Method And Apparatus For Generating Weather Data Based On Machine Learning
AssigneeSI Analytics Co., Ltd.
InventorYeji CHOI
Life of this patent
Estimating the term…
Abstract
Disclosed is a computing device for generating weather observation data for solving the problem. The computing device includes: a memory including computer executable components; and a processor executing following computer executable components stored in the memory, and the computer executable components may include an initial ground weather observation data recognition component recognizing observed initial ground weather observation data, and a weather data generation component trained to generate weather data of a gap region on the initial ground weather observation data by using a machine learning module.
Claims18
A computing device for generating weather observation data, the computing device comprising:
- a memory including computer executable components;
- and
- a processor executing following computer executable components stored in the memory,
- wherein the computer executable components include:
- an initial ground weather observation data recognition component recognizing observed initial ground weather observation data,
- a weather data generation component trained to generate weather data of a gap region on the initial ground weather observation data by using a machine learning module,
- wherein the weather data generation component is a component trained based on non-missing ground weather observation data,
- wherein the non-missing ground weather observation data is generated by applying missing region weather estimation data generated by using relational data describing relationship between the satellite weather observation data for the missing region, and at least one of the land surface characteristic data or land surface type data.
(canceled)
(canceled)
A method for generating weather observation data performed by a computing device, the method comprising:
- recognizing observed initial ground weather observation data;
- and
- generating weather data of a gap region on the initial ground weather observation data by using a machine learning module,
- wherein the machine learning module is trained based on non-missing ground weather observation data,
- wherein the non-missing ground weather observation data is generated by applying missing region weather estimation data generated by using relational data describing relationship between the satellite weather observation data for the missing region, and at least one of the land surface characteristic data or land surface type data.
A computer program stored on a non-transitory computer readable storage medium, wherein the computer program including instructions for causing one or more processors to generate weather observation data, the instructions comprising:
- recognizing observed initial ground weather observation data;
- and
- generating weather data of a gap region on the initial ground weather observation data by using a machine learning module,
- wherein the machine learning module is trained based on non-missing ground weather observation data,
- wherein the non-missing ground weather observation data is generated by applying missing region weather estimation data generated by using relational data describing relationship between the satellite weather observation data for the missing region, and at least one of the land surface characteristic data or land surface type data.
Dependencies are inferred from the claim text.