Self-Supervised Knowledge-Driven Deep Learning for 3D Magnetic Inversion

• URL: http://arxiv.org/abs/2308.12193v1
• Date: Wed, 23 Aug 2023 15:31:38 GMT
• Title: Self-Supervised Knowledge-Driven Deep Learning for 3D Magnetic Inversion
• Authors: Yinshuo Li, Zhuo Jia, Wenkai Lu, Cao Song
• Abstract summary: The proposed self-supervised knowledge-driven 3D magnetic inversion method learns on the target field data by a closed loop of the inversion and forward models. There is a knowledge-driven module in the proposed inversion model, which makes the deep learning method more explicable. The experimental results demonstrate that the proposed method is a reliable magnetic inversion method with outstanding performance.
• Score: 6.001304967469112
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The magnetic inversion method is one of the non-destructive geophysical methods, which aims to estimate the subsurface susceptibility distribution from surface magnetic anomaly data. Recently, supervised deep learning methods have been widely utilized in lots of geophysical fields including magnetic inversion. However, these methods rely heavily on synthetic training data, whose performance is limited since the synthetic data is not independently and identically distributed with the field data. Thus, we proposed to realize magnetic inversion by self-supervised deep learning. The proposed self-supervised knowledge-driven 3D magnetic inversion method (SSKMI) learns on the target field data by a closed loop of the inversion and forward models. Given that the parameters of the forward model are preset, SSKMI can optimize the inversion model by minimizing the mean absolute error between observed and re-estimated surface magnetic anomalies. Besides, there is a knowledge-driven module in the proposed inversion model, which makes the deep learning method more explicable. Meanwhile, comparative experiments demonstrate that the knowledge-driven module can accelerate the training of the proposed method and achieve better results. Since magnetic inversion is an ill-pose task, SSKMI proposed to constrain the inversion model by a guideline in the auxiliary loop. The experimental results demonstrate that the proposed method is a reliable magnetic inversion method with outstanding performance.

Related papers

• Physically Guided Deep Unsupervised Inversion for 1D Magnetotelluric Models [16.91835461818938]
  We present a new deep inversion algorithm guided by physics to estimate 1D Magnetotelluric (MT) models. Our method employs a differentiable modeling operator that physically guides the cost function minimization. We test the proposed method with field and synthetic data at different frequencies, demonstrating that the acquisition models are more accurate than other results.
  arXiv  Detail & Related papers  (2024-10-20T04:17:59Z)
• 3-D Magnetotelluric Deep Learning Inversion Guided by Pseudo-Physical Information [11.303727578628575]
  Magnetotelluric deep learning (DL) inversion methods based on joint data-driven and physics-driven have become a hot topic in recent years. We introduce pseudo-physical information through the forward modeling of neural networks (NNs) to compute this portion of the loss. We propose a new input mode that involves masking and adding noise to the data, simulating the field data environment of 3-D MT inversion.
  arXiv  Detail & Related papers  (2024-10-12T06:39:31Z)
• Phase-Based Approaches for Rapid Construction of Magnetic Fields in NV Magnetometry [9.378134074181768]
  This paper looks into estimating the magnetic field from the Optically Detected Magnetic Resonances (ODMR) signal. Mapping the shifts of ODMR signals to phase estimation, a computationally efficient approaches are proposed. Results show a significant reduction in computational time with the proposed method over existing methods.
  arXiv  Detail & Related papers  (2024-08-17T08:58:27Z)
• Magnetic Hysteresis Modeling with Neural Operators [0.7817677116789855]
  This paper proposes neural operators for modeling laws that exhibit magnetic by learning a mapping between magnetic fields. Two prominent neural operators -- deep operator network and Fourier neural operator -- are employed to predict novel first-order reversal curves and minor loops.
  arXiv  Detail & Related papers  (2024-07-03T16:45:45Z)
• Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory [53.37473225728298]
  The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data. Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. We introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory.
  arXiv  Detail & Related papers  (2024-06-28T11:06:46Z)
• A Bionic Data-driven Approach for Long-distance Underwater Navigation with Anomaly Resistance [59.21686775951903]
  Various animals exhibit accurate navigation using environment cues. Inspired by animal navigation, this work proposes a bionic and data-driven approach for long-distance underwater navigation. The proposed approach uses measured geomagnetic data for the navigation, and requires no GPS systems or geographical maps.
  arXiv  Detail & Related papers  (2024-02-06T13:20:56Z)
• Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models [63.1637853118899]
  We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. We employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions.
  arXiv  Detail & Related papers  (2023-10-15T18:44:30Z)
• Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
  The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
  arXiv  Detail & Related papers  (2023-10-09T14:30:06Z)
• Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning [16.224372286510558]
  Reward shaping is a practical approach to improving sample efficiency by embedding human domain knowledge into the learning process. This paper proposes a novel magnetic field-based reward shaping (MFRS) method for goal-conditioned RL tasks with dynamic target and obstacles. Experiments results in both simulated and real-world robotic manipulation tasks demonstrate that MFRS outperforms relevant existing methods.
  arXiv  Detail & Related papers  (2023-07-16T13:04:40Z)
• Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation [151.70234052015948]
  We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
  arXiv  Detail & Related papers  (2022-11-20T15:49:11Z)
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks [81.64530401885476]
  We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties. Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns. We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
  arXiv  Detail & Related papers  (2020-10-19T09:23:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.