Nanoimprinted Infrared Metasurface Multispectral Filters for Neural‐Network‐Assisted Low‐Temperature Sensing
- 1Global College Shanghai Jiao Tong University Shanghai China.
- 2School of Integrated Circuits Shanghai Polytechnic University Shanghai China.
Abstract
Low-temperature infrared sensing requires temperature information to be extracted from weak thermal radiation while preserving optical throughput. Nanoimprinted metasurface filters combine multispectral encoding with neural-network calibration to address this challenge. A single circular-ring geometry controls passband position, bandwidth, and overlap, with simulated tuning across 6.4-11.2 μm. Deep-ultraviolet stepper lithography and ultraviolet nanoimprinting transfer reusable master patterns to 1-inch zinc sulfide filters. Four broad, partially overlapping bands retain peak transmittance near 80% and provide complementary spectral inputs for blackbody measurements from -20°C to 20°C. Neural-network regression on the processed calibration curves achieves a mean absolute error of 0.160°C, compared with 0.434°C for one unfiltered input, a reduction of approximately 63%. Temperature-resolved comparisons also identify lower errors at the cold end of the range. By connecting geometric spectral design, replicable fabrication, and computational temperature retrieval, this approach offers a route to compact multispectral thermometers that make better use of weak infrared signals.
Related
- Anisotropic perfect absorber with borophene-based metasurface at near-infrared wavelengths
- Highly tunable mid-infrared perfect absorber based on unpatterned α-MoO ₃ integrated with an inverted metasurface
- Two-dimensional pixel-level addressable mid-infrared metasurface spatial light modulator
- Deep learning-assisted graphene-based THz metasurface for label-free and high-performance MCF-7 breast cancer cell sensing
- Infrared evanescent wave-temperature dual sensing from single chalcogenide fiber
BibTeX
@article{yang2026nanoimprinted,
title = {{Nanoimprinted Infrared Metasurface Multispectral Filters for Neural‐Network‐Assisted Low‐Temperature Sensing}},
author = {Shiyu Yang and Zhijuan Su and Yaping Dan},
journal = {Nanophotonics (Berlin, Germany)},
year = {2026},
month = nov,
doi = {10.1002/nap2.70345},
url = {https://europepmc.org/article/PMC/PMC13726500},
note = {CC BY},
}
RIS
TY - JOUR
TI - Nanoimprinted Infrared Metasurface Multispectral Filters for Neural‐Network‐Assisted Low‐Temperature Sensing
AU - Shiyu Yang
AU - Zhijuan Su
AU - Yaping Dan
PY - 2026
DA - 2026/11/01
JO - Nanophotonics (Berlin, Germany)
DO - 10.1002/nap2.70345
UR - https://europepmc.org/article/PMC/PMC13726500
AB - Low-temperature infrared sensing requires temperature information to be extracted from weak thermal radiation while preserving optical throughput. Nanoimprinted metasurface filters combine multispectral encoding with neural-network calibration to address this challenge. A single circular-ring geometry controls passband position, bandwidth, and overlap, with simulated tuning across 6.4-11.2 μm. Deep-ultraviolet stepper lithography and ultraviolet nanoimprinting transfer reusable master patterns to 1-inch zinc sulfide filters. Four broad, partially overlapping bands retain peak transmittance near 80% and provide complementary spectral inputs for blackbody measurements from -20°C to 20°C. Neural-network regression on the processed calibration curves achieves a mean absolute error of 0.160°C, compared with 0.434°C for one unfiltered input, a reduction of approximately 63%. Temperature-resolved comparisons also identify lower errors at the cold end of the range. By connecting geometric spectral design, replicable fabrication, and computational temperature retrieval, this approach offers a route to compact multispectral thermometers that make better use of weak infrared signals.
SN - 2192-8606
SN - 2192-8614
ER -