Using Neural Networks to Accelerate TALYS-2.0 Nuclear Reaction Simulations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911467116167168 |
|---|---|
| author | Lin, Wilson Apgar, Catherine E Bernstein, Lee A Lee, YunHsuan McIntosh, Alan B Medvedev, Dmitri G OBrien, Ellen M Vermeulen, Christiaan E Voyles, Andrew S Morrell, Jonathan T |
| author_facet | Lin, Wilson Apgar, Catherine E Bernstein, Lee A Lee, YunHsuan McIntosh, Alan B Medvedev, Dmitri G OBrien, Ellen M Vermeulen, Christiaan E Voyles, Andrew S Morrell, Jonathan T |
| contents | Recent efforts to improve the predictability of TALYS-2.0 calculated charged-particle residual product cross sections have focused on adjusting parameters related to the optical model potential and pre-equilibrium process. Although adjusted TALYS-2.0 outputs show marked improvements in agreement with experimental data over the default parameters, the procedure is generally time-consuming due to the need for sequential TALYS-2.0 calculations. Since the models and model parameters must be defined and constrained prior to adjustment, we show in this work that an artificial neural network can serve as a surrogate model to successfully predict TALYS-2.0 outputs within this domain of input parameters. No practical differences were observed in the trained model's performance between uniform random, Latin hypercube and Sobol sequence sampling for generating the training datasets. Once validated, trained neural network models were used to adjust TALYS-2.0 nuclear model parameters, where a multi-parameter fitting procedure was not only feasible but optimal for this process. The neural network approach is >1000x faster at generating residual product cross sections than using TALYS-2.0 directly, and a high-fidelity surrogate model could be implemented with about 1500 TALYS-2.0 files to achieve adjusted cross sections comparable to the previous publication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21239 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Using Neural Networks to Accelerate TALYS-2.0 Nuclear Reaction Simulations Lin, Wilson Apgar, Catherine E Bernstein, Lee A Lee, YunHsuan McIntosh, Alan B Medvedev, Dmitri G OBrien, Ellen M Vermeulen, Christiaan E Voyles, Andrew S Morrell, Jonathan T Computational Physics Nuclear Experiment Recent efforts to improve the predictability of TALYS-2.0 calculated charged-particle residual product cross sections have focused on adjusting parameters related to the optical model potential and pre-equilibrium process. Although adjusted TALYS-2.0 outputs show marked improvements in agreement with experimental data over the default parameters, the procedure is generally time-consuming due to the need for sequential TALYS-2.0 calculations. Since the models and model parameters must be defined and constrained prior to adjustment, we show in this work that an artificial neural network can serve as a surrogate model to successfully predict TALYS-2.0 outputs within this domain of input parameters. No practical differences were observed in the trained model's performance between uniform random, Latin hypercube and Sobol sequence sampling for generating the training datasets. Once validated, trained neural network models were used to adjust TALYS-2.0 nuclear model parameters, where a multi-parameter fitting procedure was not only feasible but optimal for this process. The neural network approach is >1000x faster at generating residual product cross sections than using TALYS-2.0 directly, and a high-fidelity surrogate model could be implemented with about 1500 TALYS-2.0 files to achieve adjusted cross sections comparable to the previous publication. |
| title | Using Neural Networks to Accelerate TALYS-2.0 Nuclear Reaction Simulations |
| topic | Computational Physics Nuclear Experiment |
| url | https://arxiv.org/abs/2602.21239 |