Developing a Technique for Automatic Lineament Identification Based on the Neural Network Approach
Authors:
- 1 December 2023
- journal article
- research article
- Published by Pleiades Publishing Ltd in Izvestiya, Atmospheric and Oceanic Physics
- Vol. 59 (10) , 1271-1280
Abstract
The purpose of this scientific work is to study the potential of neural network technologies in the field of extracting linear structures from Shuttle Radar Topography Mission (SRTM) digital terrain models (DTMs). Linear structures, also known as lineaments, play an important role in the verification of known faults, the identification of fault-fracture structures, and detailing the framework of discontinuous faults, as well as in the exploration of mineral resources. Their accurate and effective extraction in solving the depicted problems is of fundamental importance. The use of neural network technologies provides a number of advantages over sequential algorithms, including the ability to search for universal criteria for identifying lineaments based on a training sample. This paper considers a comprehensive innovative methodology that includes several key stages. The first stage is the author’s method of data preparation, which helps ensure the quality of the training sample and minimize the impact of noise. The second stage is to develop an algorithm for vectorizing the results of the neural network operation, which allows one to easily export the results (lineaments) to a geographic information system (GIS). The third stage provides a method for minimizing the noise component of the training sample and optimizing the selection of synaptic weighting coefficients by retraining the neural network using simulated data reflecting various localization conditions of the lineaments. To verify the results, a spatial comparison of linear structures extracted by the neural network and lineaments isolated by the operator is carried out. The results of this comparison demonstrate the high potential of the proposed approach and show that the use of neural network technologies is a topical and promising approach for solving the problem of extracting linear structures from digital models of the terrain. Positive conclusions are made about the expediency of using the results obtained for their practical application in the field of earth sciences.Keywords
This publication has 18 references indexed in Scilit:
- 70 years of machine learning in geoscience in review2020
- Deep learning and its application in geochemical mappingEarth-Science Reviews, 2019
- A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources ScientistsWater Resources Research, 2018
- Big Data Analytics of Identifying Geochemical Anomalies Supported by Machine Learning MethodsNatural Resources Research, 2017
- Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, ChinaJournal of Geochemical Exploration, 2016
- Machine learning in geosciences and remote sensingGeoscience Frontiers, 2016
- Supervised geochemical anomaly detection by pattern recognitionJournal of Geochemical Exploration, 2015
- The Shuttle Radar Topography MissionReviews of Geophysics, 2007
- Program LESSA (Lineament Extraction and Stripe Statistical Analysis) automated linear image features analysis—experimental resultsComputers & Geosciences, 1992
- Topological structural analysis of digitized binary images by border followingComputer Vision, Graphics, and Image Processing, 1985