Training method of geological unit classification model and geological unit classification method and device

Abstract

The invention provides a training method of a geological unit classification model. The geological unit classification model training method comprises the following steps: selecting a target area according to a lunar topographic map framing rule, and determining image data of the target area; pixel grid vector data are generated based on the image data, latitude and longitude coordinates of the center position of each pixel grid are calculated according to the pixel grid vector data, and data point vector data are obtained; performing spatial superposition operation based on the data point vector data, and determining at least one data feature; determining sample input data of a to-be-trained geological unit classification model based on the at least one data feature; and training the to-be-trained geological unit classification model by adopting a machine learning algorithm according to the sample input data. The invention further provides a geological unit classification method and device, equipment and a storage medium.

Description

technical field [0001] The present disclosure relates to the field of image technology and can be applied to the field of artificial intelligence technology, and more particularly to a training method for a geological unit classification model, a geological unit classification method, an apparatus, an electronic device and a storage medium. Background technique [0002] In the study of lunar geochronology, due to the limited conditions of lunar field survey and acquisition of lunar samples, the use of crater size-frequency distribution (CSFD) to estimate the geological age of the lunar surface has become widely used in the field of lunar and planetary science. approved method. To estimate the geological age by using the CSFD method, the geological unit should be divided first, and then the impact craters of the same geological unit should be counted. [0003] The currently publicly available USGS 1:5 million geological map and Hiesigner geological unit classification and di...

AI Technical Summary

Problems solved by technology

[0003] The currently publicly available USGS 1:5 million geological map and the classification and division of Hiesigner geological units cannot meet the requirements of using the CSFD method to estimate the geological age of the lunar surface for lunar chronology research. On the one hand, the USGS 1:5 million geological map was completed in 70 In the 1990s, the image map data obtained by the Lunar Orbiter mission was mainly used, which was limited by the resolution and type of data available at that time, and the spatial resolution of the scale of the geological map was low, so it was difficult to clearly express and synthesize the details of the lunar surface topography , so that it is impossible to achieve a more precise and accurate classification and division of geological units on the lunar surface; on the other hand, the geological units divided by Hiesigner are limited to the lunar maria, and the coverage is limited and cannot support the dating research of the whole month; the classification of geological units It is often necessary for researchers to make artificial subjective judgments on the research area. However, due to the difficulty in identifying the types of lunar geological units, lithology identification cannot rely on only one type of data, and requires multiple types of data to confirm. Due to the sensitivity of the human eye to distinguish grayscale images Different, the classification of geological units often depends on the practical experience of researchers, different researchers produce different results, the classification results of geological units are greatly affected by human factors, and the efficiency is low

Images