Reconstructing multidimensional vector fields from path-integrated projection data is a fundamental challenge in high-energy-density physics, particularly when experimental sources exhibit spectral broadening and shot-to-shot jitter. We present a physics-guided deep-learning framework that addresses this ill-posed inverse problem by formulating global reconstruction as an aggregation of local inference tasks. By training a neural network on single-particle trajectories in randomized uniform magnetic fields, we develop a “local solver” that demonstrates strong zero-shot transfer to previously unseen magnetohydrodynamic topologies. Central to addressing non-ideal laser-driven proton sources, we introduce a spectral out-of-distribution filter that rejects inputs outside the training energy envelope. By preventing extrapolation, the filter enables accurate reconstruction within the represented training domain while maintaining stable populated-cell reconstruction metrics across diverse spectral conditions. Furthermore, we introduce an a priori reconstruction-reliability indicator based on the in-distribution fraction of the source spectrum, which provides a practical estimate of reconstruction coverage before inference. This approach can be integrated with energy-resolved detector systems, such as stacked nuclear track detectors, establishing a practical and highly parallelizable framework for quantitative plasma diagnostics.
Radio telescope arrays are constrained by the number of antennas and baseline distribution, resulting in incomplete spatial-frequency sampling, limited image resolution, and blurring, distortion, and loss of small-scale structures caused by coupling between the primary and synthesized beams. Existing general-purpose model-driven methods remove observational effects sequentially and may accumulate errors, but cannot directly address limited imaging resolution, while data-driven methods lack explicit physical constraints. We propose PhySR, an end-to-end physics-informed neural network that combines a U-Net backbone, dynamic cascaded upsampling, a multiscale feature residual module, and a differentiable physical forward model incorporating the primary beam response, PSF convolution, and scale mapping. PhySR directly reconstructs high-resolution images from low-resolution dirty images without high-resolution labels while maintaining observation-domain consistency. Experiments on simulated SKA-Mid data show that, for 4x super-resolution, PhySR achieves a PSNR of 44.65 dB, an SSIM of 0.9940, and an RMSE of 0.0065. Compared with existing general-purpose methods, PSNR and SSIM improve by approximately 13.23 dB and 0.3760, respectively. Compared with mainstream deep learning models, PSNR and SSIM improve by 6.50 dB and 0.0682, while RMSE decreases by 0.0069. PhySR also remains stable for 2x and 8x super-resolution and achieves low observation-domain consistency errors, demonstrating advantages in coupling-effect removal, small-scale structure recovery, and physical consistency.
Hongkun Yang, Li Zhang, Ming Zhang et al.· 0 citations
OBJECTIVE
Magnetic Particle Imaging (MPI) is a promising, emerging medical imaging modality. MPI is based on the non-linear response of magnetic nanoparticles to an applied magnetic field and does not expose the specimen to ionizing radiation. The measured signal is the voltage induced in receive coils by the particles' response. Reconstructing the particle concentration from the signal constitutes the imaging task. Even using state-of-the-art measurement-based reconstruction, the associated spatial grid is very coarse, hence super-resolution techniques are important. In this work, we propose an approach for super-resolution in MPI inspired by energy minimization. Approach. Different methods have been proposed for super-resolution in MPI, ranging from upscaling of the associated system matrix to interpolation of the reconstruction. Here we incorporate super-resolution into the reconstruction task via an energy minimization formulation. Following the plug-and-play approach to energy minimization we derive a splitting scheme where the arising Gaussian denoising task is treated with a pre-trained learned Gaussian denoiser. Main results. We derive a super-resolution method for MPI based on a plug-and-play approach using a pre-trained denoiser in zero-shot fashion. This way, we incorporate benefits of deep learning without training and avoid the need of training data. Further, we provide a quantitative and qualitative evaluation of the proposed method on simulated data with realistic noise. Hyper-parameters are selected via an extended parameter search. The found parameters are applied for reconstruction on real data. We qualitatively show the applicability of our method on real data (MPIData: EquilibriumModelWithAnisotropy and 2D-OpenMPI Data). Significance. The proposed method employs a deep-learning denoiser without training -- thus it does not require presently scarcely available MPI training data. The denoiser behaves conservatively, i.e., no hallucination artifacts were observed. The super-resolution approach is generic such that it can be applied in future MPI contexts involving different regularizers or different imaging tasks.
Vladyslav Gapyak, Thomas März, Andreas Weinmann· Physics in Medicine and Biol...· 0 citations
High-repetition-rate (10 Hz) laser-plasma experiments require rapid and reliable reconstruction of X-ray spectra from scintillator-based linear absorption spectrometer measurements. The inverse problem is intrinsically ill-posed and complicated by practical detector non-idealities such as digitisation, saturation, and noise. In this work, we present a machine learning-based reconstruction framework that enables rapid spectral inference under realistic detector conditions, without a priori assumptions on spectral shape during inference. The approach separates spectral shape from flux, allowing an ensemble of neural networks to infer spectral shape from normalised detector measurements, while flux is recovered in a subsequent step. Training data comprises a collection of physically interpretable, multi-component spectra formed from mixtures of Boltzmann and skewed Gaussian components, enabling generalisation beyond simple parametric forms. Models are trained on synthetic data incorporating detector non-idealities. Comparison is performed with existing multi-parameter deconvolution method, demonstrating comparable performance in the presence of detector non-idealities, with approximately two orders of magnitude faster inference. A comprehensive evaluation is performed examining the role of training distribution, measurement-space data augmentation, and detector response. Results demonstrate robust reconstruction across diverse spectral morphologies and flux levels, with millisecond-level inference times suitable for high-repetition-rate experiments.
Anandaeaswaran Brainthra, C. Armstrong, G. Scott et al.· Machine Learning: Science an...· 0 citations
Reconstructing unknown electromagnetic sources from far-field radiation patterns is a fundamental inverse problem with broad applications in biomedical imaging, non-destructive testing, and telecommunications. In practical settings, however, collecting dense multi-frequency far-field measurements at the Nyquist sampling rate is often infeasible. Under-sampled or sparse data introduce non-radiating source components that sever the uniqueness of the solution, creating severe artifacts when standard inversion techniques are applied. To overcome this limitation, we present a two-stage reconstruction strategy exploiting the physical property that compactly supported, geometrically sparse sources exhibit a finite rate of innovations (FRI). In the first stage, we construct an associated wrap-around structured Hankel matrix. By leveraging the low-rank property of the matrix due to FRI of the unknown sources, we enrich the sub-sampled data. To that end, we convert missing multi-frequency far-field data recovery into a constrained matrix completion task solved via Annihilating Filter-based Low-rank Hankel Matrix Completion Approach (ALOHA). In the second stage, a Fourier inversion scheme reconstructs the current source density from the enriched dataset. Extensive numerical evaluations on electromagnetic source models show that our enrichment framework effectively eliminates under-sampling artifacts and resolves non-uniqueness challenges. The method delivers accurate and stable reconstructions under high sub-sampling rates (e.g., with $30$\% to $50$\% available samples) and strong noise conditions ($10$ dB SNR), outperforming standard $\ell_1$-compressed sensing baselines.
Atyab Khalifa Al-Shaqsi, Heba Mohammed Al-Subhi, Xianchao Wang et al.· 1 citation
EpiC-NeRF is proposed, a CT-specific closed-loop framework that actively feeds estimated epistemic uncertainty back into sparse-view reconstruction and achieves improved reconstruction fidelity over existing analytic, iterative, and neural implicit reconstruction methods.
Donghyuk Choo, Haill An, Younhyun Jung· Mathematics· 0 citations
Non-intrusive optical measurement techniques are widely used to obtain high-resolution pressure, temperature, and velocity fields, but they often suffer from random data loss caused by geometric obstruction, surface reflection, or illumination non-uniformity. Conventional reconstruction methods usually depend on high-fidelity CFD priors or large paired datasets, which limits their flexibility for arbitrary missing patterns and scarce experimental samples. This study proposes a Physics-Informed Multi-Scale Resampled Denoising Diffusion Probabilistic Model (MSR-DDPM) for missing-data reconstruction in optical flow measurements. The method shifts the reconstruction paradigm from deterministic mapping to probabilistic distribution modeling. Three features are introduced: a multi-scale hierarchical reconstruction strategy that reduces computational cost by 56% and improves stability; embedded physics-informed constraints, including divergence and gradient-continuity terms, to enhance physical consistency and reduce dependence on large training datasets; and an optional conditional diffusion module that incorporates auxiliary low-fidelity data for extreme missing-data scenarios. The framework is validated for incompressible velocity-field imputation using turbine cascade passage data, demonstrating its ability to recover complex unsteady flow structures. For missing ratios of 10%-45%, MSR-DDPM achieves high-accuracy reconstruction with Symmetric Mean Absolute Percentage Error (SMAPE) below 6% without auxiliary data. Under more severe missing ratios of 45%-65%, auxiliary guidance substantially recovers flow details and reduces reconstruction errors by approximately 60%. These results indicate that MSR-DDPM offers a flexible, data-efficient, and physically consistent solution for missing-data imputation in complex experimental flow measurements.
Bo Yu, Pingting Chen, JunKui Mao· Journal of turbomachinery· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
