Nickolas Winovich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nickolas Winovich has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
Albuquerque Sandia National Laboratories (Snl-Nm)
5 shared publicationsUsdoe National Nuclear Security Administration (Nnsa)
5 shared publications- Chinmay Sahasrabudhe
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
2 shared publications - Liam Moynihan
Sandia National Laboratories, Albuquerque, NM, USA
2 shared publications - Mohamed Ebeida
Sandia National Laboratories, Albuquerque, NM, USA
2 shared publications - Yang Ho
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
2 shared publications
Latest Publications
- 29 October 2026
- Published by Elsevier in Computer-Aided Design
- Vol. 203
Configuration-aware mesh quality prediction for tetrahedral meshing and CAD defeaturing
- 29 October 2026
- Published by Elsevier in Computer-Aided Design
- Vol. 203
Configuration-aware mesh quality prediction for tetrahedral meshing and CAD defeaturing
- Open Access
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 15071-15089
VoroClust: Scalable Clustering for Remote Sensing
Although supervised machine learning provides a powerful framework for image classification and segmentation, it requires comprehensive, consistent data sets, which are not available for many remote-sensing applications. Remote-sensing datasets are expensive to collect, and each is acquired under different environmental conditions, or with significant variations in system operating parameters. Unsupervised clustering algorithms analyze the structure of each dataset independently, rather than drawing on similarities with existing ‘training’ examples, and are thus well suited for practical remote-sensing applications. We introduce VoroClust, a fast, density-based unsupervised clustering algorithm applicable to high-resolution and highdimensional data. VoroClustruns as fast as distance-based clustering methods, while capturing complex regional geometries at least as well as current density-based methods. It uses a datacentered sphere cover to reduce computational demands, while still capturing data topology. It then propagates clusters outward from local peaks in density. We show that VoroClustprovides fast, state-of-the-art clustering for both high-resolution polarimetric synthetic aperture radar (PolSAR) and high-dimensional hyperspectral imaging (HSI) datasets.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 15071-15089
Open AccessVoroClust: Scalable Clustering for Remote Sensing
Although supervised machine learning provides a powerful framework for image classification and segmentation, it requires comprehensive, consistent data sets, which are not available for many remote-sensing applications. Remote-sensing datasets are expensive to collect, and each is acquired under different environmental conditions, or with significant variations in system operating parameters. Unsupervised clustering algorithms analyze the structure of each dataset independently, rather than drawing on similarities with existing ‘training’ examples, and are thus well suited for practical remote-sensing applications. We introduce VoroClust, a fast, density-based unsupervised clustering algorithm applicable to high-resolution and highdimensional data. VoroClustruns as fast as distance-based clustering methods, while capturing complex regional geometries at least as well as current density-based methods. It uses a datacentered sphere cover to reduce computational demands, while still capturing data topology. It then propagates clusters outward from local peaks in density. We show that VoroClustprovides fast, state-of-the-art clustering for both high-resolution polarimetric synthetic aperture radar (PolSAR) and high-dimensional hyperspectral imaging (HSI) datasets.
- Top Cited Papers
- 21 February 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 555
Active operator learning with predictive uncertainty quantification for partial differential equations
- 21 February 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 555
Top Cited PapersActive operator learning with predictive uncertainty quantification for partial differential equations
- Open Access
- 1 September 2025
- Published by Office of Scientific and Technical Information (OSTI)
Replace Human Intelligence with Fast and Smart Geometric Reasoning and Graph Neural Network to Accelerate Next Gen ModSim Workflows
We present an agent-guided approach to CAD geometry decomposition that automates hex/hybrid meshing with graph neural networks (GNNs) to accelerate next-generation ModSim workflows. Our end-to-end pipeline (i) reduces 3D boundary-representation (B-Rep) models to a 2D chordalaxis skeleton (CAT) and then to a 1D bipartite graph of surface and curve nodes, (ii) assigns pernode labels as Cubit® WebCut actions, (iii) trains a multi-action GNN under supervised learning, and (iv) predicts five surface-node and three curve-node actions on out-of-distribution test geometries. Each graph node carries geometric, topological, and meshing attributes drawn from the B-Rep "skin" and CAT "skeleton," with two-way mappings across 3D↔2D↔1D representations to maintain traceability back to 3D CAD. The supervised learning model exhibits stable convergence of the binary cross-entropy loss and achieves 98.7% accuracy on unseen lattice models. To operationalize decision-making, we rank predicted commands by geometric significance and prototyped the agent-guided workflow through the Cubit® Meshing PowerTool GUI. As a stretch goal, we explore reinforcement learning (RL) to reduce or remove label requirements and to learn policies for action sequences that maximize total reward (e.g., size of hex-meshable regions and resulting hex mesh quality). When all-hex meshing is not feasible, the agent assists in producing hybrid meshes-prioritizing hex in critical regions and transitioning to tetrahedral elements (tets) elsewhere-maintaining fidelity while ensuring robustness. The overarching objective is to replace manual, heuristics-based decomposition with data-driven, reproducible automation, cutting meshing turnaround time by orders of magnitude. We anticipate direct impact on simulation workflows through intelligent, scalable decomposition of complex CAD models into hex-meshable subdomains.
- 1 September 2025
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessReplace Human Intelligence with Fast and Smart Geometric Reasoning and Graph Neural Network to Accelerate Next Gen ModSim Workflows
We present an agent-guided approach to CAD geometry decomposition that automates hex/hybrid meshing with graph neural networks (GNNs) to accelerate next-generation ModSim workflows. Our end-to-end pipeline (i) reduces 3D boundary-representation (B-Rep) models to a 2D chordalaxis skeleton (CAT) and then to a 1D bipartite graph of surface and curve nodes, (ii) assigns pernode labels as Cubit® WebCut actions, (iii) trains a multi-action GNN under supervised learning, and (iv) predicts five surface-node and three curve-node actions on out-of-distribution test geometries. Each graph node carries geometric, topological, and meshing attributes drawn from the B-Rep "skin" and CAT "skeleton," with two-way mappings across 3D↔2D↔1D representations to maintain traceability back to 3D CAD. The supervised learning model exhibits stable convergence of the binary cross-entropy loss and achieves 98.7% accuracy on unseen lattice models. To operationalize decision-making, we rank predicted commands by geometric significance and prototyped the agent-guided workflow through the Cubit® Meshing PowerTool GUI. As a stretch goal, we explore reinforcement learning (RL) to reduce or remove label requirements and to learn policies for action sequences that maximize total reward (e.g., size of hex-meshable regions and resulting hex mesh quality). When all-hex meshing is not feasible, the agent assists in producing hybrid meshes-prioritizing hex in critical regions and transitioning to tetrahedral elements (tets) elsewhere-maintaining fidelity while ensuring robustness. The overarching objective is to replace manual, heuristics-based decomposition with data-driven, reproducible automation, cutting meshing turnaround time by orders of magnitude. We anticipate direct impact on simulation workflows through intelligent, scalable decomposition of complex CAD models into hex-meshable subdomains.
- 1 August 2025
- Published by Office of Scientific and Technical Information (OSTI)
BANYAN-Ingest: document processing for GenAI
These are the slides I will be presenting to Sandia's 2025 MLDL workshop
- 1 August 2025
- Published by Office of Scientific and Technical Information (OSTI)
BANYAN-Ingest: document processing for GenAI
These are the slides I will be presenting to Sandia's 2025 MLDL workshop
- Open Access
- 1 July 2025
- Published by Office of Scientific and Technical Information (OSTI)
TetCrust WILD: Weighted Delaunay meshing in the wild
We introduce the first conforming Voronoi mesher capable of handling unclean input geometries encountered 'in the wild'. Our algorithm handles non-watertight, non-manifold, and self-intersecting inputs without requiring any manual cleanup, providing a standalone, end-to-end meshing framework. The framework enables simultaneous Voronoi and weighted Delaunay meshing, allowing users to generate polyhedral or tetrahedral elements based on application requirements, and produces high-quality elements
- 1 July 2025
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessTetCrust WILD: Weighted Delaunay meshing in the wild
We introduce the first conforming Voronoi mesher capable of handling unclean input geometries encountered 'in the wild'. Our algorithm handles non-watertight, non-manifold, and self-intersecting inputs without requiring any manual cleanup, providing a standalone, end-to-end meshing framework. The framework enables simultaneous Voronoi and weighted Delaunay meshing, allowing users to generate polyhedral or tetrahedral elements based on application requirements, and produces high-quality elements
- Open Access
- 1 July 2025
- Published by Office of Scientific and Technical Information (OSTI)
Imperfect Recognition: A Study of OCR Limitations in the Context of Scientific Documents
- 1 July 2025
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessImperfect Recognition: A Study of OCR Limitations in the Context of Scientific Documents