Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 23 min ago
PreprintCC BY 4.0arXiv

Prediction of the maximum penetration of a circular intruder in a two-dimensional granular bed from its early trajectory using Machine Learning

  • Patricia Altshuler
Open at sourcePDFDOICite

Abstract

We test whether the maximum penetration depth of a circular intruder into a two-dimensional granular bed can be predicted from its early trajectory using machine learning, without giving the intruder density. From 100 DEM simulations with varying density, we extract kinematic features from the first 50 ms. Ridge and Random Forest predict the maximum penetration. A single feature (the intruder height at 50 ms) concentrates almost all predictive power, showing that density information is already encoded in the early impact response.

Related

  1. Intruder-driven mirror energy differences between 29Cl and 29Mg studied with antisymmetrized molecular dynamics
    Dae Ik Kim, Masaaki Kimura, Chang-Hwan Lee +1
    Physics Letters BPeer-reviewedCC BY 4.0Full textNuclear physicsCrossref
  2. Intruder structure, deformation, and E2 strengths in 14C from an ab initio perspective
    Mark A. Caprio
    arXivPreprintarXiv licenceFull textNuclear physicsarXiv
  3. Shape coexisting intruder states in even Sn isotopes and their influence on the B4/2<1 anomaly
    P. Buganu, R. Benjedi, R. Budaca
    arXivPreprintCC BY 4.0Full textNuclear physicsarXiv
  4. Intruder-driven mirror energy differences between 29Cl and 29Mg studied with antisymmetrized molecular dynamics
    Dae Ik Kim, Masaaki Kimura, Chang-Hwan Lee +1
    arXivPreprintarXiv licenceFull textNuclear physicsarXiv
  5. Intruder dynamics in granular media under localized surface loading
    E. M. Franklin, B. Darbois Texier, A. Seguin +2
    arXivPreprintCC BY 4.0Full textCondensed matterarXiv

Cite

BibTeXRIS
BibTeX
@misc{altshuler2026prediction,
  title = {{Prediction of the maximum penetration of a circular intruder in a two-dimensional granular bed from its early trajectory using Machine Learning}},
  author = {Patricia Altshuler},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.17968},
  eprint = {2609.17968},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17968},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Prediction of the maximum penetration of a circular intruder in a two-dimensional granular bed from its early trajectory using Machine Learning
AU  - Patricia Altshuler
PY  - 2026
DA  - 2026/09/16
PB  - arXiv
DO  - 10.48550/arxiv.2609.17968
UR  - https://arxiv.org/abs/2609.17968
AB  - We test whether the maximum penetration depth of a circular intruder into a two-dimensional granular bed can be predicted from its early trajectory using machine learning, without giving the intruder density. From 100 DEM simulations with varying density, we extract kinematic features from the first 50 ms. Ridge and Random Forest predict the maximum penetration. A single feature (the intruder height at 50 ms) concentrates almost all predictive power, showing that density information is already encoded in the early impact response.
ER  -