APPARATUS FOR SELECTING METHOD OF TRAINING SEA FOG DISSIPATION PREDICTION MODEL, METHOD FOR SELECTING METHOD OF TRAINING SEA FOG DISSIPATION PREDICTION MODEL, SEA FOG DISSIPATION PREDICTION APPARATUS, AND SEA FOG DISSIPATION PREDICTION METHOD

摘要

Provided is an apparatus for selecting a method of training a sea fog dissipation prediction model, capable of training the sea fog dissipation prediction model by each of N learning methods. According to one embodiment of the present invention, the apparatus for selecting a method of training a sea fog dissipation prediction model includes: a memory including at least one instruction; and at least one processor operatively connected to the memory, wherein, when the at least one instruction is executed by the at least one processor, the at least one processor is configured to: acquire various types of sea fog-related observation data; select at least two types of sea fog-related observation data among the acquired various types of sea fog-related observation data by using a first criterion; generate an input data set based on the selected at least two types of sea fog-related observation data; train the sea fog dissipation prediction model by each of N learning methods based on the generated input data set; evaluate the sea fog dissipation prediction model trained by each of the N learning methods by using a second criterion; and select at least two different learning methods according to an evaluation result.;COPYRIGHT KIPO 2020