Geological feature detection and recognition method and system based on deep learning

Abstract

The invention discloses a geological feature detection and recognition method based on deep learning. The method comprises the following steps: acquiring and sending geological information of a target area; obtaining artificial geologic feature classification data, and performing classification marking on the geologic information according to the artificial geologic feature classification data to obtain initial geologic feature information; classifying the initial geologic feature information by using a classification model obtained based on a deep learning algorithm, and generating and sending geologic feature category information; and importing the geological feature category information into a recognition model obtained based on a deep learning algorithm, and generating and sending geological feature recognition information. The invention further discloses a geological feature detection and recognition system based on deep learning. According to the method, different geologic features can be subjected to refined analysis, the accurate geologic features can be quickly and effectively recognized, and a basis is provided for subsequent geologic analysis.

Description

technical field [0001] The invention relates to the technical field of geological survey, in particular to a method and system for detecting and identifying geological features based on deep learning. Background technique [0002] Understanding geological characteristics can facilitate more accurate and faster geological survey work, and can predict the geological conditions around the survey point, which can effectively reduce survey costs and save financial resources. In recent years, especially since 2009, with the development of deep learning research in the field of machine learning, recognition technology has developed by leaps and bounds. Introducing deep learning research into the field of recognition greatly improves the accuracy of recognition and reduces human workload. The essence of deep learning is to learn more useful features by building a machine learning model with many hidden layers and massive training data, so as to ultimately improve the accuracy of cl...

AI Technical Summary

Problems solved by technology

[0003] However, the recognition accuracy of the geological recognition method using deep learning in the prior art is not high, and it can only detect and recognize simple and broad types of geological features, and cannot perform in-depth analysis to obtain more accurate recognition data

Images