Stefan Broda
YOU?
Author Swipe
View article: GEMS-GER: a machine learning benchmark dataset of long-term groundwater levels in Germany with meteorological forcings and site-specific environmental features
GEMS-GER: a machine learning benchmark dataset of long-term groundwater levels in Germany with meteorological forcings and site-specific environmental features Open
We present GEMS-GER (Groundwater Levels, Environment, Meteorology, Site Properties), the first benchmark dataset specifically designed for machine learning applications in long-term groundwater level modeling in Germany. The dataset compri…
View article: Validation Strategies for Deep Learning-Based Groundwater Level Time Series Prediction Using Exogenous Meteorological Input Features
Validation Strategies for Deep Learning-Based Groundwater Level Time Series Prediction Using Exogenous Meteorological Input Features Open
Due to the growing reliance on machine learning (ML) approaches for predicting groundwater levels (GWL), it is important to examine the methods used for performance estimation. A suitable performance estimation method provides the most acc…
View article: GEMS-GER: A Machine Learning Benchmark Dataset of Long-Term Groundwater Levels in Germany with Meteorological Forcings and Site-Specific Environmental Features
GEMS-GER: A Machine Learning Benchmark Dataset of Long-Term Groundwater Levels in Germany with Meteorological Forcings and Site-Specific Environmental Features Open
We present GEMS-GER (Groundwater Levels, Environment, Meteorology, Site Properties), the first benchmark dataset specifically designed for machine learning applications in long-term groundwater level modeling in Germany. The dataset compri…
View article: Towards a global spatial machine learning model for seasonal groundwater level predictions in Germany
Towards a global spatial machine learning model for seasonal groundwater level predictions in Germany Open
Reliable predictions of groundwater levels are crucial for sustainable groundwater resource management, which needs to balance diverse water needs and to address potential ecological consequences of groundwater depletion. Machine learning …
View article: Deep Learning Models for Seasonal Groundwater Level Prediction
Deep Learning Models for Seasonal Groundwater Level Prediction Open
The development of purely data-driven approaches for groundwater level prediction is crucial for sustainable groundwater management, offering the ability to predict groundwater levels across numerous monitoring wells and large geographical…
View article: Predicting Decadal Groundwater Levels in Brandenburg: Deep Learning Approaches for Sustainable Management
Predicting Decadal Groundwater Levels in Brandenburg: Deep Learning Approaches for Sustainable Management Open
The federal state of Brandenburg is characterized by over 3,000 lakes and hundreds of kilometres of rivers and thus is one of Germany's most water-rich regions, but also ranks among the country's driest states in terms of precipitation. Cl…
View article: Towards a Global Spatial Machine Learning Model for Seasonal Groundwater Level Predictions in Germany
Towards a Global Spatial Machine Learning Model for Seasonal Groundwater Level Predictions in Germany Open
Reliable predictions of groundwater levels are crucial for a sustainable groundwater resource management, which needs to balance diverse water needs and to address potential ecological consequences of groundwater depletion. Machine Learnin…
View article: Assessing groundwater level modelling using a 1-D convolutional neural network (CNN): linking model performances to geospatial and time series features
Assessing groundwater level modelling using a 1-D convolutional neural network (CNN): linking model performances to geospatial and time series features Open
Groundwater level (GWL) forecasting with machine learning has been widely studied due to its generally accurate results and low input data requirements. Furthermore, machine learning models for this purpose can be set up and trained quickl…
View article: Carbonate rocks and karst water resources in the Mediterranean region
Carbonate rocks and karst water resources in the Mediterranean region Open
Carbonate rocks in the Mediterranean region form karst landscapes with a variety of morphological and hydrological features, and are of particular interest from a water management perspective as they represent major karst aquifers. The Med…
View article: Advancing water resource management: Insights and implications from global machine learning models in groundwater prediction
Advancing water resource management: Insights and implications from global machine learning models in groundwater prediction Open
Accurate and reliable predictions of groundwater levels are essential for sustainable water resource management. Faced with the impacts of climate change and the increasing stress on groundwater resources, there is a growing necessity to b…
View article: The GRUVO web application: Bringing groundwater level predictions across Germany to the public
The GRUVO web application: Bringing groundwater level predictions across Germany to the public Open
The provision of current and predicted groundwater levels across Germany has become increasingly important, particularly due to the increasing likelihood of consecutive dry years. To address this issue, we present the interactive web appli…
View article: On the challenges of global entity-aware deep learning models for groundwater level prediction
On the challenges of global entity-aware deep learning models for groundwater level prediction Open
The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. Currently, the dominant model class is the so-call…
View article: Analysing agricultural plant protection product concentrations in groundwater in Germany: Nationwide database with site and compound insights
Analysing agricultural plant protection product concentrations in groundwater in Germany: Nationwide database with site and compound insights Open
Pesticides from agricultural practices are among the most pressing reasons why groundwater sources do not reach the good chemical status standards as required by the European Water Framework directive. Complementary to previous federal pes…
View article: Comment on hess-2023-192
Comment on hess-2023-192 Open
Abstract. The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. By now, the dominant model class is so c…
View article: Performance assessment of geospatial and time series features on groundwater level forecasting with deep learning
Performance assessment of geospatial and time series features on groundwater level forecasting with deep learning Open
Groundwater level (GWL) forecasting with machine learning has been widely studied due to its generally accurate results and little input data requirements. Furthermore, machine learning models for this purpose are set up and trained in a s…
View article: On the challenges of global entity-aware deep learning models for groundwater level prediction
On the challenges of global entity-aware deep learning models for groundwater level prediction Open
The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. By now, the dominant model class is so called sing…
View article: Supplementary material to "On the challenges of global entity-aware deep learning models for groundwater level prediction"
Supplementary material to "On the challenges of global entity-aware deep learning models for groundwater level prediction" Open
Predictions of groundwater levels in the test period (2012)(2013)(2014)(2015) for all 108 considered wells, for all model variants, including NSE scores.
View article: AwesomeGeodataTable - Towards a community-maintained searchable table for data sets easily usable as predictors for spatial machine learning
AwesomeGeodataTable - Towards a community-maintained searchable table for data sets easily usable as predictors for spatial machine learning Open
In the field of spatial machine learning, access to high-quality data sets is a crucial factor in the success of any analysis or modeling project, especially in subsurface hydrology. However, finding and utilizing such data sets can be a c…
View article: Performance assessment of groundwater level forecasting with deep learning: a case study of Lower Saxony, Germany.
Performance assessment of groundwater level forecasting with deep learning: a case study of Lower Saxony, Germany. Open
Groundwater level forecasting with machine learning has been widely studied due to its generally accurate results and little input data requirements. Furthermore, machine learning models for this purpose are set up and trained in a short t…
View article: First steps towards a data-driven groundwater vulnerability index for pesticides in Germany using probabilistic neural networks
First steps towards a data-driven groundwater vulnerability index for pesticides in Germany using probabilistic neural networks Open
The world largely relies on groundwater extraction for drinking water supply, which is also the case in Germany. In the EU, the Water Framework directive regulates the standards for a chemically good state of water bodies. Thresholds are o…
View article: Advanced deep learning architectures for accurate detection of subsurface tile drainage pipes from remote sensing images
Advanced deep learning architectures for accurate detection of subsurface tile drainage pipes from remote sensing images Open
Subsurface tile drainage pipes provide agronomic, economic and environmental benefits. By lowering the water table of wet soils, they improve the aeration of plant roots and ultimately increase the productivity of farmland. They do however…
View article: Groundwater resources in the ECOWAS region -Expected aquifer productivity map
Groundwater resources in the ECOWAS region -Expected aquifer productivity map Open
International audience
View article: Multiorder Hydrologic Position for Europe (EU-MOHP) as a Set of Environmental Predictor Variables for Hydrologic Modelling and Groundwater Mapping with Focus on the Application of Machine Learning
Multiorder Hydrologic Position for Europe (EU-MOHP) as a Set of Environmental Predictor Variables for Hydrologic Modelling and Groundwater Mapping with Focus on the Application of Machine Learning Open
<p>The application of machine learning in geosciences began several decades ago and is, especially in the advent of increasing and affordable computational power, continuously gaining popularity. However, in some specific areas such …
View article: Feature-based Groundwater Hydrograph Clustering Using Unsupervised Self-Organizing Map-Ensembles
Feature-based Groundwater Hydrograph Clustering Using Unsupervised Self-Organizing Map-Ensembles Open
Hydrograph clustering helps to identify dynamic patterns within aquifers systems, an important foundation of characterizing groundwater systems and their influences, which is necessary to effectively manage groundwater resources. We develo…
View article: Deep learning shows declining groundwater levels in Germany until 2100 due to climate change
Deep learning shows declining groundwater levels in Germany until 2100 due to climate change Open
In this study we investigate how climate change will directly influence the groundwater resources in Germany during the 21st century. We apply a machine learning groundwater level prediction framework, based on convolutional neural network…