Eur. Phys. J. Spec. Top. (2025) 234: 3547-3562
https://doi.org/10.1140/epjs/s11734-025-01844-0

Editorial

Artificial intelligence and complex networks meet natural sciences

¹ Baltic Center for Neurotechnology and Artificial Intelligence, Immanuel Kant Baltic Federal University, 14 Alexander Nevsky Str., 236016, Kaliningrad, Russia
² Physics and Applied Mathematics Unit, Indian Statistical Institute, 203 B. T. Road, 700108, Kolkata, India
³ Center for Biomedical Technology, Universidad Politécnica de Madrid, Campus Montegancedo, Pozuelo de Alarcón, 28223, Madrid, Spain
⁴ Physics Institute, Saratov State University, 112 Astrakhanskaya Str., 410012, Saratov, Russia
⁵ Strategic Research and Innovation Program for the Development of MU-PLOVDIV-(SRIPD-MUP), European Union-NextGenerationEU, Medical University of Plovdiv, 15A, Vassil Aprilov Blvd., 4002, Plovdiv, Bulgaria
⁶ University College London, Gower Str., WC1E 6BT, London, UK
⁷ Nonlinear Dynamics, Chaos and Complex Systems Group, Departamento de Física, Universidad Rey Juan Carlos, Tulipán s/n, Móstoles, 28933, Madrid, Spain

^a This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

This special issue delves into the transformative synergy between artificial intelligence (AI) and complex network science, showcasing cutting-edge research that spans theoretical foundations and practical applications across diverse domains of natural sciences. The collection, which included 9 reviews and 86 regular articles highlights how AI and network-based approaches are revolutionizing fields such as neuroscience, biomedicine, climate science, and nonlinear dynamics. Key themes include advances in machine learning methodologies, from federated learning to spiking neural networks, and their applications in medical diagnostics, biophysical modeling, and robotics. The issue also explores AI-driven insights into chaotic systems, synchronization phenomena, and neuromorphic computing, offering novel solutions to classical problems in nonlinear dynamics. In neuroscience, contributions demonstrate the power of graph-analytical methods combined with AI for understanding brain connectivity, diagnosing disorders, and developing brain–computer interfaces. Biomedical applications feature innovative AI tools for disease detection, personalized medicine, and medical imaging, while environmental research presents AI-enhanced climate modeling and sustainable resource management. The issue emphasizes the growing importance of interpretable AI, cross-disciplinary collaboration, and energy-efficient computing architectures. By bridging statistical physics, computer science, and life sciences, these works pave the way for future breakthroughs in understanding and harnessing complex systems.