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.

1 to 10 of 28 Results

Step 3: Scaled-up Domain and Interactions of Heat Plumes Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling Pelzer, Julia; Böttcher, Fabian, 2026, "Step 3: Scaled-up Domain and Interactions of Heat Plumes", https://doi.org/10.18419/DARUS-5808, DaRUS, V1 This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are realistic positions, and extraction rates are adapted to fit the av...
Step 2: Two Interacting Heat Plumes Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling Pelzer, Julia; Böttcher, Fabian, 2026, "Step 2: Two Interacting Heat Plumes", https://doi.org/10.18419/DARUS-5807, DaRUS, V1 This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are chosen based on realistic positions, and extraction rates are adapt...
Step 1: Single Heat Plume Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling Pelzer, Julia; Böttcher, Fabian, 2026, "Step 1: Single Heat Plume", https://doi.org/10.18419/DARUS-5806, DaRUS, V1 This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are chosen based on realistic positions, and extraction rates are adapt...
Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling(Universität Stuttgart) Apr 14, 2026 This dataverse contains the datasets for all steps of our stepwise benchmark based on input data from the region of Munich. The first step starts with a single heat pump in a heterogeneous 2D subsurface aquifer with seasonal operational pump parameters. The second step contains two potentially interacting heat plumes and fewer data points due to th...
Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics Apr 14, 2026 Baratto, Thomas, 2026, "Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics", https://doi.org/10.18419/DARUS-5815, DaRUS, V1, UNF:6:UMWqR0dTYJ/r2z0j/MZJgw== [fileUNF] Inference package for thermal plume prediction (v1.0.0). Contains pre-trained MLP and random network models, the ba-predict CLI, sample input files, and a Dockerfile. CPU-only - no GPU required. Extract with: tar xzf ba-thermal-plume-v1.0.0.tar.gz && cd ba-thermal-plume-v1.0.0 && pip install -e . Full source code (training scripts, data, tests) ava...
Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 3 + 1 Data Points 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...
Datasets: 100 Heat Pumps + Real Permeability Fields, Simulation - Raw, 4 + 1 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 + 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...
Trained Vanilla Models on Synthetic Permeability Fields, 101 Data Points 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.
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...

Step 3: Scaled-up Domain and Interactions of Heat Plumes

Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling

Pelzer, Julia; Böttcher, Fabian, 2026, "Step 3: Scaled-up Domain and Interactions of Heat Plumes", https://doi.org/10.18419/DARUS-5808, DaRUS, V1

This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are realistic positions, and extraction rates are adapted to fit the av...

Step 2: Two Interacting Heat Plumes

Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling

Pelzer, Julia; Böttcher, Fabian, 2026, "Step 2: Two Interacting Heat Plumes", https://doi.org/10.18419/DARUS-5807, DaRUS, V1

This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are chosen based on realistic positions, and extraction rates are adapt...

Step 1: Single Heat Plume

Apr 20, 2026 - Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling

Pelzer, Julia; Böttcher, Fabian, 2026, "Step 1: Single Heat Plume", https://doi.org/10.18419/DARUS-5806, DaRUS, V1

This dataset serves as training data for modeling the temperature field emanating from open-loop groundwater heat pumps. The dataset was simulated in 2D with Feflow using cut-outs from interpolated hydrogeological measurements of the Munich, Germany, region. Heat pump locations are chosen based on realistic positions, and extraction rates are adapt...

Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling(Universität Stuttgart)

Apr 14, 2026

This dataverse contains the datasets for all steps of our stepwise benchmark based on input data from the region of Munich. The first step starts with a single heat pump in a heterogeneous 2D subsurface aquifer with seasonal operational pump parameters. The second step contains two potentially interacting heat plumes and fewer data points due to th...

Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

Apr 14, 2026

Baratto, Thomas, 2026, "Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics", https://doi.org/10.18419/DARUS-5815, DaRUS, V1, UNF:6:UMWqR0dTYJ/r2z0j/MZJgw== [fileUNF]

Inference package for thermal plume prediction (v1.0.0). Contains pre-trained MLP and random network models, the ba-predict CLI, sample input files, and a Dockerfile. CPU-only - no GPU required. Extract with: tar xzf ba-thermal-plume-v1.0.0.tar.gz && cd ba-thermal-plume-v1.0.0 && pip install -e . Full source code (training scripts, data, tests) ava...

Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 3 + 1 Data Points

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...

Datasets: 100 Heat Pumps + Real Permeability Fields, Simulation - Raw, 4 + 1 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 + 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...

Trained Vanilla Models on Synthetic Permeability Fields, 101 Data Points

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.

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...

Add Data

Share Dataverse

Link Dataverse

Reset Modifications