Semi-supervised landform classification model training and geomorphologic map construction method

Abstract

The embodiment of the invention is suitable for the technical field of artificial intelligence, and discloses a semi-supervised landform classification model training and geomorphologic map construction method. The semi-supervised landform classification model training and geomorphologic map construction method comprises the steps: obtaining a geomorphologic sample data set after manual labeling and corresponding label information; performing adversarial training on the generative adversarial network by using the label information and the manually labeled geomorphic sample data set to obtain target pseudo-geomorphic data output by the generative adversarial network, wherein the target pseudo-geomorphic data is pseudo-geomorphic data output when the training effect of the generative adversarial network is optimal; training the pre-trained landform classification model by using the target pseudo-geomorphologic data; and after the training is completed, using a landform classification model to construct a geomorphologic map. According to the embodiment of the invention, based on the generative adversarial network, a large amount of training data is generated by using a small amount ofmanually labeled data, so that the acquisition time of geomorphologic sample images is reduced.

Description

technical field [0001] The application belongs to the technical field of artificial intelligence, and in particular relates to a semi-supervised landform classification model training method and a landform map construction method. Background technique [0002] A geomorphic map is a map showing various geomorphic signs. It can reflect the external morphological characteristics and causes, age, development process, development degree and mutual relationship of various landforms. [0003] At present, when using a convolutional neural network model to construct a geomorphic map, it is necessary to use a large number of manually labeled geomorphic sample images to train the corresponding model, and it takes a lot of time to manually label a large number of geomorphic sample images. Contents of the invention [0004] The embodiment of the present application provides a semi-supervised method for training the landform classification model and constructing the landform map, so as...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a semi-supervised landform classification model training and landform map construction method to solve the problem that it takes a lot of time to collect training samples in the existing landform construction

Images