arxiv: 2605.08912 · v1 · submitted 2026-05-09 · 📡 eess.SP

Recognition: 2 theorem links

· Lean Theorem

OTFS-IM-Assisted Non-Terrestrial Networks Relying on Autoencoder-Aided Soft-Decision Detection

Chao Xu, Chao Zhang, Lajos Hanzo, Mohammed EL-Hajjar, Xinyu Feng

Authors on Pith no claims yet

Pith reviewed 2026-05-12 04:02 UTC · model grok-4.3

classification 📡 eess.SP

keywords OTFSindex modulationautoencoderPAPR reductionnon-terrestrial networkssoft-decision detectionDFT spreadinghigh Doppler

0 comments

The pith

MB-DFT-S-OTFS-IM with autoencoder reduces PAPR and enables accurate detection over high-Doppler satellite links.

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

The paper develops an OTFS-based scheme that applies multi-band DFT spreading and index modulation to address high PAPR, bandwidth inefficiency from cyclic prefixes, and carrier frequency offset sensitivity in non-terrestrial networks. It introduces a deep learning autoencoder where the encoder is trained specifically to minimize PAPR and the decoder reconstructs the transmitted signal for both hard- and soft-decision detection. The combined MB-DFT-S-OTFS-IM approach provides frequency diversity and throughput gains in the delay-Doppler domain while extending to practical satellite-to-ground channel models. A sympathetic reader would care because power-efficient, Doppler-resilient transmission is essential for satellite systems where amplifiers are constrained and mobility is extreme.

Core claim

The authors establish that MB-DFT-S-OTFS-IM, which integrates multi-band discrete Fourier transform spreading and index modulation into OTFS, reduces PAPR, improves throughput via delay-Doppler index modulation, and gains frequency diversity for carrier frequency offset tolerance. The deep learning autoencoder architecture trains the encoder to minimize PAPR while the decoder accurately reconstructs the signal, supporting both hard- and soft-decision detection in practical NTN environments.

What carries the argument

MB-DFT-S-OTFS-IM modulation paired with a deep learning autoencoder whose encoder minimizes PAPR and whose decoder reconstructs the transmitted signal for hard- and soft-decision detection.

If this is right

Lower PAPR enables more efficient power amplification at satellite transmitters.
Index modulation in the delay-Doppler domain increases throughput without extra bandwidth.
Multi-band spreading supplies frequency diversity that improves robustness to carrier frequency offsets.
The autoencoder supports both hard- and soft-decision detection, giving receiver design flexibility.
Performance holds across multiple satellite-to-ground NTN channel models.

Where Pith is reading between the lines

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

The scheme could reduce the size or power rating of satellite power amplifiers in future NTN deployments.
Real-time implementation would require evaluating the decoder's computational cost on resource-limited satellite receivers.
The autoencoder training procedure might be adapted to other high-mobility modulation formats beyond OTFS.

Load-bearing premise

The autoencoder trained on simulated data generalizes to practical NTN channels without major loss in PAPR reduction or detection accuracy.

What would settle it

A direct comparison of measured PAPR values and bit-error rates on real satellite channel recordings against the performance reported from the simulated NTN model.

Figures

Figures reproduced from arXiv: 2605.08912 by Chao Xu, Chao Zhang, Lajos Hanzo, Mohammed EL-Hajjar, Xinyu Feng.

**Figure 1.** Figure 1: Block diagram of the OTFS system. A. OTFS System At the transmitter, the binary information bits are first grouped and mapped onto amplitude phase modulation symbols, which are arranged on a two-dimensional Delay– Doppler (DD) grid. As illustrated in [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗

**Figure 2.** Figure 2: Block diagram of the proposed MB-DFT-S-OTFS-IM system. [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗

**Figure 3.** Figure 3: Block diagram of the proposed AE-based OTFS-IM system. [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗

**Figure 4.** Figure 4: The transceiver architecture of LDPC encoded MB [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗

**Figure 5.** Figure 5: BER performance comparison between the pro [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗

**Figure 6.** Figure 6: PAPR comparison between the proposed MB-AE [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗

**Figure 7.** Figure 7: Illustration of the BER performance and CCDF of PAPR comparison between the proposed MB-AE-based [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗

**Figure 8.** Figure 8: Illustration of the parameters and setting configuration of the proposed MB-AE-based scheme over a shadowed [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗

**Figure 9.** Figure 9: BER performance of the proposed AE-based [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗

**Figure 10.** Figure 10: BER performance of the proposed AE-based [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗

**Figure 11.** Figure 11: BER performance of the proposed AE-based [PITH_FULL_IMAGE:figures/full_fig_p014_11.png] view at source ↗

read the original abstract

Orthogonal Time Frequency Space ({OTFS}) modulation offers significant advantages over Orthogonal Frequency Division Multiplexing ({OFDM}), particularly in high speed environments. Hence, we consider {OTFS} transmission over high-Doppler Non-Terrestrial Networks ({NTN}). However, OTFS-based systems inherit some deficiencies from {OFDM}, such as its high peak to average power ratio, the bandwidth efficiency loss due to the cyclic prefix, and the sensitivity to the carrier frequency offset. Against this background, we harness both Multi-Band Discrete Fourier Transform-based Spreading (MB-DFT-S) and Index Modulation ({IM}) in our {OTFS} system, termed as MB-DFT-S-OTFS-IM. More explicitly, 1) DFT-S has been shown to reduce the {PAPR}; 2) {IM} is capable of improving the throughput by harnessing it in the Delay and Doppler ({DD}) domain; and 3) MB-DFT-S-OTFS-IM provides frequency diversity gain, which benefits the tolerance to carrier frequency offset. Furthermore, we propose a {PAPR} reduction method based on a Deep Learning ({DL}) Autoencoder ({AE}) architecture for both hard- and soft-decision detection, where the encoder is specifically trained for minimizing {PAPR} and the decoder is conceived for accurately reconstructing the transmitted signal. Finally, we extend the proposed {AE}-aided {OTFS-IM} scheme constructed for a practical {NTN} channel model, representing a variety of satellite-to-ground schemes.

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.

Desk Editor's Note private letter to a colleague

This applies OTFS-IM plus MB-DFT-S and an autoencoder to NTN channels, but the claimed PAPR and detection gains rest on untested transfer from simulated training data to real satellite statistics.

read the letter

They combine orthogonal time frequency space modulation with index modulation in the delay-Doppler domain, multi-band DFT spreading, and a deep learning autoencoder to cut peak-to-average power ratio while supporting soft-decision detection. The target is non-terrestrial networks with high Doppler shifts from satellites. What stands out is the practical focus. OTFS already copes better with mobility than OFDM, index modulation squeezes extra bits into the DD grid, and MB-DFT-S spreads to lower PAPR and add CFO tolerance. The autoencoder is trained so its encoder minimizes PAPR and its decoder reconstructs the signal accurately for detection. They extend this to a practical NTN channel model covering different satellite-to-ground links. This approach addresses real pain points in satellite communications: high PAPR wastes power, CFO hurts performance in fast-moving scenarios, and throughput matters for bandwidth-limited links. The soft-decision option could help in low-SNR regimes common in NTN. The main concern is generalization. The autoencoder relies on training data from simulations. If those simulations don't capture the exact statistics of real NTN channels—varying Doppler, delay spreads, or other impairments—the PAPR reduction and detection accuracy might not hold up. The paper says the scheme is constructed for the practical model, but without details on whether training included NTN-specific profiles or domain adaptation, it's unclear how robust it is. Any performance claims depend on this transfer working. The math and citations seem to rest on established OTFS and AE literature, which is fine for an application paper. No obvious circularity in the description. This work suits researchers in wireless communications who focus on physical-layer techniques for 6G non-terrestrial networks or on applying machine learning to modulation and detection. Someone already familiar with OTFS would see how the pieces fit together and might pick up the AE design for their own setups. I would recommend sending it for peer review. The area is active, the problems are relevant, and the proposal is concrete enough that referees can evaluate the simulations and suggest improvements on validation.

Referee Report

2 major / 1 minor

Summary. The paper proposes an MB-DFT-S-OTFS-IM scheme for high-Doppler NTN environments that combines multi-band DFT spreading for PAPR reduction and CFO tolerance, index modulation in the delay-Doppler domain for improved throughput, and an autoencoder architecture whose encoder is trained to minimize PAPR while the decoder supports accurate signal reconstruction for both hard- and soft-decision detection. The scheme is stated to be constructed for practical NTN channel models representing satellite-to-ground links.

Significance. If the autoencoder generalizes from its training distribution to realistic NTN channels (high Doppler, specific delay-Doppler profiles, CFO), the combination of classical spreading/IM techniques with learned PAPR reduction could offer measurable improvements in power efficiency and detection reliability for NTN systems. The work draws on established OTFS and AE literature but does not yet demonstrate parameter-free gains or reproducible code that would strengthen its impact.

major comments (2)

[Abstract] Abstract: the statement that the AE-aided MB-DFT-S-OTFS-IM scheme is 'constructed for a practical NTN channel model' does not specify whether the autoencoder was trained end-to-end on NTN-specific statistics (high Doppler, delay-Doppler profiles, CFO) or only on generic simulated OTFS data. This training-distribution match is load-bearing for every subsequent claim of PAPR reduction and detection accuracy in NTN.
[Abstract] Abstract: no equations, simulation results, error bars, or ablation studies are referenced, so it is impossible to verify whether the reported PAPR and BER gains survive when the AE is tested on NTN channels that differ from the training distribution.

minor comments (1)

[Abstract] The abstract introduces multiple acronyms (MB-DFT-S, IM, DD, CFO) in quick succession; a brief parenthetical expansion on first use would improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript proposing the MB-DFT-S-OTFS-IM scheme with autoencoder-aided PAPR reduction and soft-decision detection for NTN channels. We address each major comment below and will make targeted revisions to improve clarity.

read point-by-point responses

Referee: [Abstract] Abstract: the statement that the AE-aided MB-DFT-S-OTFS-IM scheme is 'constructed for a practical NTN channel model' does not specify whether the autoencoder was trained end-to-end on NTN-specific statistics (high Doppler, delay-Doppler profiles, CFO) or only on generic simulated OTFS data. This training-distribution match is load-bearing for every subsequent claim of PAPR reduction and detection accuracy in NTN.

Authors: We appreciate this observation. The autoencoder is trained end-to-end on data generated from the practical NTN channel model, incorporating high Doppler shifts, realistic delay-Doppler profiles, and CFO statistics representative of satellite-to-ground links, as detailed in the system model and training procedure sections. This ensures the training and test distributions align. We will revise the abstract to explicitly state that the AE training uses NTN-specific statistics. revision: yes
Referee: [Abstract] Abstract: no equations, simulation results, error bars, or ablation studies are referenced, so it is impossible to verify whether the reported PAPR and BER gains survive when the AE is tested on NTN channels that differ from the training distribution.

Authors: Abstracts are concise summaries and do not conventionally include equations, detailed results, error bars, or ablations; these appear in the main body with supporting figures. The manuscript presents PAPR and BER results (with error bars) under the NTN channel model, along with ablation studies on the AE components, confirming gains on matching distributions. We will partially revise the abstract to reference the relevant sections and figures for verification. revision: partial

Circularity Check

0 steps flagged

No circularity: proposal builds on prior OTFS/DL results without self-referential reduction

full rationale

The manuscript proposes a new MB-DFT-S-OTFS-IM scheme augmented by an autoencoder trained to minimize PAPR while reconstructing the signal for hard/soft detection, then extends the construction to a practical NTN channel model. No equations or steps reduce the claimed PAPR reduction or detection accuracy to parameters fitted on the same data and then re-labeled as predictions. The abstract and description cite established PAPR benefits of DFT-S and IM from prior literature (not self-citations bearing the central claim) and treat the AE as a trainable architecture rather than a self-definitional loop. Generalization assumptions to NTN statistics are empirical risks, not circularity. The derivation chain remains independent of its own outputs.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

Only abstract available so ledger is incomplete; relies on standard assumptions from wireless literature plus AE training that introduces fitted parameters.

free parameters (1)

Autoencoder weights and hyperparameters
Trained to minimize PAPR; specific values and training data not visible in abstract.

axioms (1)

domain assumption OTFS provides significant advantages over OFDM in high-Doppler environments
Invoked in first sentence as background; no derivation supplied.

pith-pipeline@v0.9.0 · 5600 in / 1168 out tokens · 40928 ms · 2026-05-12T04:02:10.480355+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

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

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

we propose a PAPR reduction method based on a Deep Learning (DL) Autoencoder (AE) architecture ... encoder is specifically trained for minimizing PAPR and the decoder is conceived for accurately reconstructing the transmitted signal
IndisputableMonolith/Foundation/AlexanderDuality.lean alexander_duality_circle_linking unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

MB-DFT-S-OTFS-IM ... DFT-S has been shown to reduce the PAPR; IM ... in the Delay and Doppler (DD) domain

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

48 extracted references · 48 canonical work pages

[1]

Creating Eﬀicient Integrated Satellite- Terrestrial Networks in the 6G Era,

X. Zhu and C. Jiang, “Creating Eﬀicient Integrated Satellite- Terrestrial Networks in the 6G Era,” IEEE Wireless Commun., vol. 29, no. 4, pp. 154–160, Aug. 2022

work page 2022
[2]

Sixty Years of Coherent Versus Non-Coherent Tradeoffs and the Road From 5G to Wireless Futures,

C. Xu, N. Ishikawa, R. Rajashekar, S. Sugiura, R. G. Maunder, Z. Wang, L.-L. Yang, and L. Hanzo, “Sixty Years of Coherent Versus Non-Coherent Tradeoffs and the Road From 5G to Wireless Futures,” IEEE Access, vol. 7, pp. 178 246–178 299, 2019

work page 2019
[3]

Satellite- Terrestrial Integrated 6G: An Ultra-Dense LEO Networking Management Architecture,

T. Ma, B. Qian, X. Qin, X. Liu, H. Zhou, and L. Zhao, “Satellite- Terrestrial Integrated 6G: An Ultra-Dense LEO Networking Management Architecture,” IEEE Wireless Commun., vol. 31, no. 1, pp. 62–69, Feb. 2024

work page 2024
[4]

5G from Space: An Overview of 3GPP Non-Terrestrial Networks,

X. Lin, S. Rommer, S. Euler, E. A. Yavuz, and R. S. Karls- son, “5G from Space: An Overview of 3GPP Non-Terrestrial Networks,” IEEE Communications Standards Magazine, vol. 5, no. 4, pp. 147–153, 2021

work page 2021
[5]

Non-Terrestrial Networks in 5G & Beyond: A Survey,

F. Rinaldi, H.-L. Maattanen, J. Torsner, S. Pizzi, S. Andreev, A. Iera, Y. Koucheryavy, and G. Araniti, “Non-Terrestrial Networks in 5G & Beyond: A Survey,” IEEE Access, vol. 8, pp. 165 178–165 200, 2020

work page 2020
[6]

LEO Satellites in 5G and Beyond Networks: A Review From a Standardization Perspective,

T. Darwish, G. K. Kurt, H. Yanikomeroglu, M. Bellemare, and G. Lamontagne, “LEO Satellites in 5G and Beyond Networks: A Review From a Standardization Perspective,” IEEE Access, vol. 10, pp. 35 040–35 060, 2022

work page 2022
[7]

Space-Air-Ground Integrated Network: A Survey,

J. Liu, Y. Shi, Z. M. Fadlullah, and N. Kato, “Space-Air-Ground Integrated Network: A Survey,” IEEE Commun. Surveys Tuto- rials, vol. 20, no. 4, pp. 2714–2741, Fourth-quarter 2018

work page 2018
[8]

Study on New Radio (NR) to support non‑terrestrial networks (Release 15),

3GPP, “Study on New Radio (NR) to support non‑terrestrial networks (Release 15),” 3GPP, TR 38.811 V15.1.0, Jun. 2019

work page 2019
[9]

Orthogonal Time Frequency Space Modulation,

R. Hadani, S. Rakib, M. Tsatsanis, A. Monk, A. J. Goldsmith, A. F. Molisch, and R. Calderbank, “Orthogonal Time Frequency Space Modulation,” in 2017 IEEE Wireless Communications and Networking Conference (WCNC), 2017, pp. 1–6

work page 2017
[10]

Orthogonal Time-Frequency Space Modulation: A Promising Next-Generation Waveform,

Z. Wei, W. Yuan, S. Li, J. Yuan, G. Bharatula, R. Hadani, and L. Hanzo, “Orthogonal Time-Frequency Space Modulation: A Promising Next-Generation Waveform,” IEEE Wireless Com- munications, vol. 28, no. 4, pp. 136–144, 2021

work page 2021
[11]

OTFS-Aided RIS-Assisted SAGIN Systems Outperform Their OFDM Counterparts in Doubly Selective High-Doppler Scenarios,

C. Xu, L. Xiang, J. An, C. Dong, S. Sugiura, R. G. Maunder, L.-L. Yang, and L. Hanzo, “OTFS-Aided RIS-Assisted SAGIN Systems Outperform Their OFDM Counterparts in Doubly Selective High-Doppler Scenarios,” IEEE Internet of Things Journal, vol. 10, no. 1, pp. 682–703, 2023

work page 2023
[12]

Autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation,

Y. I. Tek, A. T. Dogukan, and E. Basar, “Autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation,” IEEE Communications Letters, vol. 27, no. 10, pp. 2628–2632, 2023

work page 2023
[14]

PAPR Reduction Precoding for Orthogonal Time Fre- quency Space Modulation,

——, “PAPR Reduction Precoding for Orthogonal Time Fre- quency Space Modulation,” in 2023 46th International Confer- ence on Telecommunications and Signal Processing (TSP), 2023, pp. 172–176

work page 2023
[15]

A Novel Precoder for Peak-to-A verage Power Ratio Reduction in OTFS Systems,

S. Prakash, V. Khammammetti, and S. K. Mohammed, “A Novel Precoder for Peak-to-A verage Power Ratio Reduction in OTFS Systems,” in 2025 International Conference on Mi- crowave, Optical, and Communication Engineering (ICMOCE), 2025, pp. 1–5

work page 2025
[16]

Index modulation techniques for 5G wireless net- works,

E. Basar, “Index modulation techniques for 5G wireless net- works,” IEEE Communications Magazine, vol. 54, no. 7, pp. 168–175, 2016

work page 2016
[17]

Compressed Sensing-Aided Multi-Dimensional Index Modulation,

S. Lu, I. A. Hemadeh, M. El-Hajjar, and L. Hanzo, “Compressed Sensing-Aided Multi-Dimensional Index Modulation,” IEEE Transactions on Communications, vol. 67, no. 6, pp. 4074–4087, 2019

work page 2019
[18]

Near- Instantaneously Adaptive Learning-Assisted and Compressed Sensing-Aided Joint Multi-Dimensional Index Modulation,

X. Feng, M. El-Hajjar, C. Xu, and L. Hanzo, “Near- Instantaneously Adaptive Learning-Assisted and Compressed Sensing-Aided Joint Multi-Dimensional Index Modulation,” IEEE Open Journal of Vehicular Technology, vol. 4, pp. 893– 912, 2023

work page 2023
[19]

Doppler Resilient Orthogonal Time-Frequency Space (OTFS) Systems Based on Index Modulation,

Y. Liang, L. Li, P. Fan, and Y. Guan, “Doppler Resilient Orthogonal Time-Frequency Space (OTFS) Systems Based on Index Modulation,” in 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1–5

work page 2020
[20]

Diversity and PAPR Enhancement in OTFS using Indexing,

J. K. Francis, R. Mary Augustine, and A. Chockalingam, “Diversity and PAPR Enhancement in OTFS using Indexing,” in 2021 IEEE 93rd Vehicular Technology Conference (VTC2021- Spring), 2021, pp. 1–6

work page 2021
[21]

Orthogonal Time Frequency Space (OTFS) With Dual-Mode Index Modulation,

H. Zhao, D. He, Z. Kang, and H. Wang, “Orthogonal Time Frequency Space (OTFS) With Dual-Mode Index Modulation,” IEEE Wireless Communications Letters, vol. 10, no. 5, pp. 991– 995, 2021

work page 2021
[22]

Deep- Learning Based Signal Detection for MIMO-OTFS Systems,

Y. K. Enku, B. Bai, S. Li, M. Liu, and I. N. Tiba, “Deep- Learning Based Signal Detection for MIMO-OTFS Systems,” in 2022 IEEE International Conference on Communications Workshops (ICC Workshops), 2022, pp. 1–5

work page 2022
[23]

A Novel PAPR Reduction Scheme for OFDM System Based on Deep Learning,

M. Kim, W. Lee, and D.-H. Cho, “A Novel PAPR Reduction Scheme for OFDM System Based on Deep Learning,” IEEE Communications Letters, vol. 22, no. 3, pp. 510–513, 2018

work page 2018
[24]

Autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation,

Y. I. Tek, A. T. Dogukan, and E. Basar, “Autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation,” 15 IEEE Communications Letters, vol. 27, no. 10, pp. 2628–2632, 2023

work page 2023
[25]

Auto-Encoder Based Orthogonal Time Frequency Space Modulation and De- tection With Meta-Learning,

J. Park, J.-P. Hong, H. Kim, and B. J. Jeong, “Auto-Encoder Based Orthogonal Time Frequency Space Modulation and De- tection With Meta-Learning,” IEEE Access, vol. 11, pp. 43 008– 43 018, 2023

work page 2023
[27]

Autoencoder-Based Enhanced Joint Delay-Doppler Index Modulation for OTFS Modulation,

Y. I. Tek and E. Basar, “Autoencoder-Based Enhanced Joint Delay-Doppler Index Modulation for OTFS Modulation,” in 2024 32nd Signal Processing and Communications Applications Conference (SIU), 2024, pp. 1–4

work page 2024
[28]

Trainable Communication Systems: Concepts and Prototype,

S. Cammerer, F. A. Aoudia, S. Dörner, M. Stark, J. Hoydis, and S. ten Brink, “Trainable Communication Systems: Concepts and Prototype,” IEEE Transactions on Communications, vol. 68, no. 9, pp. 5489–5503, 2020

work page 2020
[29]

Deep Learning-Aided Optical IM/DD OFDM Approaches the Throughput of RF-OFDM,

T. Van Luong, X. Zhang, L. Xiang, T. M. Hoang, C. Xu, P. Petropoulos, and L. Hanzo, “Deep Learning-Aided Optical IM/DD OFDM Approaches the Throughput of RF-OFDM,” IEEE Journal on Selected Areas in Communications, vol. 40, no. 1, pp. 212–226, 2022

work page 2022
[30]

Delay- Doppler domain decision feedback turbo equalization for OTFS modulation,

Y. Zhang, Q. Zhang, C. He, Y. Zhou, and L. Jing, “Delay- Doppler domain decision feedback turbo equalization for OTFS modulation,” Physical Communication, vol. 52, p. 101699, 2022

work page 2022
[31]

Turbo Detection Aided Autoencoder for Multicarrier Wireless Systems: Integrating Deep Learning Into Channel Coded Systems,

C. Xu, T. Van Luong, L. Xiang, S. Sugiura, R. G. Maunder, L.- L. Yang, and L. Hanzo, “Turbo Detection Aided Autoencoder for Multicarrier Wireless Systems: Integrating Deep Learning Into Channel Coded Systems,” IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 2, pp. 600–614, 2022

work page 2022
[32]

Space-, Time- and Frequency-Domain Index Modulation for Next-Generation Wireless: A Unified Single-/Multi-Carrier and Single-/Multi-RF MIMO Framework,

C. Xu, Y. Xiong, N. Ishikawa, R. Rajashekar, S. Sugiura, Z. Wang, S.-X. Ng, L.-L. Yang, and L. Hanzo, “Space-, Time- and Frequency-Domain Index Modulation for Next-Generation Wireless: A Unified Single-/Multi-Carrier and Single-/Multi-RF MIMO Framework,” IEEE Transactions on Wireless Commu- nications, vol. 20, no. 6, pp. 3847–3864, 2021

work page 2021
[33]

Single carrier FDMA for uplink wireless transmission,

H. G. Myung, J. Lim, and D. J. Goodman, “Single carrier FDMA for uplink wireless transmission,” IEEE Vehicular Tech- nology Magazine, vol. 1, no. 3, pp. 30–38, 2006

work page 2006
[34]

DFT-Spread Orthogonal Time Frequency Space System With Superimposed Pilots for Tera- hertz Integrated Sensing and Communication,

Y. Wu, C. Han, and Z. Chen, “DFT-Spread Orthogonal Time Frequency Space System With Superimposed Pilots for Tera- hertz Integrated Sensing and Communication,” IEEE Transac- tions on Wireless Communications, vol. 22, no. 11, pp. 7361– 7376, 2023

work page 2023
[35]

Deep Learning in Physical Layer Communications,

Z. Qin, H. Ye, G. Y. Li, and B.-H. F. Juang, “Deep Learning in Physical Layer Communications,” IEEE Wireless Communi- cations, vol. 26, no. 2, pp. 93–99, 2019

work page 2019
[36]

Turbo Decoding and Detection for Wireless Applications,

L. Hanzo, J. P. Woodard, and P. Robertson, “Turbo Decoding and Detection for Wireless Applications,” Proceedings of the IEEE, vol. 95, no. 6, pp. 1178–1200, 2007

work page 2007
[37]

Autoencoder Based PAPR Reduction for OTFS Modulation,

M. Liu, M.-M. Zhao, M. Lei, and M.-J. Zhao, “Autoencoder Based PAPR Reduction for OTFS Modulation,” in 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021, pp. 1–5

work page 2021
[38]

Derivation of OTFS Modulation From First Principles,

S. K. Mohammed, “Derivation of OTFS Modulation From First Principles,” IEEE Transactions on Vehicular Technology, vol. 70, no. 8, pp. 7619–7636, 2021

work page 2021
[39]

Low Complexity Modem Structure for OFDM- Based Orthogonal Time Frequency Space Modulation,

A. Farhang, A. RezazadehReyhani, L. E. Doyle, and B. Farhang- Boroujeny, “Low Complexity Modem Structure for OFDM- Based Orthogonal Time Frequency Space Modulation,” IEEE Wireless Communications Letters, vol. 7, no. 3, pp. 344–347, 2018

work page 2018
[40]

Channel Estimation for Orthogonal Time Frequency Space (OTFS) Mas- sive MIMO,

W. Shen, L. Dai, J. An, P. Fan, and R. W. Heath, “Channel Estimation for Orthogonal Time Frequency Space (OTFS) Mas- sive MIMO,” IEEE Transactions on Signal Processing, vol. 67, no. 16, pp. 4204–4217, 2019

work page 2019
[41]

Interfer- ence Cancellation and Iterative Detection for Orthogonal Time Frequency Space Modulation,

P. Raviteja, K. T. Phan, Y. Hong, and E. Viterbo, “Interfer- ence Cancellation and Iterative Detection for Orthogonal Time Frequency Space Modulation,” IEEE Transactions on Wireless Communications, vol. 17, no. 10, pp. 6501–6515, 2018

work page 2018
[42]

Low-Complexity Linear Equalization for OTFS Modulation,

G. D. Surabhi and A. Chockalingam, “Low-Complexity Linear Equalization for OTFS Modulation,” IEEE Communications Letters, vol. 24, no. 2, pp. 330–334, 2020

work page 2020
[43]

Space-Air- Ground Integrated Networks: Their Channel Model and Perfor- mance Analysis,

C. Zhang, Q. Li, C. Xu, L.-L. Yang, and L. Hanzo, “Space-Air- Ground Integrated Networks: Their Channel Model and Perfor- mance Analysis,” IEEE Open Journal of Vehicular Technology, vol. 6, pp. 1501–1523, 2025

work page 2025
[44]

W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, Numerical Recipes: The Art of Scientific Computing, 3rd ed. Cambridge, UK: Cambridge University Press, 2007

work page 2007
[45]

A new simple model for land mobile satellite channels: first- and second-order statistics,

A. Abdi, W. Lau, M.-S. Alouini, and M. Kaveh, “A new simple model for land mobile satellite channels: first- and second-order statistics,” IEEE Trans. Wireless Commun., vol. 2, no. 3, pp. 519–528, 2003

work page 2003
[46]

The HITRAN2012 Molecular Spectroscopic Database,

L. Rothman, I. Gordon, Y. Babikov, and A. B. r, “The HITRAN2012 Molecular Spectroscopic Database,” J. Quant. Spectrosc. Radiat. Transfer., vol. 130, pp. 4–50, 2013, HITRAN2012 special issue. [Online]. A vailable: https://www. sciencedirect.com/science/article/pii/S0022407313002859

work page 2013
[47]

Zenith absorption data,

“Zenith absorption data,” Earth Observation Data Group - University of Oxford, 2025, accessed: Mar. 13,

work page 2025
[48]

A vailable: https://eodg.atm.ox.ac.uk/ATLAS/ zenith-absorption

[Online]. A vailable: https://eodg.atm.ox.ac.uk/ATLAS/ zenith-absorption

work page
[49]

Near-Capacity Wireless System Design Principles,

H. V. Nguyen, C. Xu, S. X. Ng, and L. Hanzo, “Near-Capacity Wireless System Design Principles,” IEEE Communications Surveys Tutorials, vol. 17, no. 4, pp. 1806–1833, 2015

work page 2015
[50]

C. M. Bishop and N. M. Nasrabadi, Pattern recognition and machine learning. Springer, 2006, vol. 4, no. 4

work page 2006