Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.19559859 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901640269791232 |
|---|---|
| author | Berretta, Francesco |
| author_facet | Berretta, Francesco |
| contents | <p>Email contact : multiversou@gmail.com </p> <p>We present a minimalist Mixture Density Network (MDN) for nuclear mass predictions using only 12 bulk‑inspired features, excluding explicit shell corrections, Wigner terms, and deformation parameters. Trained on AME2016, the model achieves 0.38 MeV RMS for nuclei with A ≥ 60—surpassing FRDM2012 on the same subset—while failing systematically for A < 60 (RMS ≈ 2 MeV). This sharp transition identifies A ≈ 60 as the boundary between statistically learnable mean‑field behavior and quantum‑correlation‑dominated regimes. Major shell closures emerge implicitly from the data, whereas light N = Z nuclei reveal missing Wigner energy and clustering effects. The work provides a transparent, calibrated baseline for hybrid physics–machine‑learning approaches and defines the domain of validity for physics‑minimal models.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19559859 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Statistical learning of nuclear masses: Implicit shell gaps and the breakdown of minimal models for light nuclei Berretta, Francesco Physics Physics Nuclear physics Physics Machine Learning <p>Email contact : multiversou@gmail.com </p> <p>We present a minimalist Mixture Density Network (MDN) for nuclear mass predictions using only 12 bulk‑inspired features, excluding explicit shell corrections, Wigner terms, and deformation parameters. Trained on AME2016, the model achieves 0.38 MeV RMS for nuclei with A ≥ 60—surpassing FRDM2012 on the same subset—while failing systematically for A < 60 (RMS ≈ 2 MeV). This sharp transition identifies A ≈ 60 as the boundary between statistically learnable mean‑field behavior and quantum‑correlation‑dominated regimes. Major shell closures emerge implicitly from the data, whereas light N = Z nuclei reveal missing Wigner energy and clustering effects. The work provides a transparent, calibrated baseline for hybrid physics–machine‑learning approaches and defines the domain of validity for physics‑minimal models.</p> |
| title | Statistical learning of nuclear masses: Implicit shell gaps and the breakdown of minimal models for light nuclei |
| topic | Physics Physics Nuclear physics Physics Machine Learning |
| url | https://doi.org/10.5281/zenodo.19559859 |