Models and Prepared Datasets for Iterative Modeling of Two Heat Pumps

Prepared datasets and models for iterative modeling of heat plumes in groundwater.
Models were trained with <a href="https://github.com/XiaoyuZha/Heat-Plume-Prediction_temp/tree/iterative_application">Iterative modeling</a>.
<br>
<br>
File explanation:
<br>
<br>
<b>1HP.zip</b>
<br>
This zip file contains all prepared datapoints with a single heat pump. The input data fields are pressure, permeability, position of the heat pump, normalized distance to the heat pump, and temperature. Based on <a href="https://doi.org/10.18419/darus-3650">doi:darus-3650</a>
<br>
<br>
<b>2HP.zip</b>
<br>
This zip file contains all prepared datapoints with two heat pumps. The input data fields are pressure, permeability, position of the heat pump, normalized distance to the heat pump, and temperature. Based on <a href="https://doi.org/10.18419/darus-3652">doi:darus-3652</a>
<br>
<br>
<b>unet_stand_f64_d5_k4_2500dp</b>
<br>
This folder contains the model for the standard architecture. F stands for the number of initial features, d for the depth of the network, and k for the kernel size. The amount of datapoints the model was trained on is indicated by dp.
<br>
<br>
<b>unet_para_f64_d5_k4_pcs_2500dp</b>
<br>
This folder contains the model for the parallel architecture. F stands for the number of initial features, d for the depth of the network, and k for the kernel size. The amount of datapoints the model was trained on is indicated by dp.
<br>
<br>
<b>unet_quad_f64_d5_k4_2500dp</b>
<br>
This folder contains the model for the quadratic architecture. F stands for the number of initial features, d for the depth of the network, and k for the kernel size. The amount of datapoints the model was trained on is indicated by dp.