MAterials Properties Prediction (MAPP)
built on experimental data
empowered by artificial intelligence
enhanced by ab initio calculations
| Properties | Dataset Size | R2 Score (training/testing) | RMSE (training/testing) | Status |
| Melting Temperature | 9,198 | 0.995/0.98 | 50/100 K | Deployed |
| Bulk Modulus | 4,236 | 0.997/0.97 | 4/14 GPa | Deployed |
| Volume | 49,213 | 0.985/0.975 | 0.942/1.177 Ang^3/atom | Deployed |
| Superconductor Critical Temperature | 12,448 | 0.92/0.90 | 8.5/9.0 K | Deployed |
| Crystal Structure | 7,882 | AUC: 0.998/0.961 | F1 Score: 0.86/0.66 | Deployed |
| Heat Capacity | 2,074 | 0.72/0.63 | 0.66/0.79 J mol-1K-1 | In Progress |
| Heat of Fusion | 1,233 | 0.94/0.89 | 0.4/0.6 kJ mol-1 | In Progress |
| Thermal Expansion | Planned | |||
| Calphad model excess parameter LA,B;0 | 790 | 0.96/0.85 | 18/35 kJ mol-1 | Deployment in Progress |
Not everyone is an expert on machine learning
We share these models with you, so…
MAterials Properties Prediction is just a few clicks away