Announcements

We recently had the opportunity to interview Prof. Dr. Max Marian about his paper “Physics-Informed Machine Learning—An Emerging Trend in Tribology”, which was published in Lubricants (ISSN: 2075-4442) and has been highly praised by our evaluation committee members and readers.

The following is an interview with Prof. Dr. Max Marian:

1. Could you please briefly introduce yourself to our readers? Could you share your current research focus and the latest developments in your work?

Thank you very much for the invitation and the recognition. My name is Max Marian, and I am currently a Full Professor and Executive Director of the Institute of Machine Design and Tribology (IMKT) at Leibniz University Hannover, as well as a Professor for Multiscale Engineering Mechanics at Pontificia Universidad Católica de Chile. My research centers around advancing energy efficiency and sustainability through tribology, with a particular emphasis on innovative surface modifications, such as coatings, micro-textures, and 2D materials. Beyond classical tribological applications like machine elements and engine components, my group has also expanded into biotribology, artificial joints, and emerging fields such as triboelectric nanogenerators. Recently, a major focus of my work has been on integrating numerical multiscale tribo-simulation with machine learning, especially data-driven approaches, but also physics-informed machine learning, to enable better predictions and understanding of friction, wear, and lubrication phenomena, even in scenarios with scarce or noisy data.

2. Could you provide a brief overview of the main content of your award-winning paper?

The awarded review article, co-authored with Stephan Tremmel, introduces the concept of physics-informed machine learning to the tribology community. Traditional machine learning models in tribology often rely purely on large datasets, which are not always available or sufficient for complex physical systems. Physics-informed machine learning bridges this gap by embedding physical laws and domain knowledge directly into machine learning models, thus enhancing their interpretability, generalizability, and predictive accuracy. The review outlines key methodologies, especially Physics-Informed Neural Networks, in short PINNs, and systematically summarizes their recent applications in tribological tasks, such as lubrication prediction, wear and damage modeling, and fault detection. We discuss how physics-informed machine learning is already enabling breakthroughs in predicting hydrodynamic lubrication conditions, wear, and surface fatigue under realistic operating conditions, and we provide guidance on challenges and future directions in this rapidly evolving area.

3. What do you think are the key elements for writing a successful review paper?

In my view, a successful review paper requires a clear structure, critical synthesis, and a forward-looking perspective. First, it should provide a concise yet comprehensive overview of the current state of the art, highlighting both achievements and limitations in the field. Second, it is important to critically analyze the literature—not just summarizing existing work, but identifying gaps, controversies, and emerging trends. Third, a good review offers clear illustrations, tables, or conceptual figures to make complex ideas accessible to a broad audience. Finally, it should inspire new research by outlining open questions and promising future directions, acting as both a reference and a catalyst for the community.

4. How does it feel to receive the Best Paper Award? What does this recognition mean to you?

Together with Stephan Tremmel, we are truly honored and grateful to receive this award. It is a significant recognition, not only of the relevance of the topic, but also of the collaborative effort that went into the paper. For me, this distinction highlights the importance of interdisciplinary approaches and encourages continued innovation at the interface of tribology, machine learning, and physical modeling.

5. In your opinion, which research topics do you think will be the most popular in the field of tribology in the coming years?

I believe that the integration of artificial intelligence, especially physics-informed and explainable AI, will be one of the most dynamic areas in tribology over the next years. However, the true potential of AI can only be fully realized if we establish pipelines for findable, accessible, interoperable, and reusable data, also known as FAIR. Creating open, high-quality datasets and standardizing data sharing will be critical for enabling reliable AI models and accelerating innovation in our field.

Alongside AI and data-driven approaches, I see strong momentum for research into sustainable materials and lubricants, both to reduce environmental impact and to enhance performance in demanding applications. Another major trend will be the growing importance of tribology in green energy technologies. Applications such as electromobility, wind energy, and hydrogen technologies present new tribological challenges and opportunities, from advanced coatings for battery systems to wear prevention in wind turbine bearings. Altogether, the future of tribology will be shaped by how effectively we combine advanced digital tools, sustainable solutions, and applications in the rapidly evolving energy sector.

6. What attracted you to submit your work to Lubricants? Could you share your experience of submitting to this journal?

Lubricants is regarded as one of the reputable journals in the field, particularly known for its open access policy and fast, transparent review process. For us, this made it a natural platform to share our work with both the academic and industrial tribology communities. Together with my co-author Stephan Tremmel, we initiated the first Special Issue on machine learning in tribology in Lubricants back in 2020 and also published our first review article on the topic there. Since then, this initiative has grown into a very successful series of Special Issues covering the broader topic of AI in lubricants and tribology.

7. What advice and insights would you share with young scholars, particularly when it comes to selecting research topics and maintaining persistence?

My advice to young scholars is to remain curious and to pursue topics that not only address practical needs but also have the potential to make a long-term scientific impact. It is essential to build a strong foundation in both the fundamentals and the emerging tools of your field. Finally, persistence is crucial—research can be challenging and full of setbacks, but breakthroughs often come after repeated effort and learning from failure. I also encourage young researchers to seek interdisciplinary collaborations and to actively participate in scientific communities, as these networks are invaluable for both support and inspiration.

8. What are your views and expectations regarding the open access model of publishing?

I am a strong advocate for open access publishing, as it allows research results to be freely shared and accessed by the global scientific community and beyond. However, I believe that true openness in science goes beyond just publishing articles—it also means making research data openly available whenever possible. Ideally, this data should be shared in line with the FAIR principles. Open and FAIR data sharing enables reproducibility, facilitates collaboration, and significantly accelerates scientific progress, especially in fields like tribology where high-quality datasets are often scarce and when AI comes more and more into play. I hope to see the community further embrace both open access publishing and open data practices to drive transparency, innovation, and impact.