Search papers, labs, and topics across Lattice.
The paper introduces VIRSO, a graph-based neural operator, and V-KNN, a variable-connectivity graph construction algorithm, for efficient sparse-to-dense reconstruction of physical fields on irregular geometries. VIRSO achieves high accuracy (mean relative L2 errors < 1%) with significantly reduced energy-delay product (EDP), outperforming existing graph operators. Demonstrating edge deployability, VIRSO achieves sub-10W power consumption and sub-second latency on an NVIDIA Jetson Orin Nano, making it suitable for real-time virtual sensing in resource-constrained environments.
Achieve real-time, accurate virtual sensing on edge devices with VIRSO, a graph neural operator that slashes energy consumption by 20x compared to previous methods.
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.
