Saved in:
Bibliographic Details
Main Author: Zanoni, Maria Grazia
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.19551315
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>This software implements a feed-forward Deep Neural Network (DNN) for estimating groundwater contaminant transport parameters from breakthrough curve descriptors. The model predicts key quantities such as peak concentration (<em>Cpeak</em>), time to peak (<em>Tpeak</em>), and the second temporal moment (<em>S2tau</em>).</p> <p>The network is trained using synthetic data and evaluated through 5-fold cross-validation based on the Nash–Sutcliffe efficiency. The repository includes the workflow required to reproduce the DNN inference results presented in the associated study: Zanoni, M. G., de Barros, F. P.J., Bonazzi, A., and Bellin, A.,  <em>Enhancing Groundwater Contaminant Transport Forecasts Through Synergy of Machine Learning and Physics-Based Models</em>, submitted to Water Resources Research, 2026</p>