🌐 EN | 🇯🇵 JP | Last sync: 2026-01-01

NIMO: Automated Materials Exploration with AI

Closed-loop optimization for accelerated materials discovery

📖 Total Reading Time: 90-120 minutes 📊 Difficulty: Beginner 💻 Code Examples: 25 📝 Exercises: 10

Series Overview

This series provides a comprehensive introduction to NIMO (formerly NIMS-OS), a Python library that orchestrates closed-loop automated materials exploration systems. NIMO combines robotic experiments with AI optimization algorithms to enable efficient materials discovery without human intervention.

Developed by the National Institute for Materials Science (NIMS) in Japan, NIMO represents a paradigm shift in how we approach materials research. Instead of manually selecting and executing experiments one by one, NIMO creates an intelligent loop where AI algorithms propose experiments, robots execute them, and results automatically inform the next iteration.

graph LR A[🤖 AI Algorithm] -->|Proposes| B[📋 Candidates] B -->|Prepares| C[🔬 Robot System] C -->|Executes| D[📊 Experiment Results] D -->|Analyzes| A style A fill:#667eea,color:#fff style B fill:#f8f9fa style C fill:#11998e,color:#fff style D fill:#f093fb,color:#fff

Why Learn NIMO?

The Challenge: Traditional materials discovery is slow and expensive. Researchers must manually decide which experiments to run, wait for results, and then plan the next steps. This process can take years for a single material optimization.

The Solution: NIMO automates this entire workflow. With 11 built-in AI optimization algorithms (including Bayesian Optimization), 3 robot system interfaces, and powerful visualization tools, NIMO can reduce the number of required experiments by up to 90% while discovering optimal materials faster.

Content of All 5 Chapters

Chapter 1: What is NIMO? - A New Era of Experiment Automation
📖 15-20 minutes 💻 4 examples 📝 2 exercises 📊 Beginner
Understand the challenges of traditional materials exploration and learn how closed-loop automation addresses them. Get an overview of NIMO's features and install the package.
Chapter 2: NIMO Architecture
📖 20-25 minutes 💻 5 examples 📝 2 exercises 📊 Beginner
Explore NIMO's modular architecture including AI tools, robot interfaces, and visualization components. Learn about the CSV-based data flow and core workflow functions.
Chapter 3: AI Optimization Algorithms
📖 25-30 minutes 💻 6 examples 📝 2 exercises 📊 Beginner-Intermediate
Deep dive into NIMO's 11 optimization algorithms. Focus on Bayesian Optimization (PHYSBO), and learn when to use BLOX, PDC, SLESA, and other methods.
Chapter 4: Hands-on Tutorial
📖 25-30 minutes 💻 8 examples 📝 2 exercises 📊 Intermediate
Complete a full materials exploration workflow using sample data. Execute selection(), preparation_input(), and analysis_output() functions, and visualize results.
Chapter 5: Advanced Topics and Next Steps
📖 15-20 minutes 💻 4 examples 📝 2 exercises 📊 Intermediate
Learn about custom robot integration, multi-objective optimization, and connecting NIMO to real experimental systems. Explore resources for continued learning.

Target Audience

Prerequisite Knowledge

Required:

Recommended:

Key Tools

Learning Path

For Complete Beginners:
Chapter 1 → Chapter 2 → Chapter 3 → Chapter 4 → Chapter 5
Time required: 90-120 minutes

For Those Familiar with Bayesian Optimization:
Chapter 1 (skim) → Chapter 2 → Chapter 4 → Chapter 5
Time required: 60-80 minutes

Quick Practical Start:
Chapter 1 → Chapter 4
Time required: 40-50 minutes

Next Steps

After completing this series, we recommend:

Let's Get Started!

Ready to revolutionize your materials research? Start with Chapter 1 and learn how NIMO can transform your experimental workflow!

Read Chapter 1 →

Disclaimer