Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.14488 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910577845075968 |
|---|---|
| author | Appleton, Robert J. Klinger, Daniel Lee, Brian H. Taylor, Michael Kim, Sohee Blankenship, Samuel Barnes, Brian C. Son, Steven F. Strachan, Alejandro |
| author_facet | Appleton, Robert J. Klinger, Daniel Lee, Brian H. Taylor, Michael Kim, Sohee Blankenship, Samuel Barnes, Brian C. Son, Steven F. Strachan, Alejandro |
| contents | Data science and artificial intelligence are playing an increasingly important role in the physical sciences. Unfortunately, in the field of energetic materials data scarcity limits the accuracy and even applicability of ML tools. To address data limitations, we compiled multi-modal data: both experimental and computational results for several properties. We find that multi-task neural networks can learn from multi-modal data and outperform single-task models trained for specific properties. As expected, the improvement is more significant for data-scarce properties. These models are trained using descriptors built from simple molecular information and can be readily applied for large-scale materials screening to explore multiple properties simultaneously. This approach is widely applicable to fields outside energetic materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14488 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Task Multi-Fidelity Learning of Properties for Energetic Materials Appleton, Robert J. Klinger, Daniel Lee, Brian H. Taylor, Michael Kim, Sohee Blankenship, Samuel Barnes, Brian C. Son, Steven F. Strachan, Alejandro Machine Learning Materials Science Data science and artificial intelligence are playing an increasingly important role in the physical sciences. Unfortunately, in the field of energetic materials data scarcity limits the accuracy and even applicability of ML tools. To address data limitations, we compiled multi-modal data: both experimental and computational results for several properties. We find that multi-task neural networks can learn from multi-modal data and outperform single-task models trained for specific properties. As expected, the improvement is more significant for data-scarce properties. These models are trained using descriptors built from simple molecular information and can be readily applied for large-scale materials screening to explore multiple properties simultaneously. This approach is widely applicable to fields outside energetic materials. |
| title | Multi-Task Multi-Fidelity Learning of Properties for Energetic Materials |
| topic | Machine Learning Materials Science |
| url | https://arxiv.org/abs/2408.14488 |