Models and Prepared Datasets for Modeling Heat Plumes of Heat Pumps with varying Flow Directions

Prepared datasets and models for modeling orientational variation in heat plume prediction in groundwater.<br>
Models were trained with <a href="https://github.com/pLm-k/1HP_NN_equivariance/tree/release_24">1HP NN equivariance</a>. <br><br>

<strong>File name explanation:</strong><br>
<dl>
<dt>4d</dt>
<dd>The (used) dataset encompasses only cardinal flow directions.</dd>

<dt>rd</dt>
<dd>The (used) dataset encompasses random flow directions in the 2D plane.</dd>

<dt>1000dp</dt>
<dd>The (used) dataset consists of 1000 data points.</dd>

<dt>100dp</dt>
<dd>The (used) dataset consists of 100 data points.</dd>

<dt>pksi</dt>
<dd>The input data fields: liquid pressure, permeability, position of the heat pump, and normalized distance to the heat pump.</dd>

<br>

<dt>BaselineCNN</dt>
<dd>The model is trained without any modification to architecture/training procedure.</dd>

<dt>DataAugmentation</dt>
<dd>The model is trained using data augmentation where rotated variations of the original data were added to the training data.</dd>

<dt>OrientedBoxes</dt>
<dd>For this model, during both training and inference, the input data is aligned to a chosen orientation.</dd>

<dt>ECNN</dt>
<dd>The model uses the Equivariant Convolutional Neural Network (ECNN) architecture.</dd>
</dl>