The integration of artificial intelligence (AI) with materials science and engineering has become one of the most dynamic and transformative frontiers in contemporary research. By leveraging AI techniques such as machine learning, deep learning, and data-driven modeling, scientists can now accelerate material discovery, optimize material properties, and predict performance with unprecedented efficiency. Recognizing its immense potential, MDPI has launched the AI-Powered Material Science and Engineering event. We were sincerely honored to interview Dr. Pedro Morouço, an Editorial Board Member of the Journal of Functional Biomaterials (JFB, ISSN: 2079-4983).

Name: Dr. Pedro Morouço Affiliation: ESECS, Polytechnic University of Leiria, Leiria, Portugal Interests: exercise and health; artificial intelligence; machine learning; technology

The following is a short interview with Dr. Pedro Morouço:

1. Could you introduce yourself and share a brief overview of your research field?
I am a researcher and academic working at the intersection of human movement science, biomechanics, and regenerative medicine, currently serving in public-health leadership and innovation roles while maintaining active teaching and editorial duties. My scientific focus is twofold: (i) understanding how humans generate and transmit forces in real-world contexts (from sport performance to everyday function) using wearable sensing and advanced analytics; and (ii) translating those insights into smarter interventions (digital and material) such as 3D/4D-printed, functionally graded biomaterials that support performance, recovery, and healthy ageing. My group’s work combines experimental biomechanics, signal processing, and AI/ML with tissue engineering concepts, aiming for solutions that are rigorous in the lab and useful in the field.

2. What was the biggest challenge you faced in your research career?
The hardest problem has been bridging elegant laboratory findings with messy, real-world impact. Field data are noisy, heterogeneous, and often scarce in exactly the edge-cases that matter. Convincing different communities (clinicians, coaches, engineers, data scientists) to converge on common protocols, quality standards, and outcomes has also been non-trivial. I addressed this by (a) building genuinely interdisciplinary teams, (b) designing studies with deployment in mind (robust sensor pipelines, calibration and uncertainty reporting, and pragmatic endpoints), and (c) committing to transparent methods and data stewardship so results can be reproduced and extended by others.

3. In your view, what are the key advantages of integrating artificial intelligence into material science and engineering? How has artificial intelligence transformed your research methods or outcomes?
AI condenses decades of trial-and-error into tractable search. Three advantages stand out:

• Structure–property learning at scale: Models learn mappings from composition/microstructure/architecture to properties (mechanical, transport, degradation), reducing expensive experiments and accelerating down-selection;
• Inverse design and multi-objective optimization: Given target properties (e.g., stiffness, toughness, permeability, bioactivity), AI proposes candidate micro-architectures or print parameters that balance competing constraints;
• Automation of characterization: Computer vision and foundation models speed microscopy/µCT segmentation, defect detection, and feature extraction, making data flows faster and more consistent.

In my own work, AI has become the “glue” between biomechanics and biomaterials. Wearable-sensor and imaging data inform digital twins of tissues; surrogate models then explore scaffold designs that best support anticipated loads, healing profiles, or athlete-specific movement patterns. This has shortened iteration cycles (from weeks to days) when tuning lattice density, pore geometry, or printing paths to meet simultaneous targets like strength, compliance, and nutrient diffusion.

4. Looking ahead to the next decade, could you share your insights on the key development opportunities and potential breakthroughs in AI-powered material science and engineering?
I believe that the following opportunities and breakthroughs may emerge in the next decade:

• Self-driving labs for biomaterials: Closed-loop platforms that pair robotics with active learning will autonomously synthesize, test, and refine candidates, dramatically reducing discovery time;
• Physics-informed and multi-scale AI: Hybrid models will combine mechanistic simulation with ML, improving extrapolation and trust. Expect better linkages from molecular chemistry to microstructure, macroscale function, and in vivo performance;
• Four-dimensional, responsive, and “personalized” materials: Patient-specific digital twins will inform scaffolds that adapt to evolving mechanical and biochemical cues, enabling staged stiffness, controlled degradation, and guided tissue remodeling;
• Sustainability and safety by design: AI will help minimize critical raw materials, reduce waste, and flag toxicity early, aligning innovation with regulatory and ESG demands;
• Data standards and model governance: Common ontologies, benchmark datasets, and uncertainty reporting will move AI from “promising” to “qualifiable” in regulated pathways, opening doors for clinical-grade applications. 

5. As an Editorial Board Member of the Journal of Functional Biomaterials, could you share your experience with MDPI?
My experience with MDPI has been positive. The editorial workflows are efficient and transparent, which authors value; the open access model provides immediate visibility; and Special Issues, when well-curated, catalyze focused communities. I have seen steady improvements in screening, ethics checks, and data-availability expectations. Two areas I continue to champion are (i) broadening and refreshing the reviewer pool to sustain depth across fast-moving subfields and (ii) strengthening reproducibility standards (code/data deposition, reporting checklists, and clearer guidance on statistical rigor). Overall, the Journal of Functional Biomaterials has been a constructive venue for interdisciplinary biomaterials research and a journal that listens to its community.