Surrogate models for groundwater flow simulations

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

11 to 20 of 29 Results

Trained Models on Real Permeability Fields, 4+1 Data Points 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...
Trained Models on Synthetic Permeability Fields, 3+1 Data Points 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...
Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 101 Data Points 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...
Models and Prepared Datasets for Iterative Modeling of Two Heat Pumps Jan 7, 2025 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...
Models and Prepared Datasets for Convolutional Long Short-Term Memory (ConvLSTM) Networks Dec 19, 2024 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...
Models and Prepared Datasets for 3D-CNN - First Stage Nov 26, 2024 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.
Datasets: First Stage 3D Simulation - Raw, 100 and 1000 Data Points Nov 26, 2024 Pelzer, Julia, 2024, "Datasets: First Stage 3D Simulation - Raw, 100 and 1000 Data Points", https://doi.org/10.18419/DARUS-4533, DaRUS, V1 These data sets serve as training data for modelling the temperature field emanating from a groundwater heat pump. They are simulated with Pflotran and saved in h5 format. They contain 100 and 1000 data points, each consisting of one simulation run until a near steady state is reached. Each datapoint measures 320 m x 1280 m x 320 m with 64 x 256 x...
Models and Prepared Datasets for Modeling Heat Plumes of Heat Pumps with varying Flow Directions Nov 5, 2024 Miliczek, Pascal, 2024, "Models and Prepared Datasets for Modeling Heat Plumes of Heat Pumps with varying Flow Directions", https://doi.org/10.18419/DARUS-4530, DaRUS, V1 Prepared datasets and models for modeling orientational variation in heat plume prediction in groundwater. Models were trained with 1HP NN equivariance. File name explanation: 4d The (used) dataset encompasses only cardinal flow directions. rd The (used) dataset encompasses random flow directions in the 2D plane. 1000dp The (used) dataset consists...
Raw Data for Modeling Heat Plumes of Heat Pumps with varying Flow Directions Nov 5, 2024 Pelzer, Julia, 2024, "Raw Data for Modeling Heat Plumes of Heat Pumps with varying Flow Directions", https://doi.org/10.18419/DARUS-4531, DaRUS, V1 Raw datasets for modeling orientational variation in heat plume prediction in groundwater. Used with 1HP NN equivariance. File name explanation: 4d The dataset encompasses only cardinal flow directions. rd The dataset encompasses random flow directions in the 2D plane. 1000dp The dataset consists of 1000 data points.
Models and Prepared Datasets for LG-CNN Sep 17, 2024 Pelzer, Julia, 2024, "Models and Prepared Datasets for LG-CNN", https://doi.org/10.18419/DARUS-4467, DaRUS, V2 Models trained with Heat Plume Prediction and datasets prepared with Heat Plume Prediction into reasonable format, reduced set of in/outputs, 2D, normalization used to train these models. Last relevant git commit: cae87d68faf96b2bd8dab935. Based on raw data from doi:darus-4156.

Trained Models on Real Permeability Fields, 4+1 Data Points

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...

Trained Models on Synthetic Permeability Fields, 3+1 Data Points

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...

Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 101 Data Points

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...

Models and Prepared Datasets for Iterative Modeling of Two Heat Pumps

Jan 7, 2025

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...

Models and Prepared Datasets for Convolutional Long Short-Term Memory (ConvLSTM) Networks

Dec 19, 2024

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...

Models and Prepared Datasets for 3D-CNN - First Stage

Nov 26, 2024

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.

Datasets: First Stage 3D Simulation - Raw, 100 and 1000 Data Points

Nov 26, 2024

Pelzer, Julia, 2024, "Datasets: First Stage 3D Simulation - Raw, 100 and 1000 Data Points", https://doi.org/10.18419/DARUS-4533, DaRUS, V1

These data sets serve as training data for modelling the temperature field emanating from a groundwater heat pump. They are simulated with Pflotran and saved in h5 format. They contain 100 and 1000 data points, each consisting of one simulation run until a near steady state is reached. Each datapoint measures 320 m x 1280 m x 320 m with 64 x 256 x...

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

Nov 5, 2024

Miliczek, Pascal, 2024, "Models and Prepared Datasets for Modeling Heat Plumes of Heat Pumps with varying Flow Directions", https://doi.org/10.18419/DARUS-4530, DaRUS, V1

Prepared datasets and models for modeling orientational variation in heat plume prediction in groundwater. Models were trained with 1HP NN equivariance. File name explanation: 4d The (used) dataset encompasses only cardinal flow directions. rd The (used) dataset encompasses random flow directions in the 2D plane. 1000dp The (used) dataset consists...

Raw Data for Modeling Heat Plumes of Heat Pumps with varying Flow Directions

Nov 5, 2024

Pelzer, Julia, 2024, "Raw Data for Modeling Heat Plumes of Heat Pumps with varying Flow Directions", https://doi.org/10.18419/DARUS-4531, DaRUS, V1

Raw datasets for modeling orientational variation in heat plume prediction in groundwater. Used with 1HP NN equivariance. File name explanation: 4d The dataset encompasses only cardinal flow directions. rd The dataset encompasses random flow directions in the 2D plane. 1000dp The dataset consists of 1000 data points.

Models and Prepared Datasets for LG-CNN

Sep 17, 2024

Pelzer, Julia, 2024, "Models and Prepared Datasets for LG-CNN", https://doi.org/10.18419/DARUS-4467, DaRUS, V2

Models trained with Heat Plume Prediction and datasets prepared with Heat Plume Prediction into reasonable format, reduced set of in/outputs, 2D, normalization used to train these models. Last relevant git commit: cae87d68faf96b2bd8dab935. Based on raw data from doi:darus-4156.

Add Data

Share Dataverse

Link Dataverse

Reset Modifications