermined distance between the two sensors and (ii) the difference between the time stamp associated with the decrease in solar panel power output from each of the two sensors; and

determining a directional pattern of the cloud movement based on (i) a predetermined geographic location of each of the two sensors and (ii) the time stamp associated with the decrease in solar panel power output from each of the two sensors;

determining a strength of the correlation across the two sensors;

determining an extension of the correlation to one or more additional sensors within the first geographic region via;

associating a decrease in solar panel power output from each of the three or more sensors with a time stamp;

determining cloud movement speed corresponding to the decrease in solar panel power output based on (i) a predetermined distance between the three or more sensors and (ii) the difference between the time stamp associated with the decrease in solar panel power output from each of the three or more sensors; and

determining a directional pattern of the cloud movement based on (i) a predetermined geographic location of each of the three or more sensors and (ii) the time stamp associated with the decrease in solar panel power output from each of the three or more sensors;

determining a strength of the extension of the correlation;

forecasting the cloud movement across the first geographic region based on (i) each determined correlation and (ii) the determined strength of each determined correlation;

updating, in real-time, a model comprising satellite data for forecasting weather across a second geographic region based on said forecasting of the cloud movement across the first geographic region, wherein said second geographic region encompasses the first geographic region and one or more additional geographic regions; and

outputting the forecasted cloud movement to at least one of a user and a display;

wherein the steps are carried out by the at least one processor linked to the geographically distributed sensor network.

6. The system of claim 5, wherein determining the correlation comprises correlating data obtained from a near neighbor sensor with data obtained from at least one farther-positioned sensor to determine a pattern that is shifted in time.

7. The system of claim 5, wherein forecasting the cloud movement comprises training a physical model for a cloud movement prediction based on data from at least one sensor.

8. The system of claim 7, wherein the at least one processor coupled to the memory is further operative for predicting an event at a sensor located in a block neighboring an analyzed region based on the physical model.