Detector-mediated cross-spectral prediction with a gate-tunable van der Waals tunneling photodetector
Abstract
Cross-spectral prediction infers information in one spectral band from observations acquired in another. This task is ill-posed because multiple target-band signals can be compatible with a single source observation. Image-space supervision alone does not test consistency with a measured detector response. Here, we incorporate the calibrated response manifold of a gate-tunable PdSe ₂ /h-BN/WSe ₂ photodetector as a differentiable detector-response layer. Parameterized by wavelength, optical power, source-drain bias and gate voltage, this layer constrains the magnitude and polarity of the predicted detector response while preserving image fidelity. In visible-to-infrared cross-spectral prediction, the framework achieves a peak signal-to-noise ratio of 26.58 dB and a structural similarity index of 0.89. It also reduces detector-space error relative to architecture-only and response-corrupted controls. Post-inference measurements further evaluate 64-mask response consistency after 1310 nm optical re-encoding. These results establish detector-mediated cross-spectral prediction as a framework that combines image reconstruction with measured response-space consistency under the tested conditions.
Related
- Uniform instanton theory for bridge-mediated nonadiabatic tunneling
- Monolayer MoS₂ on Paper with a Copper Electrode: An Integrated CVD-Grown Broadband UV-Visible Photodetector.
- Hierarchical 2D Mn–Co–Te nanocomposites for visible light photodetector and nonlinear applications: insights from experiment and DFT
- Exploring Charge Transport, Trap States, and Activation Energy of High-Quality CsPbBr3 Single Crystal Grown by Inverse Temperature Crystallization for Photodetector Applications
- Spectroscopic study of the tunneling dynamics in N2-water observed in the O–D stretch region
BibTeX
@article{xiao2026detectormediated,
title = {{Detector-mediated cross-spectral prediction with a gate-tunable van der Waals tunneling photodetector}},
author = {Kening Xiao and Xingsi Liu and Libo Zhang and Jintao Fu and Yiran Tan and Xin Li and Wenqi Mo and Bolang Peng and Jinqiu Huang and Xueyuan Wei and Li Han and Jiale He and Guanhai Li and Cheng-Wei Qiu and Xiaoshuang Chen},
journal = {Nature Communications},
year = {2026},
month = oct,
doi = {10.1038/s41467-026-78977-w},
url = {https://www.nature.com/articles/s41467-026-78977-w},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Detector-mediated cross-spectral prediction with a gate-tunable van der Waals tunneling photodetector
AU - Kening Xiao
AU - Xingsi Liu
AU - Libo Zhang
AU - Jintao Fu
AU - Yiran Tan
AU - Xin Li
AU - Wenqi Mo
AU - Bolang Peng
AU - Jinqiu Huang
AU - Xueyuan Wei
AU - Li Han
AU - Jiale He
AU - Guanhai Li
AU - Cheng-Wei Qiu
AU - Xiaoshuang Chen
PY - 2026
DA - 2026/10/28
JO - Nature Communications
DO - 10.1038/s41467-026-78977-w
UR - https://www.nature.com/articles/s41467-026-78977-w
AB - Cross-spectral prediction infers information in one spectral band from observations acquired in another. This task is ill-posed because multiple target-band signals can be compatible with a single source observation. Image-space supervision alone does not test consistency with a measured detector response. Here, we incorporate the calibrated response manifold of a gate-tunable PdSe ₂ /h-BN/WSe ₂ photodetector as a differentiable detector-response layer. Parameterized by wavelength, optical power, source-drain bias and gate voltage, this layer constrains the magnitude and polarity of the predicted detector response while preserving image fidelity. In visible-to-infrared cross-spectral prediction, the framework achieves a peak signal-to-noise ratio of 26.58 dB and a structural similarity index of 0.89. It also reduces detector-space error relative to architecture-only and response-corrupted controls. Post-inference measurements further evaluate 64-mask response consistency after 1310 nm optical re-encoding. These results establish detector-mediated cross-spectral prediction as a framework that combines image reconstruction with measured response-space consistency under the tested conditions.
SN - 2041-1723
ER -