Physics-Guided Deep Learning for Multiview Infrared Polarization-Based Subsurface Material Classification

Research context

Research on electrical energy conversion, storage and generation dates back to the nineteenth century, but only in recent years have scientists begun to investigate the impact of electron spin on these processes. The ability to control and manipulate this intrinsically quantum property of matter opens new approaches to addressing energy science challenges. The chiral-induced spin selectivity (CISS) effect is central to this effort, as it enables control over the transport and generation of both pure spin currents and spin-polarized charge currents. In this Review, we first introduce design strategies for implementing CISS in materials and then describe examples of how CISS has been used to improve electrocatalysis and spintronics. We conclude with a forward-looking perspective on the next steps for leveraging CISS in energy science.

Keywords: Deep learning, Infrared, Feature extraction, Artificial neural network, Pattern recognition (psychology), Temperature measurement, Remote sensing, Artificial intelligence, Geology, Computer science, Computer vision, Convolutional neural network, Ground-penetrating radar, Backpropagation

Source & review

Bibliographic record reviewed for relevance and publication quality. Full-text findings have not been extracted; consult the original publication for methods and results.

OpenAlex cited-by 0; topical title/abstract and venue audit passed.

citations · OpenAlex · observed 2026-09-08

Metadata: OpenAlex · source record ↗

Cite / 引用

Jianwei Lin, Kaimin Yu, Honghui Liu, Feng Huang, Huayang He, Xianyu Wu. Physics-Guided Deep Learning for Multiview Infrared Polarization-Based Subsurface Material Classification. IEEE Transactions on Instrumentation and Measurement (2026). https://doi.org/10.1109/tim.2026.3711303

分享：本论文的永久链接