# HELENA for 5G NR LEO NTN Channel Estimation: A Comparative Evaluation

arXiv: https://arxiv.org/abs/2609.14735 · HTML: https://mlsanity.com/paper/2609.14735/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Deep Learning-Based Channel Estimation](https://mlsanity.com/paper/1810.05893/) (2018)
- [Low Complexity Deep Learning Augmented Wireless Channel Estimation for Pilot-Based OFDM on Zynq System on Chip](https://mlsanity.com/paper/2403.01098/) (2024)
- [A Compute&Memory Efficient Model-Driven Neural 5G Receiver for Edge AI-assisted RAN](https://mlsanity.com/paper/2508.12892/) (2025)
- [HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention](https://mlsanity.com/paper/2506.13408/) (2025)
- [On-board AI-based Channel Estimation for LEO NTNs](https://mlsanity.com/paper/2607.15127/) (2026)

## Abstract (arXiv)

Deep Learning (DL)-based channel estimation has shown high accuracy and low latency in terrestrial 5G NR, but Low Earth Orbit (LEO) Non-Terrestrial Networks (NTNs) introduce Doppler and synchronization impairments that may require NTN-specific architectures. We test whether High-Efficiency Learning-based channel Estimation using dual Neural Attention (HELENA), originally designed for terrestrial channels, remains effective after NTN retraining and suitable across high-performance and power-constrained inference platforms. Its unchanged architecture is trained on paired receiver-compensated (NTN-1) and residual-impaired (NTN-2) datasets and compared with eight terrestrial-origin models trained on the same NTN data and the NTN-specific MDELAN-SISO. HELENA achieves the lowest observed SNR-averaged NMSE among the DL estimators in both conditions, including 55.8-62.7% lower linear-scale NMSE than MDELAN-SISO. All DL models degrade in NTN-2, demonstrating the challenge posed by residual Doppler and its associated impairments. On an RTX PRO 4500, HELENA achieves 0.0595 ms 99th-percentile (P99) inference latency, 88.1% below the 0.5 ms budget, with lower energy than its closest attention-based competitors. On a 10 W Jetson Orin NX, it retains a favorable accuracy-energy trade-off, but no model meets the P99 budget. Thus, HELENA needs no NTN-specific redesign for the evaluated task, while embedded tail latency remains an open challenge.