# Energy-efficient operation of neural operators for virtual sensing

arXiv: https://arxiv.org/abs/2609.30580 · HTML: https://mlsanity.com/paper/2609.30580/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators](https://mlsanity.com/paper/1910.03193/) (2019)
- [The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning](https://mlsanity.com/paper/2412.00568/) (2024)
- [Virtual Sensing-Enabled Digital Twin Framework for Real-Time Monitoring of Nuclear Systems Leveraging Deep Neural Operators](https://mlsanity.com/paper/2410.13762/) (2024)
- [Active operator learning with predictive uncertainty quantification for partial differential equations](https://mlsanity.com/paper/2503.03178/) (2025)
- [mlf-core: a framework for deterministic machine learning](https://mlsanity.com/paper/2104.07651/) (2021)
- [Virtual Sensing to Enable Real-Time Monitoring of Inaccessible Locations & Unmeasurable Parameters](https://mlsanity.com/paper/2412.00107/) (2024)
- [Verification and Validation for Trustworthy Scientific Machine Learning](https://mlsanity.com/paper/2502.15496/) (2025)
- [Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon](https://mlsanity.com/paper/2604.22032/) (2026)
- [When Spike Sparsity Does Not Translate to Deployed Cost: VS-WNO on Jetson Orin Nano](https://mlsanity.com/paper/2604.17040/) (2026)
- [BLISSNet: Deep Operator Learning for Fast and Accurate Flow Reconstruction from Sparse Sensor Measurements](https://mlsanity.com/paper/2602.24228/) (2026)
- [Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Neuromorphic Virtual Sensing](https://mlsanity.com/paper/2608.23987/) (2026)

## Built on by (most cited first, 1 of 1)

- [Targeted search shows that random-device testing underestimates worst-case error in a simulated wave-based neural operator](https://mlsanity.com/paper/2610.07529/) (2026)

## Abstract (arXiv)

Virtual sensing repeatedly reconstructs physical fields from changing observations, often on a fixed geometry. We investigate how shared spatial computation reduces the energy of these updates while retaining the selected checkpoint and its evaluated predictions. In a heat-exchanger service, standard compiler freezing and explicit trunk reuse give similar operating energy reductions relative to graph replay: approximately 1% at one request per second and 20% at forty requests per second. In 15 W mode with fixed clocks, reuse with graph replay completes the same request sequence with 22.0 to 22.5% less energy than eager execution, including preparation and waiting. DeepONet and Fourier neural operator (FNO) controls distinguish the effects of reusable arithmetic and launch overhead. Preparation, artifact construction, and worker replacement add costs outside repeated inference. These results connect operator structure to operating energy and show how update frequency and execution lifetime govern the benefit of computation reuse in physical-field virtual sensing.