Machine Learning Applied to Optical Communication Systems

Dear Colleagues,

Optical communication utilizing light for high-speed data transmission has played a vital role in bringing forth the digital age. However, as the demand for data continues to grow, there is a pressing need to further increase the capacity, scalability, and reliability of optical communication systems. New technologies are of vital importance in supporting next-generation optical transport networks. Accompanied by the fast development of computing resources, in recent years, we have witnessed the growing trend of using machine learning (ML) in various applications. ML has found its place in a number of industries, and its application in optical transmission systems is one of the current hot topics to revolutionize traditional approaches in the field of optical communications.

ML algorithms such as the support vector machine, Gaussian mixture model, different types of neural networks, reinforcement learning, etc., have strong ability to analyze vast amounts of data, extract patterns, and make intelligent predictions. These properties make ML extremely suitable for applications in the optical communication domain, which is facing similar problems. By harnessing the power of ML, optical communication issues such as optical performance monitoring, modulation format identification, device imperfection estimation, channel modelling, and linear/nonlinear equalization can potentially be addressed in an efficient manner. On the other hand, optical communication is also well-suited for ML applications since it can easily generate and collect huge amounts of transmission data for ML to build complex mathematical models efficiently.

This Special Issue aims to dive into the exciting intersection of ML and optical communication systems to foster a deeper understanding of how ML can revolutionize optical communications and how optical communications can facilitate ML processing. We encourage researchers to contribute to this hot topic and present their state-of-the-art research or review articles. Potential directions include but are not limited to ML theory and design, performance evaluation, complexity analysis, hardware implementation, etc., for different types of optical communication systems (to solve the aforementioned problems) shown below:

• ML in short-reach transmission systems (IM/DD or self-coherent);
• ML in long-haul transmission systems (coherent);
• ML in optical access networks (e.g., passive optical networks);
• ML in radio-over-fiber systems;
• ML in optical wireless communications;
• ML in visible-light communication systems;
• ML in underwater optical communications;
• ML in optical vehicle-to-vehicle communication systems;
• ML in laser communications in space;
• ML in chaotic optical communications.

Dr. Jinlong Wei
Dr. Zhaopeng Xu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Photonics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• neural network
• deep learning
• optical communications
• digital signal processing
• optical performance monitoring
• modulation format identification
• device imperfection estimation
• channel modelling
• linear and nonlinear equalization