SciPost Submission Page
Particle Identification with MLPs and PINNs Using HADES Data
by Marvin Kohls
This is not the latest submitted version.
Submission summary
| Authors (as registered SciPost users): | Marvin Kohls |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2509.17685v1 (pdf) |
| Date submitted: | Sept. 23, 2025, 8:19 a.m. |
| Submitted by: | Marvin Kohls |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Computational |
Disclosure of Generative AI use
The author(s) disclose that the following generative AI tools have been used in the preparation of this submission:
Spelling and grammar corrections
Abstract
In experimental nuclear and particle physics, the extraction of high-purity samples of rare events critically depends on the efficiency and accuracy of particle identification (PID). In this work, we present a PID method applied to HADES data at the level of fully reconstructed particle track candidates. The results demonstrate a significant improvement in PID performance compared to conventional techniques, highlighting the potential of physics-informed neural networks as a powerful tool for future data analyses.
Current status:
Has been resubmitted
Reports on this Submission
Strengths
The paper is well written and easy to follows. It introduce an application of Domain-Adversarial Neural Network (DANNs) with an additional Physics-Informed loss for training on simulated data (and unlabelled real data) a neural network for Particle identification at HADES.
Report
The paper deserves publication.
Just as a minor comment, which can be easily justified by the page limit: the full form of the Bethe-Bloch physics-informed loss have not been explicitly stated. The Author may consider adding a few details about it, if it fits in the page limits.
Just as a minor comment, which can be easily justified by the page limit: the full form of the Bethe-Bloch physics-informed loss have not been explicitly stated. The Author may consider adding a few details about it, if it fits in the page limits.
Recommendation
Publish (meets expectations and criteria for this Journal)