1 to 10 of 53 Results
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia, 2024, "Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 3 + 1 Data Points", https://doi.org/10.18419/DARUS-4156, DaRUS, V2
This data set serves as training and testing data for modelling the temperature field emanating from open loop groundwater heat pumps (100, randomly placed). It is simulated with Pflotran and saved in h5 format. It contains 3 + 1 data points, each consisting of one simulation run until a quasi-steady state is reached. Each data point measures 12.8... |
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia, 2025, "Datasets: 100 Heat Pumps + Real Permeability Fields, Simulation - Raw, 4 + 1 Data Points", https://doi.org/10.18419/DARUS-5065, DaRUS, V1
This data set serves as training and testing data for modelling the temperature field emanating from open loop groundwater heat pumps (100, randomly placed). It is simulated with Pflotran and saved in h5 format. It contains 4 + 1 data points, each consisting of one simulation run until a quasi-steady state is reached. Each data point measures 12.8... |
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia; Verburg, Corné, 2025, "Trained Vanilla Models on Synthetic Permeability Fields, 101 Data Points", https://doi.org/10.18419/DARUS-5081, DaRUS, V1
Models are trained with [git: DDUNet] on 101 data points (dp). Both, vanilla UNet and DDU-Net, can be applied directly end-to-end. For inference follow the guidelines of Heat Plume Prediction to prepare raw data, then apply the models as described in [git: DDUNet]. Based on raw data from https://doi.org/10.18419/darus-5064. |
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia, 2025, "Trained Models on Real Permeability Fields, 4+1 Data Points", https://doi.org/10.18419/DARUS-5082, DaRUS, V1
Models are trained with Heat Plume Prediction on 4 data points (dp). Steps 1 and 3 of LGCNN (Local Global Convolutional Neural Network) are separate, step 2 is a numerical solver that does not require any trained model. For inference follow the guidelines of Heat Plume Prediction and applied all 3 steps/models sequentially to your input data. Based... |
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia, 2025, "Trained Models on Synthetic Permeability Fields, 3+1 Data Points", https://doi.org/10.18419/DARUS-5080, DaRUS, V1
Models are trained with Heat Plume Prediction. Steps 1 and 3 of LGCNN (Local Global Convolutional Neural Network) are separate, step 2 is a numerical solver that does not require any trained model. The vanilla UNet can be applied directly end-to-end, just does not give very good results. For inference follow the guidelines of Heat Plume Prediction... |
Jul 4, 2025 - Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Pelzer, Julia, 2025, "Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 101 Data Points", https://doi.org/10.18419/DARUS-5064, DaRUS, V1
This data set serves as training and testing data for modelling the temperature field emanating from open loop groundwater heat pumps (100, randomly placed). It is simulated with Pflotran and saved in h5 format. It contains 101 data points, each consisting of one simulation run until a quasi-steady state is reached. Each data point measures 12.8 km... |
Jun 26, 2025Surrogate models for groundwater flow simulations
Raw and prepared datasets and trained models for the publication "Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport", including randomized and real permeability fields, on different domain sizes (12.8kmx12.8km and double the size for scaling tests); DDUNet- and LGCNN architectures |
Jan 7, 2025 - Surrogate models for groundwater flow simulations
Zhang, Xiaoyu, 2024, "Models and Prepared Datasets for Iterative Modeling of Two Heat Pumps", https://doi.org/10.18419/DARUS-4518, DaRUS, V3
Prepared datasets and models for iterative modeling of heat plumes in groundwater. Models were trained with Iterative modeling. File explanation: 1HP.zip 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 tempe... |
Dec 19, 2024 - Surrogate models for groundwater flow simulations
Hofmann, Johanna, 2024, "Models and Prepared Datasets for Convolutional Long Short-Term Memory (ConvLSTM) Networks", https://doi.org/10.18419/DARUS-4514, DaRUS, V2
The dataset contains trained ConvLSTM models for heat plume extension and the prepared dataset for training and testing. In this repo the code for model training and dataset preparation is published. The last relevant git commit is 0a148e6131b98260. The prepared dataset for training is called ep_medium_1000dp_only_vary_dist inputs_ks. It consists o... |
Nov 26, 2024 - Surrogate models for groundwater flow simulations
Trick, Johanna, 2024, "Models and Prepared Datasets for 3D-CNN - First Stage", https://doi.org/10.18419/DARUS-4534, DaRUS, V1
Models trained with Heat Plume Prediction 3D and datasets prepared with Heat Plume Prediction 3D into reasonable format, normalization used to train these models. Based on raw data from doi:darus-4533. |