Joint 3D inversion of gravity and magnetic data using deep learning neural networks

Wei, Nanyu; Yang, Dikun; Wang, Zhigang; Lu, Yuanxu

doi:10.1190/image2022-3751223.1

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One can rigorously use actual forward solutions or approximated forward solutions. In this study, we take the latter approach, following Shahriari et al, (2020) and Noh et al (2021 and2022). Thus, we need to solve the following minimization problem:…”

Section: Physics-guided DL Inversion Using An Approximated Forward So...mentioning

confidence: 99%

“…Historically, the development and application of inversion techniques have progressed by invoking assumptions in 1.5-dimensional (1.5Dassuming a three-dimensional source and a one-dimensional resistivity structure) (Zhang et al 2004, Bakr et al 2017, Wang et al 2017, Deleersnyder et al 2021, Wang et al 2021, 2.5-dimensional (2.5D) (Tabarovsky & Rabinovich 1998, Thiel et al 2018, and more recently to three-dimensional (Abubakar et al 2006, Puzyrev et al 2018, Marchant et al 2019 spaces. With the recent widespread utilization of machine learning (ML) algorithms, inversion using ML-and in particular, deep learning (DL)-has become a valuable alternative to traditional geophysical inversion methods (Araya-Polo et al 2018, Colombo et al 2021, Wei et al 2022. In electromagnetic logging applications, Jin et al (2019) invert 1.5D LWD resistivity measurements with a deep neural network (DNN) and a rigorous forward model by invoking a loss function that combines both model-and data-misfit; Shahriari et al (2021) construct a DNN approximation of both forward and inverse problems; Hu et al (2020) combine a gradient-based and a ML inversion method to enhance the generalization of training conditions; Noh et al (2021) and Noh et al (2022) considers multiple DL inversion architectures designed for varying geological situations for a 2.5D inversion of possibly fractured rocks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements

Noh

Pardo

Torres‐Verdín

2023

Geophysical Journal International

View full text Add to dashboard Cite

Summary Deep Learning (DL) inversion is a promising method for real-time interpretation of logging-while-drilling (LWD) resistivity measurements for well-navigation applications. In this context, measurement noise may significantly affect inversion results. Existing publications examining the effects of measurement noise on DL inversion results are scarce. We develop a method to generate training data sets and construct DL architectures that enhance the robustness of DL inversion methods in the presence of noisy LWD resistivity measurements. We use two synthetic resistivity models to test the three approaches that explicitly consider the presence of noise: (1) adding noise to the measurements in the training set, (2) augmenting the training set by replicating it and adding varying noise realizations, and (3) adding a noise layer in the DL architecture. Numerical results confirm that each of the three approaches enhances the noise-robustness of the trained DL inversion modules, yielding better inversion results—in both the predicted earth model and measurements—compared to the basic DL inversion and also to traditional gradient-based inversion results. A combination of the second and third approaches delivers the best results.

show abstract

Section: Physics-guided DL Inversion Using An Approximated Forward So...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements

Noh

Pardo

Torres‐Verdín

2023

Geophysical Journal International

View full text Add to dashboard Cite

show abstract

“…또 한, 비지도학습, 준지도학습, 전이학습과 같은 접근법으로 자료 부족 문제를 해결하기 위한 연구들도 수행되고 있고 (e.g., Alfarraj and AlRegib, 2019;Di et al, 2020;Liu et al, 2021a;Song et al, 2022) 료 간의 상호작용을 직접적으로 모델링하는 데 제한이 있 어 성능 저하의 가능성이 있다. 최근 물리탐사 분야 딥러닝 기반 복합역산 관련 연구의 대부분이 규격화된 자료를 통합하여 사용하는 초기 통합 방식을 따른다(e.g., Wei et al., 2022a;Jiao et al, 2023)…”

unclassified

Deep Learning in Geophysics: Current Status, Challenges, and Future Directions

Yu,

Oh,

Kong

et al. 2024

J. Korean Soc. Miner. Energy Resour. Eng.

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, machine learning and deep learning techniques have been actively applied in the field of exploration geophysics. In this study, we extensively investigated the application of deep learning in geophysical techniques including seismic, gravity, magnetic, electromagnetics, ground penetrating radar, and joint inversion. Recent research has confirmed that deep learning techniques optimized for geophysical problems are being developed that transcend traditional theory-based approaches, suggesting that deep learning is becoming a new paradigm in the field of geophysics. Despite these technological advances, there are still challenges to be overcome, such as a lack of training data, model opacity, and heterogeneity between training data and field data, and this study suggests future research directions to address these aspects.

show abstract

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Hu,

Wei,

et al. 2024

GEOPHYSICS

View full text Add to dashboard Cite

Utilizing multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multi-physics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

show abstract

Joint 3D inversion of gravity and magnetic data using deep learning neural networks

Cited by 4 publications

References 15 publications

Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements

Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements

Deep Learning in Geophysics: Current Status, Challenges, and Future Directions

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Contact Info

Product

Resources

About