ChatGPT Optimized

Best ChatGPT prompts for Materials Scientists

A specialized toolkit of advanced AI prompts designed specifically for Materials Scientists to streamline high-impact decision making.

Focus Areas

01Daily task 1: Analyze the crystal structure of a given compound using density functional theory (DFT) and identify the symmetry and space group.
02Daily task 2: Simulate the mechanical properties of a material using molecular dynamics and predict its Young's modulus and yield strength.
03Daily task 3: Optimize the thermoelectric properties of a material using first-principles calculations and identify potential dopants to improve its efficiency.

Advanced Prompt Library

5 Expert Prompts
1
Copy-Paste Ready

Design a DFT-based simulation framework to analyze the crystal structure of a given compound, identifying the key structural parameters, including lattice constants, bond lengths, and angles. The framework should utilize popular libraries such as ASE and Vasp, and provide a comprehensive analysis of the material's electronic density of states, band structure, and Fermi energy. Example compounds: diamond, silicon, or silicon carbide.

2
Copy-Paste Ready

Create a molecular dynamics simulation using LAMMPS to predict the Young's modulus and yield strength of a given metal-alloy composite. The simulation should consider the effects of temperature, strain rate, and grain size on the material's mechanical properties, and provide a sensitivity analysis of the predicted values to these variables. Example materials: Cu-Al-Ti alloy, or Al-Mg-Si alloy.

3
Copy-Paste Ready

Develop a thermoelectric properties optimization framework using the Boltzmann transport equation (BTE) and first-principles calculations to identify potential dopants for a given material. The framework should predict the material's thermoelectric efficiency, figure of merit (ZT), and power factor, and provide a ranking of the optimized dope configurations. Example materials: lead telluride, bismuth antimony telluride, or tin selenide.

4
Copy-Paste Ready

Design an experiment to validate the accuracy of a machine learning model for predicting the viscosity and rheological properties of a complex fluid. The experiment should involve collecting a dataset of rheological measurements, training the model using machine learning techniques, and comparing the predicted values with the experimental data. Example liquids: paint, glue, or drilling fluids.

5
Copy-Paste Ready

Create a material database using a combination of machine learning algorithms and first-principles calculations to classify materials based on their thermomechanical properties, such as thermal conductivity, elastic modulus, and thermal shock resistance. The database should provide a comprehensive analysis of the material's properties, including its composition, crystal structure, and potential defects, and allow for the identification of new materials with desired properties.