Graph Neural Operator Towards Edge Deployability and Portability for Sparse-to-Dense, Real-Time Virtual Sensing on Irregular Grids
arXiv:2604.01802v1 Announce Type: new Abstract: Accurate sensing of spatially distributed physical fields typically requires dense instrumentation, which is often infeasible in real-world systems due to cost, accessibility, and environmental constraints. Physics-based solvers address this through direct numerical integration of governing equations, but their computational latency and power requirements preclude real-time use in resource-constrained monitoring and control systems. Here we introduce VIRSO (Virtual Irregular Real-Time Sparse Operator), a graph-based neural operator for sparse-to-dense reconstruction on irregular geometries, and a variable-connectivity algorithm, Variable KNN (V-KNN), for mesh-informed graph construction. Unlike prior neural operators that treat hardware deployability as secondary, VIRSO reframes inference as measurement: the combination of both spectral and spatial analysis provides accurate reconstruction without the high latency and power consumption o
arXiv:2604.01802v1 Announce Type: new Abstract: Accurate sensing of spatially distributed physical fields typically requires dense instrumentation, which is often infeasible in real-world systems due to cost, accessibility, and environmental constraints. Physics-based solvers address this through direct numerical integration of governing equations, but their computational latency and power requirements preclude real-time use in resource-constrained monitoring and control systems. Here we introduce VIRSO (Virtual Irregular Real-Time Sparse Operator), a graph-based neural operator for sparse-to-dense reconstruction on irregular geometries, and a variable-connectivity algorithm, Variable KNN (V-KNN), for mesh-informed graph construction. Unlike prior neural operators that treat hardware deployability as secondary, VIRSO reframes inference as measurement: the combination of both spectral and spatial analysis provides accurate reconstruction without the high latency and power consumption of previous graph-based methodologies with poor scalability, presenting VIRSO as a potential candidate for edge-constrained, real-time virtual sensing. We evaluate VIRSO on three nuclear thermal-hydraulic benchmarks of increasing geometric and multiphysics complexity, across reconstruction ratios from 47:1 to 156:1. VIRSO achieves mean relative $L_2$ errors below 1%, outperforming other benchmark operators while using fewer parameters. The full 10-layer configuration reduces the energy-delay product (EDP) from ${\approx}206$ J$\cdot$ms for the graph operator baseline to $10.1$ J$\cdot$ms on an NVIDIA H200. Implemented on an NVIDIA Jetson Orin Nano, all configurations of VIRSO provide sub-10 W power consumption and sub-second latency. These results establish the edge-feasibility and hardware-portability of VIRSO and present compute-aware operator learning as a new paradigm for real-time sensing in inaccessible and resource-constrained environments.
Executive Summary
This article presents VIRSO, a graph-based neural operator for sparse-to-dense reconstruction on irregular geometries. VIRSO achieves real-time virtual sensing in resource-constrained monitoring and control systems by reframing inference as measurement, combining spectral and spatial analysis. Evaluation on three nuclear thermal-hydraulic benchmarks demonstrates VIRSO's accuracy, scalability, and energy efficiency. The study establishes VIRSO as a potential candidate for edge-constrained, real-time virtual sensing, showcasing compute-aware operator learning as a new paradigm for inaccessible and resource-constrained environments. The results highlight VIRSO's potential for real-world applications in monitoring and control systems, particularly in edge computing scenarios.
Key Points
- ▸ VIRSO is a graph-based neural operator for sparse-to-dense reconstruction on irregular geometries.
- ▸ VIRSO reframes inference as measurement, combining spectral and spatial analysis for accurate reconstruction.
- ▸ Evaluation on three nuclear thermal-hydraulic benchmarks demonstrates VIRSO's accuracy, scalability, and energy efficiency.
Merits
Strength in Real-Time Sensing
VIRSO's ability to achieve real-time virtual sensing in resource-constrained monitoring and control systems, leveraging compute-aware operator learning.
Demerits
Limited Generalizability
The study's focus on nuclear thermal-hydraulic benchmarks may limit VIRSO's generalizability to other domains and applications.
Expert Commentary
The article presents a significant contribution to the field of neural operators, demonstrating VIRSO's potential for real-time sensing in resource-constrained environments. However, the study's focus on nuclear thermal-hydraulic benchmarks may limit VIRSO's generalizability to other domains. Furthermore, the evaluation of VIRSO's energy efficiency and scalability on various hardware platforms is crucial for its practical implementation. Nevertheless, the study's findings have important implications for the development of new policies and regulations for the use of neural operators in edge computing scenarios.
Recommendations
- ✓ Future studies should investigate VIRSO's generalizability to other domains and applications.
- ✓ The development of VIRSO's energy efficiency and scalability on various hardware platforms is crucial for its practical implementation.
Sources
Original: arXiv - cs.LG
