CORTEXA
← Browse
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24Cited by 0

Fast Prestack Wavefield Separation via 3D U-Net Knowledge Distillation

Alexander Shcherbina

We present a hybrid approach for automated prestack seismic data processing that combines expert-configured High-Resolution Wavefield Separation (HRWS) algorithms with 3D U-Net neural networks through knowledge distillation. The methodology uses HRWS with expert-tuned parameters to generate high-quality training targets, enabling neural networks to learn expert processing decisions. The model features a 51-channel input structure (50 amplitude offsets plus offset-density mask) and incorporates advanced attention mechanisms (CBAM, ASPP) for residual prediction. For industrial deployment, models are exported to ONNX format and deployed in distributed C++ environments with GPU acceleration. Experimental results demonstrate 15–20× speed improvement over classical methods while maintaining expert-level quality on diverse datasets without manual parameter tuning.

View free PDFSource page

Related papers

openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24

Implementation source code of Neural Computing and Applications (2023) 35:19279–19295 https://doi.org/10.1007/s00521-023-08717-4 ,- volV) (0123456789().,-volV)(0123456789().

Javeria Amin

Source Code for: Detection of Brain Space-Occupying Lesions Using Quantum Machine Learning", "description": "Source code for the four-phase deep-learning pipeline presented in Amin, J., Anjum, M. A., Gul, N., & Sharif, M. (2023), 'Detection of brain space-occupying lesions using…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-26

Electrical resistivity tomography surveys, trained physics-informed neural network models and code for amortized ERT inversion along Route Regionale 707, Moroccan Middle Atlas

Rajae Ajana

This deposit contains the field data, synthetic training datasets, trained network weights and analysis code supporting the article "Physics-informed neural network inversion of electrical resistivity tomography data: amortized optimization with field validation in the Moroccan M…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24

AI-Powered Fault Detection and Interpretation: From Neural Networks to Ready-to-Use Fault Surfaces

Alexander Shcherbina, Petr Popov, Ruslan Peisakhov, Yulia Sherman, Alex Berkovich

We present a comprehensive automated solution for 3D seismic fault detection and interpretation that combines deep learning with advanced geometric post-processing. The method integrates a 3D U-Net neural network trained on synthetic data with normalized distance function targets…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-25

QSM-CI method: BFRnet (v1)

Xuanyu Zhu, Yang Gao, Feng Liu, Stuart Crozier, Hongfu Sun

Deep-learning background field removal (BFRnet): a 3D dual-frequency octave-convolution U-net trained to predict the background field of the brain — including brains with significant pathological susceptibility sources (haemorrhage, calcification). Consumes the total field (ppm)…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-26

Output Management Plan For Its Honesty and Integrity

K. Yamada

July 25, 2026. Paper Permission: What Publisher AI Policies Allow and Practice Withholds AFS3.6: Paper Permission: What Publisher AI Policies Allow and Practice Withholds Names Paper Permission: a permission present in the text of publisher policy and largely absent from open pra…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-26

AI-Driven Intrusion Detection for the Internet of Things: A Scoping Review of Federated Learning, Privacy-Preserving Architectures, and Edge Deployability

Gilbert Aimufua, Godwin Agbonkhese

Federated learning has emerged as the dominant architectural response to the privacy and communication constraints of centralised intrusion detection in Internet of Things environments, yet the field lacks a synthesis that maps the concurrent state of architecture diversity, priv…

View free PDFSource page