Saved in:
| Main Author: | |
|---|---|
| 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>