AI-Guided Quantum Material Simulator for Education. Case Example: The Neuromorphic Materials Calculator 2025
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918147405119488 |
|---|---|
| author | Barrionuevo, Santiago D. Aguirre, Myriam H. |
| author_facet | Barrionuevo, Santiago D. Aguirre, Myriam H. |
| contents | Teaching and learning in advanced materials science are often limited by two barriers: the technical complexity of quantum-mechanical simulations and the lack of individualized support in inquiry-based education. Here, we introduce the Neuromorphic Materials Calculator 2025 (NMC2025), a command-line platform that integrates a conversational artificial intelligence (AI) tutor with automated simulation workflows. NMC2025 combines large language model (LLM) guidance, real-time literature feedback, and domain-specific computation to create an adaptive learning environment. The system includes modular Python components for material discovery, simulation parameter optimization, and automated input generation for Quantum ESPRESSO (QE). Grounded in constructivist pedagogy, the tool enables students to carry out authentic research tasks such as identifying candidate materials for neuromorphic memristors or tuning density functional theory (DFT) inputs, while receiving context-aware explanations from the AI tutor. A case study illustrates how iterative, AI-guided refinement of hypotheses and calculations enhances both accuracy and understanding. NMC2025 fosters deeper conceptual insight, independent exploration, and smooth transfer of research methods into the classroom. This approach highlights the potential of AI-augmented education to reduce barriers to complex simulations and to expand access to computational modeling across science, technology, engineering, and mathematics (STEM). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI-Guided Quantum Material Simulator for Education. Case Example: The Neuromorphic Materials Calculator 2025 Barrionuevo, Santiago D. Aguirre, Myriam H. Physics Education Materials Science Teaching and learning in advanced materials science are often limited by two barriers: the technical complexity of quantum-mechanical simulations and the lack of individualized support in inquiry-based education. Here, we introduce the Neuromorphic Materials Calculator 2025 (NMC2025), a command-line platform that integrates a conversational artificial intelligence (AI) tutor with automated simulation workflows. NMC2025 combines large language model (LLM) guidance, real-time literature feedback, and domain-specific computation to create an adaptive learning environment. The system includes modular Python components for material discovery, simulation parameter optimization, and automated input generation for Quantum ESPRESSO (QE). Grounded in constructivist pedagogy, the tool enables students to carry out authentic research tasks such as identifying candidate materials for neuromorphic memristors or tuning density functional theory (DFT) inputs, while receiving context-aware explanations from the AI tutor. A case study illustrates how iterative, AI-guided refinement of hypotheses and calculations enhances both accuracy and understanding. NMC2025 fosters deeper conceptual insight, independent exploration, and smooth transfer of research methods into the classroom. This approach highlights the potential of AI-augmented education to reduce barriers to complex simulations and to expand access to computational modeling across science, technology, engineering, and mathematics (STEM). |
| title | AI-Guided Quantum Material Simulator for Education. Case Example: The Neuromorphic Materials Calculator 2025 |
| topic | Physics Education Materials Science |
| url | https://arxiv.org/abs/2509.20372 |