Virtual sensing to enable real-time monitoring of inaccessible locations & unmeasurable parameters.
7 affiliations
- 1Nuclear, Plasma, & Radiological Engineering Department, The Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA.
- 2Mechanical Science and Engineering Department, The Grainger College of Engineering, University of ILlinois Urbana-Champaign, Urbana, IL, USA.
- 3National Center for Supercomputing Applications, University of Illinois Urbana-Champaign, Urbana, IL, USA.
- 4Department of Applied Mechanics, Indian Institute of Technology Delhi, Delhi, India.
- 5Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, Delhi, India.
- 6Nuclear, Plasma, & Radiological Engineering Department, The Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA. [email protected].
- 7National Center for Supercomputing Applications, University of Illinois Urbana-Champaign, Urbana, IL, USA. [email protected].
Abstract
Real-time monitoring of safety-critical interior states remains an open problem across energy, environmental, and industrial systems where direct instrumentation is infeasible. Existing approaches based on governing equations, discrete state vectors, or fixed sensor locations fail to provide mesh-independent, field-level reconstructions at arbitrary interior coordinates under real-time constraints. Here we introduce neural operator-based virtual sensing as a general framework for recovering inaccessible interior fields from sparse, heterogeneous measurements and operating conditions, instantiated with MIMONet, a multi-input, multi-output neural operator that fuses heterogeneous inputs and decodes coupled physical fields through a shared latent representation. Across three engineering-grade evaluations of escalating complexity, from confined recirculating flows to pressurized water reactor subchannels and compact power-system heat exchangers, MIMONet achieves ≤5% relative reconstruction error, while generating full-field predictions with sub-millisecond inference on an NVIDIA H200, at least five orders of magnitude faster than traditional high-fidelity CFD simulations, with calibrated uncertainty and noise resilience demonstrated on the heat-exchanger case. We validate the framework on three independent real-world datasets spanning electrochemical energy, atmospheric science, and physical oceanography: current-density mapping in a hydrogen fuel cell, wind-speed profiling on instrumented meteorological towers, and North Atlantic ocean-state from a global ocean reanalysis. MIMONet improves over classical virtual-sensing baselines by 72-84%: 84% on fuel-cell internal-field recovery from 10% sensor coverage and 83% on hub-height wind-speed recovery from lower-level tower sensors. Most notably, it recovers sea-surface height, a field with zero direct sensors, from its learned coupling to observed temperature and salinity at 4.1 × lower error than the best classical predictor, a cross-modal field recovery beyond the reach of classical interpolation. These results establish operator-based virtual sensing as a practical route to real-time field observability in systems where the states that matter most cannot be directly measured.
Related
- Complementarity Test with Unmeasured, Permanently Inaccessible Path Markers
- Thermodynamic Irreversibility from Inaccessible Endogenous Quantum Histories
- Inferring missing locations in human mobility data using memory effects
- Dual-focal display through polarization-directed birefringence for compact virtual reality
- Four-scanner virtual-conjugation for large field-of-view, broadband one-, two- and three-photon microscopy
BibTeX
@article{kobayashi2026virtual,
title = {{Virtual sensing to enable real-time monitoring of inaccessible locations & unmeasurable parameters.}},
author = {Kazuma Kobayashi and Farid Ahmed and Jaewan Park and Subhankar Sarkar and Seid Koric and Souvik Chakraborty and Syed Bahauddin Alam},
journal = {Nature communications},
year = {2026},
month = sep,
doi = {10.1038/s41467-026-77463-7},
url = {https://europepmc.org/article/MED/42901902},
note = {CC BY},
}
RIS
TY - JOUR
TI - Virtual sensing to enable real-time monitoring of inaccessible locations & unmeasurable parameters.
AU - Kazuma Kobayashi
AU - Farid Ahmed
AU - Jaewan Park
AU - Subhankar Sarkar
AU - Seid Koric
AU - Souvik Chakraborty
AU - Syed Bahauddin Alam
PY - 2026
DA - 2026/09/19
JO - Nature communications
DO - 10.1038/s41467-026-77463-7
UR - https://europepmc.org/article/MED/42901902
AB - Real-time monitoring of safety-critical interior states remains an open problem across energy, environmental, and industrial systems where direct instrumentation is infeasible. Existing approaches based on governing equations, discrete state vectors, or fixed sensor locations fail to provide mesh-independent, field-level reconstructions at arbitrary interior coordinates under real-time constraints. Here we introduce neural operator-based virtual sensing as a general framework for recovering inaccessible interior fields from sparse, heterogeneous measurements and operating conditions, instantiated with MIMONet, a multi-input, multi-output neural operator that fuses heterogeneous inputs and decodes coupled physical fields through a shared latent representation. Across three engineering-grade evaluations of escalating complexity, from confined recirculating flows to pressurized water reactor subchannels and compact power-system heat exchangers, MIMONet achieves ≤5% relative reconstruction error, while generating full-field predictions with sub-millisecond inference on an NVIDIA H200, at least five orders of magnitude faster than traditional high-fidelity CFD simulations, with calibrated uncertainty and noise resilience demonstrated on the heat-exchanger case. We validate the framework on three independent real-world datasets spanning electrochemical energy, atmospheric science, and physical oceanography: current-density mapping in a hydrogen fuel cell, wind-speed profiling on instrumented meteorological towers, and North Atlantic ocean-state from a global ocean reanalysis. MIMONet improves over classical virtual-sensing baselines by 72-84%: 84% on fuel-cell internal-field recovery from 10% sensor coverage and 83% on hub-height wind-speed recovery from lower-level tower sensors. Most notably, it recovers sea-surface height, a field with zero direct sensors, from its learned coupling to observed temperature and salinity at 4.1 × lower error than the best classical predictor, a cross-modal field recovery beyond the reach of classical interpolation. These results establish operator-based virtual sensing as a practical route to real-time field observability in systems where the states that matter most cannot be directly measured.
SN - 2041-1723
ER -