A Comprehensive Survey on Machine and Deep Learning for Optical Communications
Bibliographic record
Abstract
The increasing complexity of optical communication systems and networks necessitates advanced methodologies for extracting valuable insights from vast and heterogeneous datasets. Machine learning (ML) and deep learning (DL) have emerged as pivotal tools in this domain, revolutionizing data analysis and enabling automated self-configuration in optical communication systems. Their adoption is fueled by the growing intricacy of systems and links, driven by numerous adjustable and interdependent parameters. This complexity is particularly evident in areas such as coherent transceivers, advanced digital signal processing, optical performance monitoring, cross-layer network optimizations, and nonlinearity compensation. While ML and DL offer immense potential, their application in optical communications is still in its early stages, with significant opportunities remaining unexplored. Many algorithms have yet to be fully deployed in practical settings, underscoring the emerging nature of this research area. This paper presents a comprehensive survey of ML and DL applications across optical fiber communication (OFC), optical wireless communication (OWC), and optical communication networking (OCN), highlighting the challenges, current advancements, and future potential of these approaches. To address the identified gaps, this survey evaluates and compares ML and DL algorithms in terms of their performance, complexity, objectives, input data, metrics, and applications in optical communication. Specific emphasis is placed on identifying how these algorithms enhance system performance and optimization. Furthermore, the advantages and limitations of existing methods are analyzed, offering a clear perspective on the role of ML and DL in this domain. The survey also includes updated visual representations and domain-specific examples to elucidate the practical applications of ML and DL in OFC, OWC, and OCN. It concludes by discussing the open challenges, proposing potential solutions, and identifying promising future research directions to foster advancements in intelligent optical communication systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".