📅 Day 1: Materials Informatics and AI-Based Nanomaterial Property Screening
- Introduction to AI and materials informatics in nanomaterials research
- How machine learning accelerates nanomaterial discovery and design
- Key nanomaterial descriptors: size, shape, surface area, porosity, charge, bandgap, conductivity, stability, and morphology
- Data sources for AI-driven nanomaterials research: literature, experimental datasets, simulations, Materials Project, NanoHUB, and open repositories
- Preparing nanomaterial data for AI: descriptors, labels, missing values, and application-specific targets
- Property prediction vs material screening vs inverse design
- Research opportunities in AI-assisted nanomaterial discovery
🛠️ Hands-on:
Tool: Materials Project / NanoHUB / Citrination Demo Resources / Google Sheets
Activity: Explore nanomaterial property data, identify candidate materials, and prepare a simple AI-ready screening table for energy, biosensing, or biomedical applications.
📅 Day 2: Machine Learning for Energy Storage and Biosensing Nanomaterials
- Nanomaterials for batteries, supercapacitors, hydrogen storage, and fuel cells
- AI for predicting conductivity, stability, charge-transfer behavior, capacity, and material performance
- Nanomaterials for biosensors, wearable sensing, electrochemical sensing, and biomarker detection
- Classification and regression workflows for nanomaterial datasets
- Feature selection and descriptor importance in AI-based material prediction
- Case studies: graphene, MXenes, quantum dots, metal oxides, and carbon nanotubes
- Translating research paper data into AI-based nanomaterial design workflows
🛠️ Hands-on:
Tool: Orange Data Mining
Activity: Build a no-code ML workflow to classify or predict nanomaterial performance using sample material or sensor data.
📅 Day 3: Biomedical Nanomaterials, Toxicity Prediction and Future AI-Nano Research
- Nanomaterials in drug delivery, imaging, diagnostics, and tissue engineering
- AI for nanoparticle toxicity, biocompatibility, and drug-release prediction
- Biomedical nanomaterial design challenges: safety, reproducibility, and clinical translation
- Generative AI and inverse design for nanomaterials
- Digital twins and simulation-assisted nanomaterial development
- Autonomous labs and self-driving materials discovery
- Future trends: AI-nano-bio convergence, explainable AI, and research automation
- How to frame an AI-nanomaterials research problem for thesis, proposal, or publication
🛠️ Hands-on:
Tool: Weka / Orange Data Mining
Activity: Create a simple no-code model to predict nanoparticle toxicity or biomedical suitability using sample descriptors.
