Stuttgart Center for Simulation Science (SC SimTech)

EXC 2075 Project Networks

SIGDIUS

Projects without PN Affiliation

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.

21 to 30 of 20,733 Results

inputs_unnormed.zip Apr 20, 2026 - Step 1: Single Heat Plume ZIP Archive - 3.3 GB - MD5: a00de41a0f220d6fca3232a990f4ab10 Data
labels_unnormed.zip Apr 20, 2026 - Step 1: Single Heat Plume ZIP Archive - 20.5 GB - MD5: 31f8e67c53ce725cbbba3afc3a86fd07 Data
Stepwise Benchmarking: Data-Scarce Groundwater Heat Pumps' Modeling(Universität Stuttgart) Apr 14, 2026Surrogate models for groundwater flow simulations 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...
ba-thermal-plume-v1.0.0-code.zip Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics ZIP Archive - 51.4 KB - MD5: 8453de4985a61ead4a8d8270f79eddf8 Inference source code (release branch): Python package with CLI (ba-predict), MLP and random-weight network implementations, dataset configurations, sample inputs, Dockerfile, and installation files. No model weights included.
Clean_Results_Isotherm.csv Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics Tabular Data - 7.7 MB - 13 Variables, 85531 Observations - UNF:6:6k+73yoVIjlpTOs2PFnb6w== Isotherm dataset used for training of the models.
Depression_cones.csv Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics Tabular Data - 436.7 KB - 5 Variables, 12835 Observations - UNF:6:/zEueaz1Rf9v1RaAambp4g== Depression cones dataset used for training of the models.
mlp-cone.zip Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics ZIP Archive - 562.0 KB - MD5: e63261aaac394e7adda836657c4d3938 Pre-trained MLP model for depression cone prediction. 2-hidden-layer architecture (244 neurons, LeakyReLU), Optuna-tuned over 200 trials. Contains PyTorch weights (best_model.pt), input/output scalers, training diagnostics plots, power consumption logs, and evaluation metrics (KGE=0.993, nRMSE=0.015, R²=0.991).
mlp-isotherm.zip Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics ZIP Archive - 4.0 MB - MD5: e9c366ae9359a2497ff88bfe4fb53479 Pre-trained MLP model for isotherm geometry prediction (Area, Iso_distance, Iso_width). 5-hidden-layer architecture (256 neurons, GELU), Optuna-tuned over 200 trials. Contains PyTorch weights (best_model.pt), input/output scalers, training diagnostics plots, power consumption logs, and evaluation metrics (KGE=0.999, nRMSE=0.0002, R²≈1.0).
random-cone-edRVFL-SC.zip Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics ZIP Archive - 221.3 MB - MD5: 3dee8ba0e945a09faead07808d5aa91f Pre-trained edRVFL-SC random-weight network for depression cone prediction. 1000 hidden neurons, 3 layers, GELU activation, 10-member ensemble with dense stacking. Pareto frontier winner (accuracy vs. training time) from 558 configurations. Contains serialized model (model.pkl), scalers, power logs, and evaluation metrics (KGE=0.976, nRMSE=0.022, R...
random-isotherm-dRVFL-KGE.zip Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics ZIP Archive - 1.3 MB - MD5: 8209e3a4a7d12ec955eac25459018e4e Pre-trained dRVFL random-weight network for isotherm geometry prediction (Area, Iso_distance, Iso_width). 1500 hidden neurons, 1 layer, ELU activation. Best KGE model on the Pareto frontier from 558 configurations. Contains serialized model (model.pkl), scalers, test predictions, and power consumption logs.

inputs_unnormed.zip

Apr 20, 2026 - Step 1: Single Heat Plume

ZIP Archive - 3.3 GB -

Data

labels_unnormed.zip

Apr 20, 2026 - Step 1: Single Heat Plume

ZIP Archive - 20.5 GB -

Data

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

Apr 14, 2026Surrogate models for groundwater flow simulations

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...

ba-thermal-plume-v1.0.0-code.zip

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

ZIP Archive - 51.4 KB -

Inference source code (release branch): Python package with CLI (ba-predict), MLP and random-weight network implementations, dataset configurations, sample inputs, Dockerfile, and installation files. No model weights included.

Clean_Results_Isotherm.csv

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

Tabular Data - 7.7 MB - 13 Variables, 85531 Observations -

Isotherm dataset used for training of the models.

Depression_cones.csv

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

Tabular Data - 436.7 KB - 5 Variables, 12835 Observations -

Depression cones dataset used for training of the models.

mlp-cone.zip

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

ZIP Archive - 562.0 KB -

Pre-trained MLP model for depression cone prediction. 2-hidden-layer architecture (244 neurons, LeakyReLU), Optuna-tuned over 200 trials. Contains PyTorch weights (best_model.pt), input/output scalers, training diagnostics plots, power consumption logs, and evaluation metrics (KGE=0.993, nRMSE=0.015, R²=0.991).

mlp-isotherm.zip

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

ZIP Archive - 4.0 MB -

Pre-trained MLP model for isotherm geometry prediction (Area, Iso_distance, Iso_width). 5-hidden-layer architecture (256 neurons, GELU), Optuna-tuned over 200 trials. Contains PyTorch weights (best_model.pt), input/output scalers, training diagnostics plots, power consumption logs, and evaluation metrics (KGE=0.999, nRMSE=0.0002, R²≈1.0).

random-cone-edRVFL-SC.zip

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

ZIP Archive - 221.3 MB -

Pre-trained edRVFL-SC random-weight network for depression cone prediction. 1000 hidden neurons, 3 layers, GELU activation, 10-member ensemble with dense stacking. Pareto frontier winner (accuracy vs. training time) from 558 configurations. Contains serialized model (model.pkl), scalers, power logs, and evaluation metrics (KGE=0.976, nRMSE=0.022, R...

random-isotherm-dRVFL-KGE.zip

Apr 14, 2026 - Trained Neural Networks on Simulated Data of Groundwater Heat Plume Characteristics

ZIP Archive - 1.3 MB -

Pre-trained dRVFL random-weight network for isotherm geometry prediction (Area, Iso_distance, Iso_width). 1500 hidden neurons, 1 layer, ELU activation. Best KGE model on the Pareto frontier from 558 configurations. Contains serialized model (model.pkl), scalers, test predictions, and power consumption logs.

Add Data

Share Dataverse

Link Dataverse

Reset Modifications