Magnetic anomaly map mender
AssigneeHoneywell International Inc.
InventorsCarl Arthur Dins, Umut Orhan, Trevor Keith Stephens, Angel Sylvester
Life of this patent
Estimating the term…
Loading patent…
AssigneeHoneywell International Inc.
InventorsCarl Arthur Dins, Umut Orhan, Trevor Keith Stephens, Angel Sylvester
Estimating the term…
A method comprises selecting a first data set including a first magnetic anomaly map of a given area, the first map having a first accuracy; selecting a second data set including geological data for the given area; sending the first and second data sets to a machine learning model; and generating a second magnetic anomaly map of the given area based on the first and second data sets, the second map having a second accuracy higher than the first accuracy. The method further comprises comparing the second map with a ground truth map to train the machine learning model; and performing a validation test of the trained machine learning model by sending an additional data set including held-out magnetic anomaly map data to the machine learning model. In response to a validation threshold being met, the trained machine learning model is used to generate higher accuracy magnetic anomaly maps.
A method comprising:
A system comprising:
Dependencies are inferred from the claim text.