arXiv subjects

Mingwei Wang

Publications and source records attributed to Mingwei Wang.

17 recordsLinked to original sources

arXiv2026

Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imaging

Acoustic impedance imaging is a fundamental yet severely ill-posed problem in subsurface analysis: the seismic wavelet is unknown, observations are band-limited, and labeled well-log samples are extremely scarce (typically <1% of all traces). Existing semi-supervised deep learning methods mitigate few-shot problem by incorporating forward modeling, yet they either rely on inaccurate prior wavelet assumptions or introduce auxiliary networks, leading to unstable optimization and degraded performance. We propose RD-SCL, a novel framework that integrates regularized deconvolution with semi-supervised cross-learning. At its core lies a differentiable, closed-form first-order Tikhonov deconvolution operator that dynamically estimates the latent wavelet in the frequency domain during training, providing stable physics-guided feedback without explicit auxiliary networks and fixed wavelet priors. Building on this operator, we design a symmetric cross-learning that enforces consistency between predictions on labeled and unlabeled data, thereby effectively exploiting abundant unlabeled traces. Extensive experiments on the SEAM and Marmousi 2 benchmarks demonstrate that RD-SCL consistently outperforms state-of-the-art supervised and semi-supervised methods, achieving substantial gains with lower computational cost. With only 56.5k learnable parameters and competitive runtime, RD-SCL offers a practical, physically consistent, and efficient solution for acoustic impedance imaging.

cs.CV↗

arXiv2026

Existence of twisted Hermitian-Einstein metrics on unstable vector bundles

In this paper, we demonstrate that twisted Hermitian-Einstein metrics on holomorphic vector bundles exist without obstruction. More precisely, for an arbitrary holomorphic vector bundle $E$ over a compact K\"ahler manifold $(M,\omega_g)$, we prove that the twisted Hermitian-Einstein equation $$\Lambda_{\omega_g}\left(\sqrt{-1}R^h\right) = \lambda h + P$$ admits a unique smooth solution $h$, provided that $P\in\Gamma(M,E^*\otimes\bar{E}^*)$ is positive-definite and $\lambda<\lambda_E^-$. The constant $\lambda_E^-$ is intrinsically associated with the stability constant of $E$. This result extends the classical Donaldson-Uhlenbeck-Yau (DUY) theorem for stable bundles and, in the limit $P\rightarrow0$, gives a new proof of the DUY theorem. As an application, we obtain an intrinsic Chern number inequality for unstable vector bundles: $$\int_M \left((r-1)c_1(E)^2 - 2rc_2(E)\right) \wedge \omega_g^{n-2} \leq \Bigl\lfloor \frac{r^2}{4} \Bigr\rfloor \frac{(\lambda_E^+-\lambda_E^-)^2}{4\pi^2 n^2} \int_M \omega_g^n.$$

math.DG↗

arXiv2026

Existence of Hermitian metrics with prescribed Hermitian-Yang-Mills tensors II

In this paper, we solve the prescribed Hermitian-Yang-Mills tensor problem for Higgs bundles over compact complex manifolds. Let $ (E,\theta) $ be a Higgs bundle over a compact Hermitian manifold $(M,\omega_g) $. Suppose that there exists a smooth Hermitian metric $ h_0 $ on $E$ such that the Hermitian-Yang-Mills tensor $ \Lambda_{\omega_g}\left(\sqrt{-1} R^{D^{h_0}}\right) $ of the Higgs connection is positive definite. Then for any Hermitian positive definite tensor $ P\in \Gamma\left(M,E^*\otimes \bar E^*\right) $, there exists a unique smooth Hermitian metric $ h $ on $E$ such that $$\Lambda_{\omega_g} \left(\sqrt{-1} R^{D^h}\right)=P.$$ We also establish quantitative Chern number inequalities for Higgs bundles.

math.DG↗

arXiv2026

Existence of Hermitian metrics with prescribed Hermitian-Yang-Mills tensors I

In this paper, we solve the prescribed Hermitian-Yang-Mills tensor problem. Let $ E $ be a holomorphic vector bundle over a compact K\"ahler manifold $(M,\omega_g) $. Suppose that there exists a smooth Hermitian metric $ h_0 $ on $E$ such that the Hermitian-Yang-Mills tensor $ \Lambda_{\omega_g}\left(\sqrt{-1} R^{h_0}\right) $ is positive-definite. Then for any positive-definite Hermitian tensor $ P\in \Gamma\left(M,E^*\otimes \overline E^*\right) $, there exists a unique smooth Hermitian metric $ h $ on $E$ such that $$\Lambda_{\omega_g} \left(\sqrt{-1} R^h\right)=P.$$ The proof is based on a new comparison theorem for Hermitian-Yang-Mills tensors. Inspired by these results, we have also derived quantitative Chern number inequalities that apply to both holomorphic vector bundles and compact K\"ahler manifolds.

math.DG↗

arXiv2025

KOSS: Kalman-Optimal Selective State Spaces for Long-Term Sequence Modeling

Recent selective state space models (SSMs), such as Mamba and Mamba-2, have demonstrated strong performance in sequence modeling owing to input-dependent selection mechanisms. However, these mechanisms lack theoretical grounding and cannot support context-aware selection from latent state dynamics. To address these limitations, we propose KOSS, a Kalman-optimal Selective State Space model that formulates selection as latent state uncertainty minimization. Derived from estimation theory, KOSS adopts a continuous-time latent update driven by a Kalman gain that dynamically modulates information propagation based on content and context, enabling a closed-loop, context-aware selectivity mechanism. To ensure stable computation and near-linear scalability, KOSS employs global spectral differentiation for frequency-domain derivative estimation, along with a segment-wise scan for hardware-efficient processing. On a selective copying task with distractors, KOSS achieves over 79\% accuracy while baselines drop below 20\%, demonstrating robust context-aware selection. Furthermore, across nine long-term forecasting benchmarks, KOSS reduces MSE by 2.92--36.23\% and consistently outperforms state-of-the-art models in both accuracy and stability. To assess real-world applicability, a case study on secondary surveillance radar (SSR) tracking confirms KOSS's robustness under irregular intervals and noisy conditions and demonstrates its effectiveness in real-world applications. Finally, supplementary experiments verify Kalman gain convergence and the frequency response of spectral differentiation, providing theoretical support for the proposed closed-loop design.

cs.LG↗

arXiv2025

Physics-Informed Cross-Learning for Seismic Acoustic Impedance Inversion and Wavelet Extraction

Seismic acoustic impedance inversion is one of the most challenging tasks in geophysical exploration. Many studies have proposed the use of deep learning for processing; however, most of them are limited by factors such as seismic wavelets and low-frequency initial models. Furthermore, self-supervised frameworks constructed entirely using deep learning models struggle to form direct and effective physical constraints to unlabeled outputs during the multi-model concatenation, which leads to instability in inversion. In this work, we introduced innovations in both the deep learning framework and training strategy. First, we designed a deep learning framework to perform acoustic impedance inversion and seismic wavelet extraction simultaneously. Building on this foundation, considering the scarcity of well data, we proposed a physics-informed cross-learning strategy to impose effective constraints on the framework. We conducted comparative experiments and ablation experiments on both synthetic datasets and field datasets. The results demonstrate that the proposed method achieves a significant improvement compared with semi-supervised learning methods and can extract seismic wavelets with relatively high accuracy. Finally, to ensure the reproducibility of this work, we have made the code open-source.

physics.geo-ph↗

arXiv2025

Weitzenb\"ock-Bochner-Kodaira formulas with quadratic curvature terms

In this paper we establish new Bochner-Kodaira formulas with quadratic curvature terms on compact K\"ahler manifolds: for any $\eta\in \Omega^{p,q}(M)$, $$ \left\langle\Delta_{\overline \partial} \eta,\eta\right\rangle =\left\langle \Delta_{{\overline\partial}_F} \eta,\eta\right\rangle +\frac{1}{4}\left\langle \left(\mathcal {R} \otimes \mathrm{Id}_{\Lambda^{p+1,q-1}T^*M}\right)(\mathbb T_\eta),\mathbb T_\eta \right\rangle. $$ This linearized curvature term yields new vanishing theorems and provides estimates for Hodge numbers under exceptionally weak curvature conditions. Furthermore, we derive Weitzenb\"ock formulas with quadratic curvature terms on both Riemannian and K\"ahler manifolds.

math.DG↗

arXiv2025

Encoder-Inverter Framework for Seismic Acoustic Impedance Inversion

Seismic acoustic impedance inversion is a challenging problem in geophysical exploration, primarily due to the scarcity of well-logging data and the inherent nonlinearity of the task. Most existing inversion methods, including semi-supervised learning approaches, still face limitations in accuracy and robustness. In this work, we propose a novel Encoder-Inverter framework that maps continuous seismic traces into high-dimensional linear features, thereby transforming the inversion task into a linear extrapolation or interpolation problem to enhance stability and performance. To achieve this, we introduce two auxiliary models to assist in encoder training and adopt a heterogeneous model structure to prevent shortcut learning, enabling the extraction of more generalizable and effective linear features. We evaluate the proposed method on widely used benchmark datasets, and experimental results demonstrate that our approach achieves superior inversion accuracy and robustness compared to previous methods. To promote reproducibility, we will also open-source the data and code.

physics.geo-ph↗

arXiv2025

First eigenvalue estimates on complete K\"ahler manifolds

Let $ (M,\omega_g) $ be a complete K\"ahler manifold of complex dimension $n$. We prove that if the holomorphic sectional curvature satisfies $\mathrm{HSC} \geq 2 $, then the first eigenvalue $\lambda_1$ of the Laplacian on $(M,\omega_g)$ satisfies $$ \lambda_1 \geq \frac{320(n-1)+576}{81(n-1)+144}.$$ This result is established through a new Bochner-Kodaira type identity specifically developed for holomorphic sectional curvature.

math.DG↗

arXiv2025

Strong noise attenuation of seismic data based on Nash equilibrium

Seismic data acquisition is often affected by various types of noise, which degrade data quality and hinder subsequent interpretation. Recovery of seismic data becomes particularly challenging in the presence of strong noise, which significantly impacts both data accuracy and geological analysis. This study proposes a novel single-encoder, multiple-decoder network based on Nash equalization (SEMD-Nash) for effective strong noise attenuation in seismic data. The main contributions of this method are as follows: First, we design a shared encoder-multi-decoder architecture, where an improved encoder extracts key features from the noisy data, and three parallel decoders reconstruct the denoised seismic signal from different perspectives. Second, we develop a multi-objective optimization system that integrates three loss functions-Mean Squared Error (MSE), Perceived Loss, and Structural Similarity Index (SSIM)-to ensure effective signal reconstruction, high-order feature preservation, and structural integrity. Third, we introduce the Nash Equalization Weight Optimizer, which dynamically adjusts the weights of the loss functions, balancing the optimization objectives to improve the models robustness and generalization. Experimental results demonstrate that the proposed method effectively suppresses strong noise while preserving the geological characteristics of the seismic data.

physics.geo-ph↗

arXiv2025

Semi-Supervised Learning for AVO Inversion with Strong Spatial Feature Constraints

One-dimensional convolution is a widely used deep learning technique in prestack amplitude variation with offset (AVO) inversion; however, it lacks lateral continuity. Although two-dimensional convolution improves lateral continuity, due to the sparsity of well-log data, the model only learns weak spatial features and fails to explore the spatial correlations in seismic data fully. To overcome these challenges, we propose a novel AVO inversion method based on semi-supervised learning with strong spatial feature constraints (SSFC-SSL). First, two-dimensional predicted values are obtained through the inversion network, and the predicted values at well locations are sparsely represented using well-log labels. Subsequently, a label-annihilation operator is introduced, enabling the predicted values at non-well locations to learn the spatial features of well locations through the neural network. Ultimately, a two-way strong spatial feature mapping between non-well locations and well locations is achieved. Additionally, to reduce the dependence on well-log labels, we combine the semi-supervised learning strategy with a low-frequency model, further enhancing the robustness of the method. Experimental results on both synthetic example and field data demonstrate that the proposed method significantly improves lateral continuity and inversion accuracy compared to one- and two-dimensional deep learning techniques.

physics.geo-ph↗

arXiv2024

An Efficient Self-supervised Seismic Data Reconstruction Method Based on Self-Consistency Learning

Seismic exploration remains the most critical method for characterizing subsurface structures in geophysics. However, complex surface conditions often cause a non-uniform distribution of seismic receivers along survey lines, leading to irregularly acquired seismic data, which affects subsequent processing and inversion. Prior deep learning-based seismic data reconstruction methods typically rely on datasets for supervised training. While some existing methods avoid extra data, they lack effective constraints on reconstructed data, leading to unstable performance. In this study, we propose a self-supervised self-consistency learning strategy with a lightweight network for seismic data reconstruction. Our method requires no extra datasets, and it leverages inter-component correlations in seismic data to design a loss function, optimizing a network with only 188,849 learnable parameters. Validated on two public seismic datasets, results demonstrate our approach yields high-quality reconstruction, providing significant value for large-scale and complex seismic exploration tasks.

eess.IV↗

arXiv2024

Prior-Driven Self-Supervised Lightweight Method for Seismic Signal Denoising

Seismic exploration is currently the most mature approach for studying subsurface structures, yet the presence of noise greatly restricts its imaging accuracy. Previous methods still face significant challenges: traditional computational methods are often computationally complex and their effectiveness is hard to guarantee; deep learning methods rely heavily on datasets, and the complexity of network training makes them difficult to apply in practical field scenarios. In this paper, we proposed a neural network that has only 2464 learnable parameters, which is hundreds or even thousands of times lower than that of the current mainstream deep learning networks. And its parameter constraints rely on priors rather than requiring training data. We proposed two types of priors: the local prior and the global variance prior for self-supervised learning, and put forward low-scale learning to further enhance its performance in noise processing. We validated our method on both synthetic and field data, and the results indicate that our proposed approach effectively attenuates random noise.

physics.geo-ph↗

arXiv2024

Machine Learning-Based Research on the Adaptability of Adolescents to Online Education

With the rapid advancement of internet technology, the adaptability of adolescents to online learning has emerged as a focal point of interest within the educational sphere. However, the academic community's efforts to develop predictive models for adolescent online learning adaptability require further refinement and expansion. Utilizing data from the "Chinese Adolescent Online Education Survey" spanning the years 2014 to 2016, this study implements five machine learning algorithms - logistic regression, K-nearest neighbors, random forest, XGBoost, and CatBoost - to analyze the factors influencing adolescent online learning adaptability and to determine the model best suited for prediction. The research reveals that the duration of courses, the financial status of the family, and age are the primary factors affecting students' adaptability in online learning environments. Additionally, age significantly impacts students' adaptive capacities. Among the predictive models, the random forest, XGBoost, and CatBoost algorithms demonstrate superior forecasting capabilities, with the random forest model being particularly adept at capturing the characteristics of students' adaptability.

cs.LG↗

arXiv2024

High-resolution closed-loop seismic inversion network in time-frequency phase mixed domain

Thin layers and reservoirs may be concealed in areas of low seismic reflection amplitude, making them difficult to recognize. Deep learning (DL) techniques provide new opportunities for accurate impedance prediction by establishing a nonlinear mapping between seismic data and impedance. However, existing methods primarily use time domain seismic data, which limits the capture of frequency bands, thus leading to insufficient resolution of the inversion results. To address these problems, we introduce a new time-frequency-phase (TFP) mixed-domain closed-loop seismic inversion network (TFP-CSIN) to improve the identification of thin layers and reservoirs. First, the inversion network and closed-loop network are constructed by using bidirectional gated recurrent units (Bi-GRU) and convolutional neural network (CNN) architectures, enabling bidirectional mapping between seismic data and impedance data. Next, to comprehensive learning across the entire frequency spectrum, the Fourier transform is used to capture frequency information and establish frequency domain constraints. At the same time, the phase domain constraint is introduced through Hilbert transformation, which improves the method's ability to recognize the weak reflection region features. Both experiments on the synthetic data show that TFP-CSIN outperforms the traditional supervised learning method and time domain semi-supervised learning methods in seismic inversion. The field data further verify that the proposed method improves the identification ability of weak reflection areas and thin layers.

physics.geo-ph↗

arXiv2023

Distance Guided Generative Adversarial Network for Explainable Binary Classifications

Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification.

cs.CV↗

arXiv2022

Channel Estimation for Reconfigurable Intelligent Surface-Assisted Cell-Free Communications

Recent research has focused on reconfigurable intelligent surface (RIS)-assisted cell-free systems with the goal of enhancing coverage and lowering the cost of cell-free networks. However, current research makes the assumption that the perfect channel state information is known. Channel acquisition is, certainly, a difficulty in this case. This work is aimed at investigating RIS-assisted cell-free channel estimation. Toward this end, two unique characteristics are pointed out: 1) For all users, a common channel exists between the base station (BS) and the RIS; and 2) For all BSs, a common channel exists between the RIS and the user. Based on these two characteristics, cascaded and two-timescale channel estimation concerns are studied. Subsequently, two solutions for tackling with the two issues are presented respectively: a three-dimensional multiple measurement vector (3D-MMV)-based compressive sensing technique and a multi-BS cooperative pilot-reduced methodology. Finally, simulations illustrate the effectiveness of the schemes we have presented.

eess.SP↗