About this resource
<p>Proton Accelerator Neutron Shielding Dataset and ML Analysis This repository contains datasets and Python codes used for curve fitting and machine learning (ML) analysis in our study on secondary neutron dose attenuation in various shielding environments for high-energy proton accelerators.</p> <p>The datasets were generated from high-statistics FLUKA Monte Carlo simulations performed by Demet Sariyer. The machine learning models, statistical analyses, and Python implementations were developed by Ali Osman Gökcan.</p> <p><strong>Machine learning models:</strong></p> <p>Linear Regression (LR) Decision Tree Regressor (DTR) Random Forest Regressor (RFR) Evaluation metrics: R², RMSE, MAE, and 5-fold cross-validation</p> <p>Programming language: Python 3.x</p> <p>-----------------------</p> <p>Attribution & Citation If you use this dataset or code, please cite the related study as follows:</p> <p class="gs_rt"><a href="https://www.sciencedirect.com/science/article/pii/S0306454926001325?casa_token=oGCOLKY_GBEAAAAA:vAGQ_Hcf4_VL9fld3RJNBVzkwjQsD3EApSXrZlZqLFTe0O4CH_aeQ5Q0-WvzSroh3Aimf6HYMXc"><strong>CITE: High</strong>-<strong>energy neutron shielding </strong>analysis using curve fitting and <strong>machine </strong>learning: a Monte Carlo-based study in concrete and Ferro-Boron configurations</a></p> <p class="gs_rt">Gökcan, A. O., & Sarıyer, D. (2026). High-energy neutron shielding analysis using curve fitting and machine learning: a Monte Carlo-based study in concrete and Ferro-Boron configurations. <em>Annals of Nuclear Energy</em>, <em>232</em>, 112244.</p> <p class="gs_rt">-----------------------</p> <p>We kindly request that you give appropriate credit when using this dataset or code in any form of research or publication.</p>
Files and access
Resources are read online through DARE. Direct file links are not published; access is checked against DSpace when a document is opened. Authorised librarian workflows are unaffected.
This record contains bibliographic metadata, but no files are currently attached.
