Source-aware reinforcement-learning optical-channel selection for compact VIS-NIR sensing with botanical validation
Optics Express · 24.08.2026 · 34 (17) · 32557
DOI: 10.1364/oe.606625 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 19.08.2026. Verfasst von Mingkun Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Chinese Aeronautical Establishment.
Abstract (Originalsprache)
Compact visible-near-infrared (VIS-NIR) sensors require a few optical passbands that remain informative under source and acquisition variation, but conventional wavelength selectors usually optimize classifier accuracy after dense spectra have already been collected. We introduce a source-aware reinforcement-learning (RL) optical-channel selector that treats wavelength choice as an early-stage sensor-design problem. The key innovation is a policy-gradient reward derived from a source-robust optical utility: blocked-source macro-F1, balanced accuracy, Fisher separability, source consistency, inter-channel redundancy, and channel cost are optimized in one objective, while a no-repeat action mask, entropy regularization, and weighted consensus aggregation convert stochastic selections into stable passband proposals. A 31-channel Pseudostellariae Radix-Codonopsis Radix VIS-NIR dataset covering nominal 360-980 nm measurements is used only as a botanical validation case and is evaluated with leave-one-source-out testing over four source blocks. With three channels, the proposed selector achieved a macro-F1 of 0.9580, compared with 0.9766 for the full 31-channel reference. With five channels, it achieved performance comparable to CARS, while CARS and SPA remained competitive or performed better under some other channel budgets. A 15-channel consensus policy reached a macro-F1 of 0.9733. These results position the proposed method as a source-aware compact sensing policy rather than a universally superior optical-channel selector. The final output is not a classifier-specific feature list, but a compact optical-channel specification with stable candidate centers at 455, 465, 730, 750, and 770 nm for simplified VIS-NIR sensing.
Förderung
- Chinese Aeronautical Establishment
Zitieren
APA
Zhang, M., Ma, C., Li, Y., Huang, J., Du, M., Niu, H., & Ma, J. (2026). Source-aware reinforcement-learning optical-channel selection for compact VIS-NIR sensing with botanical validation. Optics Express, 34(17), 32557. https://doi.org/10.1364/oe.606625
Vancouver
Zhang M, Ma C, Li Y, Huang J, Du M, Niu H, et al. Source-aware reinforcement-learning optical-channel selection for compact VIS-NIR sensing with botanical validation. Optics Express. 2026;34(17):32557. doi:10.1364/oe.606625
BibTeX
@article{Zhang2026,
author = {Zhang, Mingkun and Ma, Chao and Li, Yuxiang and Huang, Jiayu and Du, Mingtong and Niu, Huawei and Ma, Jianwei},
title = {Source-aware reinforcement-learning optical-channel selection for compact VIS-NIR sensing with botanical validation},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {17},
pages = {32557},
doi = {10.1364/oe.606625}
}
EUVIMED