ML-Based Beamforming and Direction Finding
Keywords:
Machine Learning For Array Signal Processing, Beamforming Parameter Estimation, Direction Finding Techniques, Supervised Learning For Beamforming, Unsupervised Learning Paradigms, Self-Supervised Learning Methods, Spatial Signal Modeling, Radar And Sonar Systems, Custom Neural Network Architectures, Convolutional Neural Networks For Spatial Data, Recurrent Neural Networks And LSTM, Transformer Architectures For Long-Range Dependency, Attention Mechanisms In Direction Finding, Real-World Data Evaluation, Domain-Oriented Learning Solutions, Robust Machine Learning Models, Adversarial Detection And Defense, Unlabeled Data Exploitation, High-Dimensional Spatiotemporal Modeling, 4D Signal Representation.Abstract
Machine learning techniques for the array signal processing tasks of beamforming and direction finding are reviewed, focusing on recent works in the field. Beamforming techniques for parameter estimation problems are framed as supervised learning tasks with spatial information captured by custom-designed networks. Unsupervised and self-supervised learning paradigms are applied to localized data, tackling tasks with elusive labels such as direction finding in radar and sonar. Evaluation on real-world data brings new problems to the discussion, showcasing the need for domain-oriented solutions. It encompasses networks for convolutional and recurrent networks adapted to spatial signals, transformer architectures for long-range dependencies, and attention mechanisms for depth and efficiency in direction finding. Robustness considerations are addressed, with particular emphasis on adversarial detection and defense.
Machine learning (ML) exploits statistical regularities in data to learn models that are capable of generalizing and performing well under unseen conditions. With years, radar and sonar systems along with their data have grown large. Nonetheless, the underlying abundance of unlabeled data has been overlooked until recently. For some other tasks, data collection is computationally expensive for both labeled and unlabeled data. Such work incorporated, combined, or evolved unsupervised and self-supervised learning paradigms. In supervised settings, the vast majority of approaches model only a small portion of the entire radar/sonar workflow, typically focusing on the parameter estimation problems cast into the beamforming frame. Most studies also utilize 1D temporal represented data. In addition, architectures dedicated to 2D convolutional neural networks have also been adapted to recurrent neural networks on the label correspondences using LSTM units. Modeling across 4D frames brings notable challenges from seeking and capturing spatial long-range dependency with depth and width.
References
1. Barthelme, A., & Utschick, W. (2021). DoA estimation using neural network-based covariance matrix reconstruction. IEEE Signal Processing Letters, 28, 783–787.
2. Wandale, S., & Ichige, K. (2021). Design of sparse arrays via deep learning for enhanced DOA estimation. EURASIP Journal on Advances in Signal Processing, 2021, 17.
3. Lyu, X., Wang, J., & Zhang, Y. (2021). Direction of arrival estimation in passive radar based on deep neural network. IET Signal Processing, 15(8), 506–518.
4. Sriram, H. K., Challa, K., Gadi, A. L., & Singreddy, S. (2025). AI and Cloud-Driven Transformation in Finance, Insurance, and the Automotive Ecosystem: A Multi-Sectoral Framework for Credit Risk, Mobility Services, and Consumer Protection. Anil Lokesh and singreddy, Sneha, AI and Cloud-Driven Transformation in Finance, Insurance, and the Automotive Ecosystem: A Multi-Sectoral Framework for Credit Risk, Mobility Services, and Consumer Protection (March 15, 2025).
5. Liu, Y., Tong, F., Zhong, S., Hong, Q., & Li, L. (2021). Reverberation aware deep learning for environment tolerant microphone array DOA estimation. Applied Acoustics, 184, 108337.
6. Ge, S., Li, K., & Rum, S. N. B. M. (2021). Deep learning approach in DOA estimation: A systematic literature review. Mobile Information Systems, 2021, 6392875.
7. Seenu, A., Sheelam, G. K., Motamary, S., Meda, R., Koppolu, H. K. R., & Inala, R. (2025). AI-Driven Innovations in Infrastructure Management with 6G Technology. In 2025 2nd International Conference on Computing and Data Science (ICCDS) (pp. 1–6). IEEE. 2025 2nd International Conference on Computing and Data Science (ICCDS). https://doi.org/10.1109/iccds64403.2025.11209649
8. Huang, X., Bell, M. A. L., & Ding, K. (2021). Deep learning for ultrasound beamforming in flexible array transducer. IEEE Transactions on Medical Imaging, 40(11), 3178–3189.
9. Kim, H., Kim, J., & Lee, S. (2021). DoA estimation for FMCW radar by 3D-CNN. Sensors, 21(16), 5319.
10. Narasareddy Annapareddy, V., Pamisetty, A., Malempati, M., Kaulwar, P. K., & Bhardwaj Komaragiri, V. (2025, April). Enhancing Solar Power System Efficiency Through AI-Driven Predictive Maintenance and Cloud-Based Infrastructure Stability Solutions. In International Conference on Smart Computing and Informatics (pp. 328-337). Cham: Springer Nature Switzerland.
11. Jiang, W., Ren, Y., Liu, Y., & Leng, J. (2022). Artificial neural networks and deep learning techniques applied to radar target detection: A review. Electronics, 11(1), 156.
12. Chen, D., Shi, S., Gu, X., & Shim, B. (2022). Robust DoA estimation using denoising autoencoder and deep neural networks. IEEE Access, 10, 52551–52564.
13. Dutta, P., Adusupalli, B., Koppolu, H. K. R., Dodda, A., Yağanoğlu, M., Banerjee, J. S., & Chakraborty, A. (2025, March). Textual Social Data Disinformation Analysis Using a Hybrid Context-Enhanced Deep Learning Model. In Doctoral Symposium on Human Centered Computing (pp. 342-352). Singapore: Springer Nature Singapore.
14. Hoang, D. T., & Lee, K. (2022). Deep learning-aided coherent direction-of-arrival estimation with the FTMR algorithm. IEEE Transactions on Signal Processing, 70, 1118–1130.
15. Chung, H., Park, H., & Kim, S. (2022). Leveraging deep learning for practical DoA estimation: Experiments with real data collected via USRP. Sensors, 22(19), 7578.
16. Challa, S. R., Burugulla, J. K. R., Pamisetty, A., Challa, K., & Paleti, S. (2025, April). AI and ML-Powered Cybersecurity Strategies for Cloud Computing: Ensuring Infrastructure Stability in Financial and Retail Sectors. In International Conference on Smart Computing and Informatics (pp. 315-327). Cham: Springer Nature Switzerland.
17. Muthuchidambaranathan, P., Jeyakumar, P., Manikandan, E., & Muthukumaran, P. (2022). Beamforming design with fully connected analog beamformer using deep learning. International Journal of Communication Systems, 35(7), e5109.
18. Maden, K., & Erer, I. (2022). DOA estimation in MIMO radars via deep learning. In Proceedings of the IEEE Radar Conference.
19. Challa, S. R., Kaulwar, P. K., Koppolu, H. K. R., Adusupalli, B., & Suura, S. R. (2025, April). Big Data and AI in Wealth Management: Leveraging Cloud Computing for Secure and Scalable Financial Infrastructure. In International Conference on Smart Computing and Informatics (pp. 307-318). Cham: Springer Nature Switzerland.
20. Kassir, H. A., Zaharis, Z. D., Lazaridis, P. I., Kantartzis, N. V., Yioultsis, T. V., & Xenos, T. D. (2022). A review of the state of the art and future challenges of deep learning-based beamforming. IEEE Access, 10, 80869–80882.
21. Chen, T., Shen, M., Guo, L., & Hu, X. (2023). A gridless DOA estimation algorithm based on unsupervised deep learning. Digital Signal Processing, 133, 103823.
22. Qin, Y. (2023). Deep networks for direction of arrival estimation with sparse prior in low SNR. IEEE Access, 11, 44637–44648.
23. Singireddy, J., Kaulwar, P. K., Somu, B., Meda, R., Dodda, A., & Yellanki, S. K. (2025, August). Reinforcement Learning-Based Asset Allocation in Algorithmic Trading for Banking Institutions. In International Conference on Artificial Intelligence: Theory and Applications (pp. 357-369). Cham: Springer Nature Switzerland.
24. Lan, X., Zhai, H., & Wang, Y. (2023). A novel DOA estimation of closely spaced sources using attention mechanism with conformal arrays. IEEE Access, 11, 44010–44018.
25. Li, Y., Shi, B., Shu, F., Song, Y., & Wang, J. (2023). Deep learning-based DOA estimation for hybrid massive MIMO receive array with overlapped subarrays. EURASIP Journal on Advances in Signal Processing, 2023, 110.
26. Davuluri, P. S. L. (2023). AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems. AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems (December 15, 2023).
27. Gao, S., Ma, H., Liu, H., Yang, J., & Yang, Y. (2023). A gridless DOA estimation method for sparse sensor array. Remote Sensing, 15(22), 5281.
28. Vadisetty, R., Nuka, S. T., Kalisetty, S., Pandugula, C., Burugulla, J. K. R., & Annapareddy, V. N. (2025, February). Generative AI for Advanced Recycling Processes in Polyethylene and Polypropylene Manufacturing. In International Ethical Hacking Conference (pp. 269-284). Singapore: Springer Nature Singapore.
29. Kowalk, U., Doclo, S., & Bitzer, J. (2023). Geometry-aware DoA estimation using a deep neural network with mixed-data input features. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing.
30. Subramanian, A. S., Weng, C., Watanabe, S., Yu, M., & Yu, D. (2022). Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition. Computer Speech & Language, 75, 101360.
31. Singireddy, S., Pandiri, L., Motamary, S., Kummari, D. N., Somu, B., & Lakkarasu, P. (2025, August). Blockchain-Powered Claims Validation for Enhancing Trust in Health and Auto Insurance Ecosystems. In International Conference on Artificial Intelligence: Theory and Applications (pp. 26-38). Cham: Springer Nature Switzerland.
32. Elbir, A. M., et al. (2023). Deep learning-based direction finding in the presence of direction-dependent mutual coupling. ICT Express, 9(4), 670–676.
33. Pandugula, C., Ganti, V. K. A. T., Kalisetty, S., Ande, R., & Mehta, D. (2025). Modeling the Som Kamla Amba Sub-Watershed Using Artificial Neural Networks (ANN) and the SWAT Tool. Available at SSRN 5341614.
34. Fadakar, A., Jafari, A., Tavana, P., Jahani, R., & Akhavan, S. (2024). Deep learning based 2D-DOA estimation using L-shaped arrays. Journal of the Franklin Institute, 361(6), 106743.
35. Zheng, S., Yang, Z., Shen, W., Zhang, L., et al. (2024). Deep learning-based DOA estimation. IEEE Transactions on Cognitive Communications and Networking, 10(3), 819–835.
36. Wang, M., Liu, X., Na, X., Zhang, Y., Liu, Y., & Qiu, T. (2024). Neural network-based DOA estimation for distributed sources in massive MIMO systems. AEU—International Journal of Electronics and Communications, 176, 155132.
37. KOTHAPALLI, S. L., SEENU, A., DILEEP, V., & YASMEEN, Z. (2025). THE FUTURE OF CUSTOMER ENGAGEMENT IN RETAIL BANKING: EXPLORING THE POTENTIAL OF AUGMENTED REALITY AND IMMERSIVE TECHNOLOGIES. INTERNATIONAL JOURNAL, 73(1), 72-79.
38. Chen, P., Chen, Z., Liu, L., Chen, Y., & Wang, X. (2024). SDOA-Net: An efficient deep-learning-based DOA estimation network for imperfect array. IEEE Transactions on Instrumentation and Measurement, 73, 8503512.
39. Zhang, B., He, J., Liu, P., Wang, L., et al. (2024). An automated multi-layer perceptron discriminative neural network based on Bayesian optimization achieves high-precision one-source single-snapshot direction-of-arrival estimation. Scientific Reports, 14, 10300.
40. Mylonakis, C. M., & Zaharis, Z. D. (2024). A novel three-dimensional direction-of-arrival estimation approach using a deep convolutional neural network. IEEE Open Journal of Vehicular Technology, 5, 643–657.
41. Ande, R., Mehta, D., Pandugula, C., Krishna AzithTejaGanti, V., & Kalisetty, S. (2025). Modeling the Som Kamla Amba sub-watershed using Artificial Neural Networks (ANN) and the SWAT tool. Available at SSRN 5341755.
42. Kassir, H. A., Kantartzis, N. V., Lazaridis, P. I., Sarigiannidis, P., Goudos, S. K., Christodoulou, C., & Zaharis, Z. D. (2024). Improving DOA estimation via an optimal deep residual neural network classifier on uniform linear arrays. IEEE Open Journal of Antennas and Propagation, 5(2), 460–473.
43. Liu, A., Guo, J., Arnatovich, Y., & Liu, Z. (2024). Lightweight deep neural network with data redundancy removal and regression for DOA estimation in sensor array. Remote Sensing, 16(8), 1423.
44. Bianco, S., Celona, L., Crotti, P., Napoletano, P., Petraglia, G., & Vinetti, P. (2024). Enhancing direction-of-arrival estimation with multi-task learning. Sensors, 24(22), 7390.
45. Lu, Y., Guan, H., Yang, K., Peng, T., Wen, C., & Li, X. (2024). Improving the accuracy of direction of arrival estimation with multiple signal inputs using deep learning. Sensors, 24(10), 2971.
46. Maguluri, K. K. (2025). Ethical challenges in artificial intelligence. How Artificial Intelligence is Transforming Healthcare IT: Applications in Diagnostics, Treatment Planning, and Patient Monitoring, 132.
47. Liu, L., et al. (2024). Direction of arrival estimation of coherent sources via a signal space deep convolution network. Symmetry, 16(4), 433.
48. Xu, X., & Huang, Q. (2024). MD-DOA: A model-based deep learning DOA estimation architecture. IEEE Sensors Journal.
49. Raiguru, P., Rout, S. K., Sahani, M., & Mishra, R. K. (2024). Machine learning-aided sparse direction of arrival estimation. IEEE Sensors Journal, 24(22), 38125–38134.
50. Su, Y., Wang, X., & Li, L. (2024). A novel off-grid deep learning framework for DOA estimation. In Proceedings of the 2024 IEEE International Conference on Signal, Information and Data Processing.
51. Monga, S., et al. (2024). Advanced beamforming and reflection control in intelligent reflecting surfaces with integrated channel estimation. IET Microwaves, Antennas & Propagation, 18(12), 917–931.
52. Di Barba, P., & Januszkiewicz, Ł. (2023). Linear antenna array modeling with deep neural networks. Journal of Applied Electromagnetism, 73(4).
53. Cousik, T. S., Shah, V. K., Reed, J. H., Tran, H. X., & Jana, R. (2023). Deep learning based fast and accurate beamforming for millimeter-wave systems. IEEE Wireless Communications Letters.
54. Hu, R., Jiang, L., & Li, P. (2021). Hybrid beamforming with deep learning for large-scale antenna arrays. IEEE Access, 9.
55. ADUSUPALLI, B. (2025). Redefining Financial Risk Strategies: The Integration of Smart Automation, Secure Access Systems, and Predictive Intelligence in Insurance, Lending, and Asset Management. JAIBDD.
56. Ma, K., Wang, Z., Tian, W., Chen, S., & Hanzo, L. (2021). Deep learning for beam-management: State-of-the-art, opportunities and challenges. IEEE Wireless Communications.
57. Jiang, W., et al. (2021). Deep-learning for radar: A survey. IEEE Access, 9, 141800–141818.
58. Bhalke, D., Paikrao, P. D., & Anguera, J. (2024). Deep learning-based beamforming approach incorporating linear antenna arrays. Journal of Telecommunications and Information Technology.
59. Ahmadinejad, A., & Talebi, S. (2025). Beamforming design via machine learning in intelligent reflecting surface-aided wireless communication. Physical Communication, 68, 102586.
60. Zhao, Y., Fan, X., Liu, J., Li, Y., Yao, L., & Wang, J. (2025). Efficient 2D-DOA estimation based on triple attention mechanism for L-shaped array. Sensors, 25(8), 2359.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2025 Benjamin Clark (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain full copyright of their published work. Under this license, others are free to share, copy, distribute, transmit, remix, transform, and build upon the published work for any purpose, including commercial use, provided that appropriate credit is given to the original authors, a link to the license is provided, and any changes made are clearly indicated. No additional restrictions may be applied that limit others from doing anything the license permits. All published articles are freely and permanently accessible online to readers worldwide without any subscription or access fees.
License URL: https://creativecommons.org/licenses/by/4.0/
