☆ 4.7 Article

Smooth Deep Learning Magnetotelluric Inversion Based on Physics-Informed Swin Transformer and Multiwindow Savitzky-Golay Filter

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2023)

Related references

Note: Only part of the references are listed.

Article Geochemistry & Geophysics

IncepTCN: A new deep temporal convolutional network combined with dictionary learning for strong cultural noise elimination of controlled-source electromagnetic data

Guang Li et al.

Summary: Researchers have developed a new strong-noise elimination method called IncepTCN-SISC, based on deep learning and dictionary learning, to effectively remove noise from CSEM data contaminated by intense cultural noise and low signal-to-noise ratio (S/N lower than 0 dB). By creating a deep neural network model called IncepTCN, the strong-noise segments in the observed signal are recognized and discarded, and the remaining weak-noise segments are denoised using a shift-invariant convolutional coding-based dictionary learning method. Simulated and field data experiments demonstrate that IncepTCN network outperforms alternative methods in terms of accuracy and efficiency.

GEOPHYSICS (2023)

Add to Collection

Article Geochemistry & Geophysics

Physics-Driven Deep Learning Inversion for Direct Current Resistivity Survey Data

Bin Liu et al.

Summary: The direct-current resistivity method is commonly used in geophysical surveys for adverse geological conditions. Inversion, the reconstruction of the resistivity model from data, is an important step in these surveys. Deep learning offers new methods for solving inverse problems, but most current methods rely heavily on labels, which are difficult to obtain in field surveys. This study proposes an unsupervised learning resistivity inversion scheme based on physical laws of electric field propagation to address this issue, and demonstrates its accuracy in locating and depicting geological targets through numerical simulations and field tests.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2023)

Add to Collection

Article Geochemistry & Geophysics

Transdimensional Bayesian inversion of magnetotelluric data in anisotropic layered media with galvanic distortion correction

Ronghua Peng et al.

Summary: The presence of electrical anisotropy in the lithosphere can provide valuable insights into regional structures and tectonic processes, and can be imaged using magnetotelluric data. This study introduces a transdimensional Bayesian approach for inverting MT data in layered anisotropic media, which allows for flexible model parametrization and effectively addresses the effects of galvanic distortion.

GEOPHYSICAL JOURNAL INTERNATIONAL (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Instantaneous Inversion of Airborne Electromagnetic Data Based on Deep Learning

Sihong Wu et al.

Summary: The airborne electromagnetic (AEM) method is an effective means for subsurface electrical property reconstruction with the merits of terrain adaptability and acquisition efficiency. A fast inversion operator guided by deep learning is developed to translate time-domain AEM measurements directly into subsurface resistivity structures.

GEOPHYSICAL RESEARCH LETTERS (2022)

Add to Collection

Article Geochemistry & Geophysics

A Deep Learning Estimation of the Earth Resistivity Model for the Airborne Transient Electromagnetic Observation

Xin Wu et al.

Summary: This study proposes a deep learning method for processing airborne electromagnetic observation data, introduces a manifold assumption, and establishes a feedback mechanism between signal-noise distinguishing and signal-model mapping to obtain more reliable estimation results of earth resistivity model.

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH (2022)

Add to Collection

Article Environmental Sciences

Physics-Driven Deep Learning Inversion with Application to Magnetotelluric

Wei Liu et al.

Summary: This paper introduces a physics-driven deep learning method for geophysical inversion, which incorporates physics laws into network training and takes advantage of both data-driven and traditional physics-based methods to handle complex realistic exploration scenarios.

REMOTE SENSING (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Swin Transformer V2: Scaling Up Capacity and Resolution

Ze Liu et al.

Summary: This paper presents techniques for scaling Swin Transformer up to 3 billion parameters and the ability to train with high-resolution images. By increasing the capacity and resolution, Swin Transformer achieves new records on four representative vision benchmarks. Several novel technologies are proposed to address training instability and effectively transfer models from low-resolution to high-resolution. Using these techniques and self-supervised pre-training, a strong 3 billion Swin Transformer model is successfully trained, achieving state-of-the-art accuracy on various benchmarks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Inversion of 1D frequency- and time-domain electromagnetic data with convolutional neural networks

Vladimir Puzyrev et al.

Summary: This study examines the feasibility of using deep convolutional neural networks for the inversion of marine and onshore electromagnetic data, showing higher uncertainty in regions with resistivity anomalies. The proposed method opens up possibilities for real-time estimation of subsurface resistivity distribution in exploration scenarios.

COMPUTERS & GEOSCIENCES (2021)

Add to Collection

Article Geochemistry & Geophysics

Physics-driven deep-learning inversion with application to transient electromagnetics

Daniele Colombo et al.

Summary: By combining physics-driven and deep learning inversion approaches, utilizing the advantages and characteristics of both techniques, it is possible to achieve solutions that outperform individual inversions and bring the solution closer to the global minimum of a nonconvex inverse problem.

GEOPHYSICS (2021)

Add to Collection

Article Geochemistry & Geophysics

Recovering 3D Basement Relief Using Gravity Data Through Convolutional Neural Networks

Siyuan He et al.

Summary: The study introduces a new method for depth-to-basement inversion directly from gravity data using CNN and Random-Midpoint-Displacement to generate realistic models. While this method reduces the size of training data sets, it struggles to recover models like abrupt faults.

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Deep learning audio magnetotellurics inversion using residual-based deep convolution neural network

Zhengguang Liu et al.

Summary: A novel 18-layers residual full convolutional neural network (18RFCN) was developed for audio magnetotellurics (AMT) data inversion, achieving accurate results with minimal time consumption. The algorithm is based on big-data training and new methods for sample generation to improve network generalization.

JOURNAL OF APPLIED GEOPHYSICS (2021)

Add to Collection

Article Geochemistry & Geophysics

Application of Sample-Compressed Neural Network and Adaptive-Clustering Algorithm for Magnetotelluric Inverse Modeling

Weiqiang Liu et al.

Summary: This letter presents improvements to two machine learning algorithms for magnetotelluric (MT) inversion and boundary demarcation. The validity of these new algorithms is demonstrated using simulated and actual data, showing enhanced efficiency and automation in MT data inversion imaging.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

Add to Collection

Article Geochemistry & Geophysics

Two-dimensional deep learning inversion of magnetotelluric sounding data

Wei Liu et al.

Summary: The study introduces an inversion strategy based on deep learning deep belief network for instantaneous inversion of MT data, with improvements in convergence performance and global optimization capability through the introduction of scaled momentum learning rate and a novel activation function. The use of k-means++ algorithm for clustering MT field data as prior information is also highlighted. Experiments demonstrate the feasibility and effectiveness of the proposed DBN method for MT 2D inversion, showing promise in accurately delineating subsurface structures and performing rapid inversion.

JOURNAL OF GEOPHYSICS AND ENGINEERING (2021)

Add to Collection

Article Geochemistry & Geophysics

A theory-guided deep-learning formulation and optimization of seismic waveform inversion

Jian Sun et al.

GEOPHYSICS (2020)

Add to Collection

Article Geochemistry & Geophysics

Application of supervised descent method for 2D magnetotelluric data inversion

Rui Guo et al.

GEOPHYSICS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Window Selection of the Savitzky-Golay Filters for Signal Recovery From Noisy Measurements

Mohammad Sadeghi et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Add to Collection

Article Environmental Sciences

(Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network

Peng Bai et al.

REMOTE SENSING (2020)

Add to Collection

Article Geochemistry & Geophysics

A Physics-Driven Deep-Learning Network for Solving Nonlinear Inverse Problems

Yuchen Jin et al.

PETROPHYSICS (2020)

Add to Collection

Article Geochemistry & Geophysics

Convolutional neural network for seismic impedance inversion

Vishal Das et al.

GEOPHYSICS (2019)

Add to Collection

Article Metallurgy & Metallurgical Engineering

Nonlinear inversion for magnetotelluric sounding based on deep belief network

He Wang et al.

JOURNAL OF CENTRAL SOUTH UNIVERSITY (2019)

Add to Collection

Article Geochemistry & Geophysics

Efficient hierarchical trans-dimensional Bayesian inversion of magnetotelluric data

Enming Xiang et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2018)

Add to Collection

Article Geochemistry & Geophysics

Trans-dimensional Bayesian inversion of airborne transient EM data from Taylor Glacier, Antarctica

Daniel Blatter et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2018)

Add to Collection

Article Mathematics, Applied

Solving ill-posed inverse problems using iterative deep neural networks

Jonas Adler et al.

INVERSE PROBLEMS (2017)

Add to Collection

Article Geochemistry & Geophysics

3D inversion for multipulse airborne transient electromagnetic data

Yunhe Liu et al.

GEOPHYSICS (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

MTpy: A Python toolbox for magnetotellurics

Lars Krieger et al.

COMPUTERS & GEOSCIENCES (2014)

Add to Collection

Article Geochemistry & Geophysics

Three-dimensional parallel distributed inversion of CSEM data using a direct forward solver

A. V. Grayver et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2013)

Add to Collection

Article Geochemistry & Geophysics

Non-linearity in Bayesian 1-D magnetotelluric inversion

Rongwen Guo et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2011)

Add to Collection

Article Geochemistry & Geophysics

Non-linear conjugate gradient inversion for global EM induction: resolution studies

Anna Kelbert et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2008)

Add to Collection

Article Geochemistry & Geophysics

Determinable and non-determinable parameters of galvanic distortion in magnetotellurics

HM Bibby et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2005)

Add to Collection

Article Engineering, Electrical & Electronic

Properties of Savitzky-Golay digital differentiators

JW Luo et al.

DIGITAL SIGNAL PROCESSING (2005)

Add to Collection

Article Geochemistry & Geophysics

The magnetotelluric phase tensor

TG Caldwell et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2004)

Add to Collection

Article Environmental Sciences

A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky-Golay filter

J Chen et al.

REMOTE SENSING OF ENVIRONMENT (2004)

Add to Collection

Article Geochemistry & Geophysics

Nonlinear conjugate gradients algorithm for 2-D magnetotelluric inversion

W Rodi et al.

GEOPHYSICS (2001)

Add to Collection

Article Geochemistry & Geophysics

An efficient data-subspace inversion method for 2-D magnetotelluric data

W Siripunvaraporn et al.

GEOPHYSICS (2000)

Add to Collection

Article Geochemistry & Geophysics

Three-dimensional magnetotelluric inversion using non-linear conjugate gradients

GA Newman et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.