pith. sign in

arxiv: 2605.21224 · v1 · pith:RQIHH3DTnew · submitted 2026-05-20 · ⚛️ physics.optics · cs.AI· eess.SP

Artificial Intelligence Reshapes Microwave Photonics

Peng Li , Xihua Zou , Jia Ye , Wei Pan , Lianshan Yan This is my paper

Pith reviewed 2026-05-21 01:36 UTC · model grok-4.3

classification ⚛️ physics.optics cs.AIeess.SP
keywords microwave photonicsartificial intelligencesignal processingphotonic radarterahertz signalsautonomous systemsphotonic communicationsAI optimization
0
0 comments X

The pith

AI is reshaping microwave photonics by automating design, simulation, fabrication, testing, deployment, and maintenance of systems for microwave and terahertz signals.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper reviews how artificial intelligence techniques are being applied to microwave photonics, an interdisciplinary field that uses light to handle high-frequency electrical signals beyond the limits of conventional electronics. It shows AI integration across the full pipeline of generating, transmitting, processing, and detecting these signals, with examples like photonic radar and high-speed data links. A sympathetic reader would see this as evidence that AI brings self-optimizing behavior and higher performance to photonic hardware that once required extensive manual tuning. The review compiles advances to argue that this combination delivers more efficient and autonomous operation than older approaches. Readers should care because it maps a path toward practical systems that can adapt in real time for applications in communications, sensing, and computing.

Core claim

The paper states that AI has revolutionized the design, simulation, fabrication, testing, deployment, and maintenance of MWP systems, delivering autonomous operation and exceptional efficiency beyond traditional systems. It presents the first comprehensive overview of AI-enabled MWP by summarizing state-of-the-art advances in signal generation, transmission, processing, and detection, along with representative breakthroughs such as fully photonic microwave radar, photonic analog-to-digital converters reaching 320 GHz bandwidth, and wireless links at 616 Gbit/s.

What carries the argument

AI models and optimization routines applied to each stage of MWP system development and operation to enable automation and performance gains.

If this is right

  • MWP radar systems can achieve full photonic operation with reduced size and power needs.
  • Photonic analog-to-digital converters can extend usable bandwidths toward and beyond 320 GHz through AI-guided design.
  • Wireless links can sustain data rates near 616 Gbit/s while adapting automatically to changing conditions.
  • Overall system maintenance shifts from periodic manual checks to continuous AI-driven monitoring and correction.
  • New MWP devices can be fabricated with fewer trial iterations by using AI simulation loops.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Hybrid AI-MWP platforms could become standard building blocks for future 6G infrastructure where both speed and adaptability matter.
  • The same AI methods might uncover previously unknown photonic circuit layouts that further lower loss or increase bandwidth.
  • Deployment in harsh environments such as satellite links or remote sensors could benefit from the claimed autonomous correction features.
  • Cost reductions in large-scale MWP networks may follow if AI shortens the development cycle from months to weeks.

Load-bearing premise

The reviewed examples reflect real, scalable improvements from AI across all parts of MWP systems without major gaps in practical deployment or performance under varied conditions.

What would settle it

A controlled comparison in which AI-designed or AI-operated MWP hardware shows no measurable gain in bandwidth, data rate, or reliability over conventional methods when tested in field conditions would falsify the central claim.

read the original abstract

As a rapidly emerging interdisciplinary field that intrinsically integrates microwave and photonics, microwave photonics (MWP) provides disruptive solutions to overcome the fundamental bandwidth of conventional electronic systems. By exploiting the inherently ultra-wide bandwidth and low-loss characteristics of photonic technologies, MWP enables the generation, transmission, processing, and detection of microwave, millimeter-wave, and terahertz signals. Representative breakthroughs include fully photonic microwave radar systems, photonic analog-to-digital converters with bandwidth up to 320 GHz, and photonic wireless communication systems achieving data rate as high as 616 Gbit/s. Meanwhile, the rapid growth of artificial intelligence (AI) is reshaping scientific research, engineering, and daily life in unprecedented ways, such as AI for science/engineering and AI co-scientist/assistant. Correspondingly, AI is profoundly reshaping MWP in all aspects, ranging from signal generation, transmission to signal processing and detection. AI has revolutionized the design, simulation, fabrication, testing, deployment, and maintenance of MWP systems, delivering autonomous operation and exceptional efficiency beyond traditional systems. Motivated by these developments, this Review Paper provides the first comprehensive overview of AI-enabled MWP, systematically summarizing the state-of-the-art advances and presenting insights for both the academic community and the broader public.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. This review paper claims that AI is profoundly reshaping microwave photonics (MWP) across signal generation, transmission, processing, and detection. It asserts that AI has revolutionized the design, simulation, fabrication, testing, deployment, and maintenance of MWP systems, enabling autonomous operation and exceptional efficiency beyond traditional approaches. The manuscript positions itself as the first comprehensive overview, summarizing state-of-the-art advances from the literature and offering insights for the community.

Significance. If the synthesis holds with balanced analysis, the review could consolidate emerging work at the AI-MWP intersection and guide future research in photonics and microwave systems. The significance is reduced by the absence of critical evaluation of practical limitations in the cited examples, which weakens the broad claims of revolution and autonomy.

major comments (2)
  1. [Abstract] Abstract: The assertion that 'AI has revolutionized the design, simulation, fabrication, testing, deployment, and maintenance of MWP systems, delivering autonomous operation and exceptional efficiency beyond traditional systems' is presented without reference to specific quantitative metrics, head-to-head comparisons against optimized non-AI baselines, or deployment-scale results from the reviewed works. This generalization is load-bearing for the central narrative.
  2. [Literature summary sections] Main text (literature summary sections): The review summarizes cited advances but does not systematically address real-world limitations such as data scarcity for training AI models on MWP datasets, latency constraints in real-time photonic control loops, or insertion losses at AI-photonic interfaces. Without this, the claim of 'exceptional efficiency' and 'autonomous operation' does not follow from the presented evidence.
minor comments (2)
  1. Clarify the selection criteria for the cited literature to avoid potential selection bias in a comprehensive review.
  2. Ensure that performance claims from individual papers are accompanied by context on experimental conditions (e.g., simulation vs. hardware demonstration) for reader evaluation.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which help strengthen the balance and evidentiary support in our review. We address the major comments point by point below, with plans to revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] The assertion that 'AI has revolutionized the design, simulation, fabrication, testing, deployment, and maintenance of MWP systems, delivering autonomous operation and exceptional efficiency beyond traditional systems' is presented without reference to specific quantitative metrics, head-to-head comparisons against optimized non-AI baselines, or deployment-scale results from the reviewed works. This generalization is load-bearing for the central narrative.

    Authors: We acknowledge that the abstract phrasing is broad. As a review synthesizing trends across the literature, the statement reflects collective advances reported in multiple studies rather than new empirical claims by the authors. To address the concern, we will revise the abstract to incorporate specific quantitative examples drawn from the cited works (e.g., reported improvements in processing speed or efficiency in AI-optimized MWP components) and will cross-reference head-to-head comparisons where they appear in the primary literature. revision: yes

  2. Referee: [Literature summary sections] The review summarizes cited advances but does not systematically address real-world limitations such as data scarcity for training AI models on MWP datasets, latency constraints in real-time photonic control loops, or insertion losses at AI-photonic interfaces. Without this, the claim of 'exceptional efficiency' and 'autonomous operation' does not follow from the presented evidence.

    Authors: The referee correctly notes that the current draft focuses primarily on reported advances without a dedicated treatment of practical constraints. We will add a new section on challenges and limitations that explicitly discusses data scarcity for MWP-specific training sets, latency requirements in closed-loop photonic control, and insertion losses at AI-photonic interfaces. This addition will qualify the efficiency and autonomy claims with evidence-based caveats drawn from the reviewed literature. revision: yes

Circularity Check

0 steps flagged

Review paper with no internal derivations or self-referential reductions

full rationale

This is a review paper summarizing state-of-the-art advances in AI-enabled microwave photonics from external cited literature. No equations, derivations, fitted parameters, or predictions are present that could reduce by construction to the paper's own inputs. The central claims draw from independent sources without self-citation load-bearing or ansatz smuggling in the narrative. As a survey, the content is self-contained against external benchmarks and exhibits no circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This review rests on the completeness and representativeness of the surveyed literature on AI applications in MWP; no new mathematical axioms, free parameters, or invented entities are introduced by the paper itself.

pith-pipeline@v0.9.0 · 5758 in / 988 out tokens · 32065 ms · 2026-05-21T01:36:12.091742+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

116 extracted references · 116 canonical work pages

  1. [1]

    Capmany, D

    J. Capmany, D. Novak, Nat. Photon. 2007, 1, 319

    work page 2007

  2. [2]

    J. Yao, J. Lightwave Technol. 2009, 27, 314

    work page 2009

  3. [3]

    A. J. Seeds, K. J. Williams, J. Lightwave Technol. 2006, 24, 4628

    work page 2006

  4. [4]

    Berceli, P

    T. Berceli, P. R. Herczfeld, IEEE Trans. Microw. Theory Techn. 2010, 58, 2992

    work page 2010

  5. [5]

    J. Yao, J. Capmany, Sci. China Inf. Sci. 2022, 65, 221401

    work page 2022

  6. [6]

    C. Liu, J. Wang, L. Cheng, et al., J. Lightwave Technol. 2014, 32, 3452

    work page 2014

  7. [7]

    Capmany, P

    J. Capmany, P. Muñoz, J. Lightwave Technol. 2014, 32, 2849

    work page 2014

  8. [8]

    Waterhouse, D

    R. Waterhouse, D. Novak, IEEE Microw. Mag. 2015, 16, 84

    work page 2015

  9. [9]

    K. Xu, R. Wang, Y. Dai, et al., Photonics Res. 2014, 2, B54

    work page 2014

  10. [10]

    Ghelfi, F

    P. Ghelfi, F. Laghezza, F. Scotti, et al., Nature 2014, 507, 341

    work page 2014

  11. [11]

    S. Pan, Y. Zhang, J. Lightwave Technol. 2020, 38, 5450

    work page 2020

  12. [12]

    S. S. S. Panda, T. Panigrahi, S. R. Parne, et al., IEEE Sens. J. 2021, 21, 21144

    work page 2021

  13. [13]

    S. Li, Z. Cui, X. Ye, et al., Laser Photon. Rev. 2020, 14, 1900239

    work page 2020

  14. [14]

    Maresca, G

    S. Maresca, G. Serafino, C. Noviello, et al., J. Lightwave Technol. 2022, 40, 6626

    work page 2022

  15. [17]

    Kumar, M

    C. Kumar, M. D. Nadeem, S. K. Raghuwanshi, et al., IEEE Sens. J. 2024, 24, 11974

    work page 2024

  16. [18]

    Serafino, S

    G. Serafino, S. Maresca, C. Porzi, et al., J. Lightwave Technol. 2020, 38, 5339

    work page 2020

  17. [19]

    Ghelfi, F

    P. Ghelfi, F. Scotti, D. Onori, et al., IEEE J. Sel. Top. Quantum Electron. 2019, 25, 1

    work page 2019

  18. [20]

    Bogoni, P

    A. Bogoni, P. Ghelfi, F. Laghezza, et al., IET SciTech Publishing, 2019

    work page 2019

  19. [21]

    Ghelfi, D

    P. Ghelfi, D. Onori, F. Laghezza, et al., Proc. Eur. Radar Conf. 2015, 197

    work page 2015

  20. [22]

    Seeds, IEEE Trans

    A. Seeds, IEEE Trans. Microw. Theory Techn. 2002, 50, 877

    work page 2002

  21. [23]

    R. A. Kiehl, E. P. EerNisse, Proc. Int. Electron Devices Meeting 1977, 103

    work page 1977

  22. [24]

    R. A. Kiehl, IEEE Trans. Electron Devices 1978, 25

    work page 1978

  23. [25]

    Thomson, A

    D. Thomson, A. Zilkie, J. E. Bowers, et al., J. Opt. 2016, 18, 073003

    work page 2016

  24. [26]

    Zhang, J

    W. Zhang, J. Yao, IEEE J. Quantum Electron. 2015, 52, 1

    work page 2015

  25. [27]

    Leuthold, C

    J. Leuthold, C. Koos, W. Freude, Nat. Photon. 2010, 4, 535

    work page 2010

  26. [28]

    M. Smit, X. Leijtens, H. Ambrosius, et al., Semicond. Sci. Technol. 2014, 29, 083001

    work page 2014

  27. [29]

    M. Smit, K. Williams, J. van der Tol, APL Photon. 2019, 4, 050901

    work page 2019

  28. [30]

    C. G. H. Roeloffzen, L. Zhuang, C. Taddei, et al., Opt. Express 2013, 21, 22937

    work page 2013

  29. [31]

    D. J. Moss, R. Morandotti, A. L. Gaeta, et al., Nat. Photon. 2013, 7, 597

    work page 2013

  30. [32]

    Géron, O’Reilly Media, 2022

    A. Géron, O’Reilly Media, 2022

    work page 2022

  31. [33]

    Russell, P

    S. Russell, P. Norvig, Pearson, 2020

    work page 2020

  32. [34]

    Zhang, Z

    A. Zhang, Z. C. Lipton, M. Li, et al., Cambridge Univ. Press, 2023

    work page 2023

  33. [35]

    Goodfellow, Y

    I. Goodfellow, Y. Bengio, A. Courville, MIT Press, 2016

    work page 2016

  34. [36]

    T. Park, S. Mondal, W. Cai, Laser Photon. Rev. 2025, 19, 2401520

    work page 2025

  35. [37]

    M. G. Mahmoud, A. S. Hares, M. F. O. Hameed, et al., APL Photon. 2024, 9, 086101

    work page 2024

  36. [38]

    Alagappan, J

    G. Alagappan, J. R. Ong, Z. Yang, et al., Photonics 2022, 9, 75

    work page 2022

  37. [39]

    Yadav, S

    K. Yadav, S. Bidnyk, A. Balakrishnan, J. Opt. Soc. Am. B 2024, 41, 1739

    work page 2024

  38. [40]

    M. U. Hadi, ICT Express 2021, 7, 253

    work page 2021

  39. [41]

    X. Liu, J. Zhang, M. Zhu, et al., Opt. Express 2023, 31, 20005

    work page 2023

  40. [42]

    Nakai, I

    M. Nakai, I. Takai, S. W. Chung, et al., Opt. Express 2024, 32, 18746

    work page 2024

  41. [43]

    L. Leng, Z. Zeng, G. Wu, et al., Photonics Res. 2022, 10, 347

    work page 2022

  42. [44]

    H. Niu, D. Lin, S. Shi, et al., J. Lightwave Technol. 2026, 44, 215

    work page 2026

  43. [45]

    J. Y. Kim, J. Kim, J. Yoon, et al., Sci. Rep. 2023, 13, 19929

    work page 2023

  44. [46]

    T. Hao, Y. Liu, J. Tang, et al., Adv. Photon. 2020, 2, 044001

    work page 2020

  45. [47]

    M. Li, L. Guo, D. Sun, et al., Photonics Res. 2025, 13, 2618

    work page 2025

  46. [48]

    J. Tang, T. Hao, W. Li, et al., Opt. Express 2018, 26, 12257

    work page 2018

  47. [49]

    Zhang, T

    G. Zhang, T. Hao, Q. Cen, et al., Opt. Express 2023, 31, 16929

    work page 2023

  48. [50]

    P. Li, Z. Dai, Z. Fan, et al., Opt. Lett. 2020, 45, 3139

    work page 2020

  49. [51]

    J. Tang, B. Zhu, W. Zhang, et al., Nat. Commun. 2020, 11, 3814

    work page 2020

  50. [52]

    P. Li, L. Yan, J. Ye, et al., Opt. Lett. 2020, 45, 1990

    work page 2020

  51. [53]

    P. Li, L. Yan, J. Ye, et al., Opt. Express 2018, 26, 28013

    work page 2018

  52. [54]

    C. Wang, J. Yao, J. Lightwave Technol. 2010, 28, 1652

    work page 2010

  53. [55]

    M. H. Khan, H. Shen, Y. Xuan, et al., Nat. Photon. 2010, 4, 117. 13

    work page 2010

  54. [56]

    Z. Xu, H. Tian, Z. Zeng, et al., PhotoniX 2025, 6, 5

    work page 2025

  55. [57]

    C. Fang, Y. Ruan, Q. Guo, et al., Opt. Laser Technol. 2025, 180, 111449

    work page 2025

  56. [58]

    H. Liu, Y. Du, X. Li, et al., ACS Photon. 2024, 11, 5195

    work page 2024

  57. [59]

    G. P. Agrawal, J. Opt. Soc. Am. B 2011, 28, A1

    work page 2011

  58. [60]

    D. Wang, Y. Song, J. Li, et al., J. Lightwave Technol. 2020, 38, 4730

    work page 2020

  59. [61]

    H. Yang, Z. Niu, S. Xiao, et al., J. Lightwave Technol. 2020, 39, 1322

    work page 2020

  60. [62]

    H. Yang, Z. Niu, H. Zhao, et al., J. Lightwave Technol. 2022, 40, 4571

    work page 2022

  61. [63]

    Y. Zang, Z. Yu, K. Xu, et al., Opt. Express 2022, 30, 46626

    work page 2022

  62. [64]

    Jiang, Z

    R. Jiang, Z. Fu, Y. Bao, et al., IEEE Photon. J. 2022, 14, 1

    work page 2022

  63. [65]

    X. He, L. Yan, L. Jiang, et al., J. Lightwave Technol. 2022, 41, 2301

    work page 2022

  64. [66]

    Zhang, H

    N. Zhang, H. Yang, Z. Niu, et al., J. Lightwave Technol. 2022, 40, 7779

    work page 2022

  65. [67]

    Y. Zhu, J. Ye, L. Yan, et al., J. Lightwave Technol. 2023, 41, 2657

    work page 2023

  66. [68]

    L. Tao, Y. Wang, Y. Gao, et al., IEEE Photon. Technol. Lett. 2013, 25, 2346

    work page 2013

  67. [69]

    L. Zhao, J. Zhang, L. Huang, et al., Photonics 2022, 9, 794

    work page 2022

  68. [70]

    G. H. Thng, M. H. Jaward, M. Bakaul, J. Lightwave Technol. 2022, 40, 7727

    work page 2022

  69. [71]

    Q. Zhou, F. Lu, M. Xu, et al., IEEE Photon. Technol. Lett. 2018, 30, 1511

    work page 2018

  70. [72]

    Y. Zhu, J. Ye, L. Yan, et al., J. Lightwave Technol. 2023, 41, 7192

    work page 2023

  71. [73]

    K. Wang, C. Wang, W. Li, et al., J. Lightwave Technol. 2022, 40, 2791

    work page 2022

  72. [74]

    Z. Li, J. Jia, G. Li, et al., Opt. Express 2023, 31, 15239

    work page 2023

  73. [75]

    J. Shi, Z. Li, J. Jia, et al., J. Lightwave Technol. 2023, 41, 2381

    work page 2023

  74. [76]

    A. Sun, Z. Li, J. Jia, et al., J. Lightwave Technol. 2023, 42, 80

    work page 2023

  75. [77]

    Y. Zhu, J. Ye, L. Yan, et al., J. Lightwave Technol. 2024, 42, 7532

    work page 2024

  76. [78]

    G. C. Valley, Opt. Express 2007, 15, 1955

    work page 2007

  77. [79]

    G. Yang, W. Zou, X. Li, et al., Opt. Express 2015, 23, 2174

    work page 2015

  78. [80]

    G. Yang, W. Zou, L. Yu, et al., Opt. Express 2016, 24, 24061

    work page 2016

  79. [81]

    Yao, IEEE Microw

    J. Yao, IEEE Microw. Mag. 2015, 16, 46

    work page 2015

  80. [82]

    Hamidi, D

    E. Hamidi, D. E. Leaird, A. M. Weiner, IEEE Trans. Microw. Theory Techn. 2010, 58, 3269

    work page 2010

Showing first 80 references.