WEATHER FORECASTING SYSTEM AND METHODS

• US 20160178803A1
• Filed: 02/26/2016
• Published: 06/23/2016
• Est. Priority Date: 01/24/2014
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: HAAS, Richard M., JOHNSON, Randy S., NORTHWAY, Tedrick N., RINCKEL, William H.
• Granted Patent: US 10,295,704 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01W 1/02 Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed G01W1/10 takes precedence
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30192 Weather; Meteorology
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06T 7/35 using statistical methods
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85

Abstract

An approach for forecasting local weather patterns. The approach includes a method that includes receiving, by at least one computing device, images that include weather related information. The method includes analyzing, by the at least one computing device, the images to determine particular types of weather phenomena. The method includes analyzing, by the at least one computing device, the images to determine a motion of the particular types of weather phenomena. The method includes determining, by the at least one computing device, a weather forecast based on the analyzed images and the motion of the particular types of weather phenomena.

Claims

1. A method of using multiple sensors at different locations to predict weather comprising:

providing sensors at locations different from one another, each sensor being configured to provide images including current weather related information at the location where the sensor is located;

receiving, by at least one computing device, the images from the sensors that include weather related information;

identifying, by the at least one computing device, the location of each of the sensors based upon information provided by the sensors;

performing a time series analysis to forecast weather conditions comprising;

analyzing, by the at least one computing device, the images to determine particular types of weather phenomena;

analyzing, by the at least one computing device, the images to determine a motion of the particular types of weather phenomena; and

determining, by the at least one computing device, a first weather forecast based on the analyzed images and the motion of the particular types of weather phenomena;

performing a weather map analysis to forecast weather conditions comprising;

accessing a database of weather maps showing weather conditions at different points of time;

analyzing the weather maps to determine constant weather features at two or more different locations of the sensors at the different points of time and evolving weather features at the two or more different locations of the sensors at the different points of time; and

aggregating the constant weather features and the evolving weather features to create a second weather forecast based on the weather map analysis; and

integrating the first weather forecast and the second weather forecast into a consolidated weather forecast.

2. The method of claim 1, further comprising determining a probability that the first weather forecast will occur.

3. The method of claim 1, wherein the sensors include at least one of traffic cameras, security cameras, mobile cameras, and mobile devices.

4. The method of claim 1, wherein the analyzing the images to determine the particular types of weather phenomena includes analyzing the images for different types of precipitation, wherein the precipitation includes at least one of rain, hail, sleet, and snow.

5. The method of claim 1, wherein the analyzing the images to determine the particular types of weather phenomena includes analyzing the images for levels of grey that are used to determine sky conditions.

6. The method of claim 1, further comprising:

receiving sensor information that includes information relating to at least one of temperature, pressure, magnetic levels, and humidity; and

analyzing the sensor information to determine the weather related information and using the weather related information to determine the first weather forecast.

7. The method of claim 1, wherein the images are associated with a particular image quality level.

8. The method of claim 1, wherein the images include at least one of structured data, unstructured data, and a combination of the structured data and the unstructured data.

9. The method of claim 1, further comprising:

determining a level of accuracy of the first weather forecast by comparing the first weather forecast with actual weather phenomena; and

updating the at least one computing device'"'"'s weather forecasting capabilities based on the level of accuracy.

10. The method of claim 1, wherein the weather maps include information indicating at least one of pressure levels and temperature levels.

11. The method of claim 1, further comprising searching for additional sensors to receive images including the weather related information from after the location of each of the sensors has been identified and before analyzing the images to determine the particular types of weather phenomena.

12. The method of claim 1, further comprising determining an age of the weather maps in the database and comparing the age of the weather maps with a predetermined threshold age of the weather maps, wherein the analyzing of the weather maps is limited to weather maps which do not exceed the predetermined threshold age.