Biological and epidemiological phenomena are governed by intricate processes operating across diverse spatial and temporal levels, from molecular interactions within cells to large-scale population dynamics. While traditional mathematical frameworks, such as deterministic and stochastic models, have been instrumental in understanding these systems, they often face challenges in handling complex, noisy, and high-dimensional datasets. The rapid growth of Artificial Intelligence (AI) and Machine Learning (ML) has introduced new opportunities to overcome these limitations through data-centric analysis and predictive capabilities. Combining these modern techniques with established mechanistic models has led to the development of hybrid multiscale approaches that improve reliability and flexibility. This collection seeks to highlight recent advances in such integrative methodologies and their applications in biology, epidemiology, and related interdisciplinary domains.

This Research Topic aims to develop effective and interpretable approaches for analyzing complex biological and epidemiological systems that operate across multiple scales. Current models often struggle either with oversimplified assumptions or with incorporating large and diverse datasets, limiting their practical applicability in areas such as disease prediction, ecological management, and healthcare planning. To address these challenges, the focus will be on integrating mechanistic frameworks with modern AI and ML techniques. Emphasis will be given to multiscale modeling, data integration, and reliability of predictions. The goal is to encourage interdisciplinary research that leads to more accurate models and improved understanding of complex biological dynamics.

This Research Topic invites contributions focused on advanced mathematical and computational approaches for studying biological and epidemiological systems across multiple scales. Areas of interest include, but are not limited to:
- hybrid modeling frameworks combining mechanistic and data-driven methods;
- multiscale dynamics linking cellular and population processes;
- AI-assisted parameter estimation and model calibration;
- stochastic and deterministic modeling;
- network and agent-based approaches;
- applications to infectious diseases, ecological systems, and biomedical problems.

Studies addressing uncertainty analysis, model validation, and real-world data integration are particularly encouraged.

We invite submissions in the form of original research articles, comprehensive review papers, and brief reports presenting novel methodologies, theoretical developments, or applied case studies. Interdisciplinary contributions bridging mathematics, biology, and data science are especially welcome.

Are you interested in contributing a manuscript to this Research Topic?

AI-Driven Multiscale Modeling in Biological and Epidemiological Systems