A method and system for predicting mineral resources based on neural network model

Abstract

The invention discloses a method and system for predicting mineral resources based on a neural network model, which relates to the field of geoinformation science and mainly includes: cutting out a known geological map to obtain a research area containing multiple sampling points; Construct the buffer zone; obtain the weight value of the mineralization probability according to the location information of the sampling point and the center line of the buffer zone; calculate the metallogenic probability according to the location information of the sampling point and the linear relationship between the importance of the Triassic Talc Guan Formation and the siliceous breccia Eigenvalues; calculate the data label according to the weight table; construct a matrix data set with the number of rows equal to the number of sampling points, each row of data corresponds to the content of geochemical elements contained in a sampling point, the weight value of the mineralization probability, the characteristic value of the mineralization probability and Data labeling; use the matrix data set to train and optimize the constructed neural network model; use the trained and optimized model to predict the area to be surveyed and delineate the target area of ​​​​mineral resources. The invention can realize more accurate prediction results.

Description

technical field [0001] The invention relates to the field of earth information science, in particular to a method and system for predicting mineral resources based on a neural network model. Background technique [0002] In recent years, with the rapid development of the world economy, mineral resources have increasingly become an important material basis for economic and social development, and the development and utilization of mineral resources has also become an inevitable requirement for modernization. Metallogenic prediction is a comprehensive research work to improve the effectiveness and predictability of ore prospecting. It can comprehensively analyze the geological characteristics of the working area based on the actual data of various geological minerals and geophysical and chemical exploration in the working area. and the types and scales of various minerals that have been discovered and their relationship with geological structures in time and space, clarify the...

AI Technical Summary

Problems solved by technology

Compared with the traditional mineralization prediction method, the neural network can achieve more accurate results in a shorter period of time. However, the existing neural network mineral resource prediction methods generally have low efficiency and cannot process data in batches. The neural network model is aimed at defects such as poor performance and low prediction accuracy

Images