Safe and sustainable by design with ML/AI: A transformative approach to advancing nanotechnology

• Georgia Melagraki

Beilstein J. Nanotechnol. 2026, 17, 176–185, doi:10.3762/bjnano.17.11

• containing them. The growing complexity of engineered nanomaterials calls for proactive strategies to mitigate potential risks while maintaining their functional benefits. The "Safe and Sustainable by Design" (SSbD) concept addresses these challenges by embedding safety measures and sustainability

• opportunities, and the path forward for integrating ML/AI-driven SSbD frameworks into regulatory and industrial practices. Keywords: digital twins; machine learning; materials informatics; safe and sustainable by design; Introduction Nanotechnology has fundamentally changed the landscape of materials science

• valuable, are resource intensive and inadequate to fully address the dynamic risks associated with ENMs and their myriad nanoscale forms (i.e., different sizes, geometries, coatings) [11]. The need for more proactive and efficient methodologies has led to the emergence of the Safe and Sustainable by Design

The round-robin approach applied to nanoinformatics: consensus prediction of nanomaterials zeta potential

• Dimitra-Danai Varsou,
• Arkaprava Banerjee,
• Joyita Roy,
• Kunal Roy,
• Giannis Savvas,
• Haralambos Sarimveis,
• Ewelina Wyrzykowska,
• Mateusz Balicki,
• Tomasz Puzyn,
• Georgia Melagraki,
• Iseult Lynch and
• Antreas Afantitis

Beilstein J. Nanotechnol. 2024, 15, 1536–1553, doi:10.3762/bjnano.15.121

• NMs’ properties when small datasets are available [4][5][6]. These in silico methodologies can be used in the early steps of the “safe-and-sustainable by design” framework and in the development of novel NMs to filter out unpromising candidates and prioritize NMs with desired properties. The rational