Graph Neural Operator Towards Edge Deployability and Portability for Sparse-to-Dense, Real-Time Virtual Sensing on Irregular Grids

2026-04-02

AI Summary

This work addresses the challenge of achieving high-fidelity, real-time physical field sensing under constraints of cost, accessibility, and environmental impact, where dense sensor deployment is impractical and conventional solvers suffer from excessive latency and power consumption, precluding edge deployment. To this end, we propose VIRSO—the first graph neural operator explicitly designed for hardware deployability—leveraging Variable KNN-based dynamic graph construction and a hybrid spectral-spatial modeling strategy to enable accurate reconstruction of dense fields from sparse measurements. Evaluated on three complex nuclear thermal-hydraulic benchmarks, VIRSO achieves an average L₂ error below 1% at a reconstruction ratio of 156:1. It attains an energy-delay product as low as 10.1 J·ms on an H200 GPU, and operates within <10 W power and <1 s latency on a Jetson Orin Nano, establishing a new paradigm for efficient operator learning tailored to edge computing.

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.

Problem

• virtual sensing
• irregular grids
• edge deployability
• real-time reconstruction
• sparse-to-dense

Innovation

• Graph Neural Operator
• Edge Deployability
• Variable KNN
• Real-Time Virtual Sensing
• Irregular Grids