References

Projects, publications and presentations

A selection of our projects as well as all publications, presentations, interviews and datasets of the baseflow team.

Selected projects 18

Water level forecasting system for the Austrian Danube

via donau – Österreichische Wasserstraßen-Gesellschaft mbH

Details

Following a call for tenders, viadonau commissioned us to develop and operate an AI-based water level forecasting system for the Austrian Danube, with a focus on low flow. We are carrying out the project together with UBIMET, which provides the meteorological forecasts and reanalyses.

The system combines our AI model baseflow:hydroAI with the conceptual hydrological model COSERO. baseflow:hydroFusion merges both forecasts with the observations at the upstream gauges. The result is hourly water level forecasts for the Kienstock and Wildungsmauer gauges with a horizon of at least six days, updated four times a day and with confidence intervals. They are provided via the baseflow:dashboard and a REST API.

The project started in November 2026. Development will be followed by an online test phase, a pilot phase running in parallel to the existing system and then operational use.

Short-term power forecasting at run-of-river power plants - part 1: development

VERBUND Energy4Business GmbH

Details

At the Austrian hydropower plant operator Verbund, a conceptual, spatially distributed hydrological model with a following hydrodynamic module is operationally used for the prediction of power produced by run-of-river power plants. Potential for improvement was identified especially in times of steeply increasing and decreasing flow rates.

The performance of machine learning methods in short-term power forecasting (up to 4 hours) was determined at the run-of-river power plants Braunau-Simbach (river Inn), Aschach (Danube) and Greifenstein (Danube). Measured runoff and power values from upstream run-of-river power plants and gauges were used as input for the machine learning models.

The achieved results are promising and the developed machine learning models will be incorporated into operational planning at Verbund after an evaluation phase. The documentation of the project was published in the open-access ÖWAV journal. Link to article

Short-term power forecasting at run-of-river power plants - part 2: operation

VERBUND Energy4Business GmbH

Details

In this project we applied the developed approach from the previous project (see reference above) on the whole Austrian Danube run-of-river power plant chain (10 power plants: Jochenstein, Aschach, Ottensheim-Wilhering, Abwinden-Asten, Wallsee-Mitterkirchen, Ybbs-Persenbeug, Melk, Altenwörth, Greifenstein, Freudenau | average total power approx. 1,500 MW) and on 7 Inn run-of-river power plants (Oberaudorf, Nussdorf, Braunau-Simbach, Ering-Frauenstein, Egglfing-Obernberg, Schärding-Neuhaus, Passau-Ingling | average total power approx. 350 MW).

In contrast to the previous project, not the individual but the total power of 10 respectively 7 run-of-river power plants is forecasted. This procedure led to a faster project accomplishment and also to advantages in initializing a forecast. Prior to the model training, a preparation of the provided input time series was conducted. The created application for periodically calculating the forecasts includes several checks. In case of missing or unrealistic input values the application switches automatically to a back-up model. In conclusion, both forecast models for the Danube and the Inn have shown high accuracy in an independent test period.

Operational flood warning system Zauchbach

Office of the Lower Austrian Provincial Government, Department of Hydraulic Engineering (WA3)

Details

In the basin of the Zauchbach (Lower Austria, 64 km²) a mobile flood protection system was installed. In case of a flood event, at least 2 hours warning time is required to build up the mobile protecting walls.

On behalf of the federal state of Lower Austria, we created an operational flood warning system, whereby meteorological forecast data and water levels measured in real time are continuously integrated. A special feature is the concept of the in-house developed rainfall-runoff model: Due to the extremely efficient programming approach, the spatially distributed model can be calibrated in real time. This enables continuous adaptation to current conditions in the basin without external intervention. The result is a higher forecast accuracy and less maintenance required.

Operational flood warning system Mühlbach

WSI Systems GmbH

Details

Together with WSI Systems GmbH, we have implemented an innovative flood warning system for the Mühlbach (Artstetten and Klein-Pöchlarn, Lower Austria, 9 km²). For this purpose, three water level gauges and five precipitation gauges with real-time data transfer were installed. Compared to the Zauchbach flood warning system (see previous reference), precipitation measurement data is now also used for the local adjustment of the spatially distributed precipitation forecasts in real time. This enables a further quality improvement of the flood warnings.

Operational flood warning system Sierning

WSI Systems GmbH

Details

The river Sierning in Lower Austria (approx. 90 km²) was heavily affected by the big flood event in 2024. Together with WSI Systems GmbH and in collaboration with local stakeholders, we set up a flood warning system based on five water level gauges and five rain gauges with real-time data transfer. Similar to the Mühlbach system (see previous reference), the measured rain data is used to correct the spatially distributed precipitation forecasts (+60h).

Hydro-AI

Österreichische Forschungsförderungsgesellschaft mbH (FFG)

Details

The aim of this practical research project is to develop a scalable and modular software environment for accurate and cost-efficient forecasting of runoff, power or flow temperature. The forecasting horizon depends on the used meteorological forecast product and is in the range of hours or days. Another focus is establishing a deep learning architecture that enables the integration of high-resolution input data (e.g. precipitation fields) into the model without prior aggregation.

Study "Impact of Minimum Flow Requirements on Electricity Production in Austria | RestStrom"

Department National and International Water Management of the Ministry for Agriculture and Forestry, Climate and Environmental Protection, Regions and Water Management as well as Oesterreichs Energie

Details

Together with BOKU University and the AIT (Austrian Institute of Technology), we investigated how the full implementation of the EU Water Framework Directive regarding residual flows would affect energy production from hydropower in Austria. First, we conducted a comprehensive data preparation for all hydropower plants > 5 MW as well as for a large sample of small hydropower plants. After that we used machine learning models to simulate hydrological characteristics and inflow time series for more than 1,000 ungauged catchments. The partially complex linking of power plant groups was thereby fully taken into account. In addition to the current scenario, we examined seven other residual flow scenarios – ranging from a gradual increase of the minimum flows to dynamic requirements. The results were evaluated separately by power plant type and season. For a detailed overview, please have a look at the study published by the ministry. Link to study

Study "Water availability in Austria's streams"

Department National and International Water Management of the Ministry for Agriculture and Forestry, Climate and Environmental Protection, Regions and Water Management

Details

In cooperation with our client, we analyzed how much water would theoretically be available in Austria’s watercourses at present and in the near future, taking into account aquatic ecological requirements. In detail, the statistical evaluations are based on discharge data from 560 measuring stations of the period 1991 to 2021. The range of theoretically available water amount is estimated by examining several residual flow scenarios. Our study and the data provided offer a solid basis for an initial assessment of Austria’s water availability and show in which regions or times sufficient water is available or water deficits are to be expected. Link to study

Drilling profile extraction from PDFs

GGU Zentrale Verwaltung GmbH

Details

As part of the digitization offensive in Germany, drilling profile and groundwater data in PDFs shall be digitized in a specific XML format. Until now, the digitization process has been carried out manually, which takes a significant amount of time when dealing with many PDFs. We developed an application based on text and image recognition to automatically extract relevant data from PDFs and store it in a specific format. Our application was integrated into our client’s software environment. Finally, the solution was approved by a geological office and a large construction company from Germany. Our client’s customers are now able to digitize the relevant data much more efficiently.

Analysis of a chain of retention basins

IBL Ziviltechniker GmbH

Details

In the catchment area of a river in Amstetten (Lower Austria), four flood retention basins were built. During the 2020 and 2021 flood events, the two retention basins located in the lower part of the river exhibited significantly different behaviour than those two in the middle part. The reasons could be determined by detailed hydrological modelling and systematic analysis of measured data.

Based on the findings of the first part, structural and control modifications were worked out to optimize all retention basins.

Dimensioning of retention basins

IBL Ziviltechniker GmbH

Details

The municipality of Ybbsitz in Lower Austria aims to be protected up to a 100-year flood event by a combination of flood retention basins (RB) and linear structures. The main tributaries in Ybbsitz are the river Schwarze Ois and the river Prollingbach. The RB Großmoos with a volume of around 400,000 m³ is built at the Prollingbach. We were contracted to determine the required retention volumes of the RB Jungwurzlehen at the Schwarze Ois and the RB Dürnbach at a tributary to the Schwarze Ois. The impact of the RB Großmoos and the other flood protection structures had to be taken into account. The obligatory rainfall-runoff-model was calibrated with observed flood events. Based on this model a required retention volume of 610,000 m³ for RB Jungwurzlehen and 260,000 m³ for RB Dürnbach was determined with a precipitation duration analysis. Thereby several precipitation distributions and design variants were considered.

For the RB Jungwurzlehen, the safety flood rate (SHQ) was also calculated by us together with the freeboard determination. This is necessary to ensure the safety of the RB in accordance with the guidelines of the Austrian Reservoir Commission. The results were presented to representatives of the corresponding ministry in preparation for the submission of the project at the Reservoir Commission.

Retention investigation

Municipality of Klosterneuburg

Details

The municipality of Klosterneuburg is planning a flood protection system for the river Kierlingbach, which will consist of several retention basins and linear structures. The design of parallel or serially connected retention basins is a complex issue.

Therefore, a hydrological model was set up to evaluate and optimize the effectiveness of individual retention basins – as well as their impact in connection. In addition, recommendations for hydraulic optimizations were prepared.

Meteorological forecasts for building automation

STIWA AMS GmbH

Details

As part of the Clean Energy Hackathon, we developed for STIWA a concept  for the continuous integration of meteorological forecast data into building automation. This makes it possible to optimize the building automation on several levels. For example, the heating / cooling of the building can be controlled more efficiently and a more accurate peak shifting of the machines would be possible.

Austria-wide prediction of runoff characteristics

University of Natural Resources and Life Sciences Vienna (BOKU), Institute for Hydrobiology and Aquatic Ecosystem Management

Details

The aquaZoom project, which was commissioned by the European Marine and Fisheries Fund and the Austrian Federal Ministry BMLRT, estimated the nationwide potential for aquaculture flow-through systems in Austria. Information about runoff characteristics, e.g. average minimum runoff, are not only an important basis for planning aquaculture flow-through systems, but also for various other applications. The calculation of runoff characteristics is simple if a runoff gauge with a correspondingly long observation time series is in the immediate vicinity of the area of interest. However, since the number of gauge stations is limited, baseflow AI was commissioned to predict six different runoff characteristics for approximately 8,000 Austrian surface water bodies, including an estimate of the prediction uncertainty.

Machine learning methods have often shown significant improvements compared to conventional methods in a wide variety of hydrological applications. Therefore, after initial tests of several models, we used the XGBoost (eXtreme Gradient Boosting) algorithm to predict the runoff characteristics. Uncertainties in the predictions were determined with Quantile Random Forests (QRF). In addition to the data from all publicly available runoff gauges from Austria and its hydrological upstream regions, we also used a large number of (catchment area) properties with approximately 90 predictors for training the models.

With a median deviation of around 20% between model predictions and observations in basins treated as ungauged, the applied models achieved a high performance. Even local artificial characteristics such as the increase in low water flows due to large reservoirs or the influence of cross-basin water transfers could be reproduced. Detailed information and results were published in the ÖWAV journal. Link to article. Our client has also agreed that the predicted runoff characteristics and the degree of uncertainty are publicly available free of charge. Link to dataset

“The cooperation with baseflow AI solutions was very successful and pleasant. The professional and solution-oriented processing by baseflow AI led to exactly the results that we needed.”
Dr. Florian Borgwardt (Senior Scientist)

Workshop about Machine Learning in Hydrology

Digital Engineering – Association for networking and supporting digitization in engineering

Details

The association “Digital Engineering” organizes an annual boot camp to educate young engineers in the field of Data Science and Earth Observation. We were invited to conduct a workshop about Machine Learning in Hydrology. This workshop included theoretical as well as practical elements, where the participants were encouraged to optimize the prediction of water temperature of an Austrian river with Machine Learning methods using a prepared JupyterLab.

“The founders of baseflow AI solutions conducted a workshop on Machine Learning in Hydrology at the Digital Engineering Bootcamp 2022. The complex topic was explained in an understandable way accompanied by numerous exercises. The high expectations of our participants were exceeded. We thank Moritz and Christoph for their great commitment and hope to welcome them again at our next bootcamp.”
Oliver Konold, BSc (Association President)

EFAS runoff forecasts

via donau – Österreichische Wasserstraßen-Gesellschaft mbH

Details

The pan-European flood warning system EFAS (European Flood Awareness System, spatial coverage 5,000 × 4,750 km, link) supports the EFAS partners with runoff forecasts for operational use. The runoff forecasts are initialized twice a day and have forecast ranges of +10 days (meteor. forcing ECMWF) respectively +7 days (DWD) with a six-hour increment. EFAS forecasts are provided in binary file format (NetCDF or GRIB).

viadonau investigates the possibility of using EFAS. Therefore, we were contracted to provide the following services: 1) Automated retrieval of EFAS raw data for the relevant spatial domain and the last 4 years via API. 2) Extracting and processing the runoff forecasts with 40 (ECMWF) respectively 28 (DWD) forecast levels per initialization date for two locations. This step was done by an algorithm including checks for data completeness. 3) Creating the output files with a format suitable for viadonau.

Workshop about Machine Learning in runoff forecasting

via donau – Österreichische Wasserstraßen-Gesellschaft mbH

Details

Machine Learning (ML) models can effectively represent complex relationships, structures and patterns in data due to their internal structural flexibility and consequently their ability to generalize and transfer learned patterns. This flexibility can lead to clear improvements in various hydrological tasks.

To strengthen the in-house understanding at viadonau, two workshops were conducted addressing the topics 1) theoretical background of ML, 2) possible applications of ML in runoff forecasting, and 3) current research findings.

Publications 32

  1. 2026

    BiasCast: learning and adjusting real time biases from meteorological forecasts to enhance runoff predictions.

    Oliver Konold, Moritz Feigl, Patrick Podest, Christoph Klingler, Karsten Schulz

    Hydrology and Earth System Sciences, 30(15), 5067-5096

  2. 2026

    Assessment of Sentinel-1 C-band SAR snow depth assimilation in operational hydrological modeling of high-alpine catchments.

    Thomas Pulka-Petzolt, Caroline Ehrendorfer, Hans Lievens, Franziska Koch, Karsten Schulz, Herbert Formayer, Francesco Avanzi, Manuela Girotto, Mathew Herrnegger

    Journal of Hydrology, 677, 135888

  3. 2026

    Undercatch corrected gridded precipitation data to improve hydrological modeling in high-alpine orography.

    Philipp Maier, Caroline Ehrendorfer, Sophie Lücking, Thomas Pulka-Petzolt, Fabian Lehner, Mathew Herrnegger, Herbert Formayer, Franziska Koch

    Hydrology and Earth System Sciences, 30(18), 5901-5924

  4. 2026

    Distilling hydrological and land-surface model parameters from physio-geographical properties using text-generating AI.

    Moritz Feigl, Mathew Herrnegger, Karsten Schulz

    Nature Water (only for personal use)

  5. 2025

    GGU-CONNECT: Automated PDF data extraction in the geotechnical digitization process

    Simon Buß, Nicole Keller, Christoph Klingler

    . SUBSTANZ, 16/2025, 18-21

  6. 2025

    The spatiotemporal distribution of water quality characteristics of the tropical, transboundary Sio Malaba Malakisi River Basin using multivariate statistical techniques.

    Hope Mwanake, Moritz Feigl, Bano Mehdi-Schulz, Nzula Kitaka, Karsten Schulz, Luke O Olang, Jakob Lederer, Mathew Herrnegger

    Environmental Monitoring and Assessment, 197, 865

  7. 2025

    Systematic comparison of Commercial seizure detection Software: Update equals Upgrade?

    Johannes Koren, Kady Colabrese, Manfred Hartmann, Moritz Feigl, Clemens Lang, Sebastian Hafner, Nicolas Nierenberg, Tilmann Kluge, Christoph Baumgartner

    Clinical Neurophysiology, 174, 178-188

  8. 2025

    Attitudes towards epilepsy in the Austrian general population: Predictors and national trends

    Clemens Lang, Ekaterina Pataraia, Edda Haberlandt, Michael Feichtinger, Silvia Bonelli, Gudrun Gröppel, Moritz Feigl, Eugen Trinka, Christoph Baumgartner

    . Epilepsy & Behavior, 165, 110291

  9. 2024

    Evaluating precipitation corrections to enhance high-alpine hydrological modeling.

    Thomas Pulka, Mathew Herrnegger, Caroline Ehrendorfer, Sophie Lücking, Francesco Avanzi, Herbert Formayer, Karsten Schulz, Franziska Koch

    Journal of Hydrology, 645, 132202

  10. 2024

    Improving the weir operating rules of Lake Mondsee, part I – Hydraulics.

    Max Preiml, Christoph Klingler, Hubert Holzmann, Petr Lichtneger, Christine Sindelar, Helmut Habersack

    Österreichische Wasser- und Abfallwirtschaft, 76(3), 182-192

  11. 2024

    Improving the weir operating rules of Lake Mondsee, part II – Hydrology.

    Christoph Klingler, Max Preiml, Helmut Habersack, Hubert Holzmann

    Österreichische Wasser- und Abfallwirtschaft, 76(3), 193-202

  12. 2023

    Widespread deoxygenation in warming rivers.

    Wei Zhi, Christoph Klingler, Jiangtao Liu, Li Li

    Nature Climate Change, 1758-6798 (only for personal use)

  13. 2023
  14. 2022

    Machine Learning in Hydrological Modeling

    Moritz Feigl

    . Dissertation, Institute for Hydrology and Water Management, University for Natural Resources and Life Sciences Vienna, 211p

  15. 2022

    Learning from mistakes – Assessing the performance and uncertainty in process-based models.

    Moritz Feigl, Benjamin Roesky, Mathew Herrnegger, Karsten Schulz, Masaki Hayashi

    Hydrological Processes, 36(2), e14515

  16. 2022

    Automatic Regionalization of Model Parameters for Hydrological Models.

    Moritz Feigl, Stephan Thober, Robert Schweppe, Mathew Herrnegger, Luis Samaniego, Karsten Schulz

    Water Resources Research, 58(12), e2022WR031966

  17. 2022

    Prediction of runoff characteristics in ungauged basins with machine learning.

    Christoph Klingler, Moritz Feigl, Florian Borgwardt, Carina Seliger, Stefan Schmutz, Mathew Herrnegger

    Österreichische Wasser- und Abfallwirtschaft, 74(11), 469-485

  18. 2022

    Performance of Machine Learning in short-term power forecasting within a run-of-river power plant chain.

    Christoph Klingler, Moritz Feigl, Thomas Linsbichler, Simon Frey, Karsten Schulz

    Österreichische Wasser- und Abfallwirtschaft, 74(5), 224-240

  19. 2022

    Evaluation of satellite precipitation products for water allocation studies in the

    Paul Omonge, Moritz Feigl, Luke Olang, Karsten Schulz, Mathew Herrnegger

    Sio-Malaba-Malakisiriver basin of East Africa. Journal of Hydrology: Regional Studies, 39, 100983

  20. 2022

    Prediction of soil hydraulic properties for the extent of Austria.

    Hanna Zeitfogel, Moritz Feigl, Karsten Schulz

    Österreichische Wasser- und Abfallwirtschaft, 74(3), 166-178

  21. 2021

    Machine-learning methods for stream water temperature prediction.

    Moritz Feigl, Katharina Lebiedzinski, Mathew Herrnegger, Karsten Schulz

    Hydrology and Earth System Sciences, 25(5), 2951-2977

  22. 2021

    Regionalization of hydrological models using function space optimization.

    Moritz Feigl, Mathew Herrnegger, Robert Schweppe, Stephan Thober, Daniel Klotz, Luis Samaniego, Karsten Schulz

    Österreichische Wasser- und Abfallwirtschaft, 73(7), 281-294

  23. 2021

    Prediction of stream water temperatures in Austrian catchments using machine learning methods.

    Moritz Feigl, Katharina Lebiedzinski, Mathew Herrnegger, Karsten Schulz

    Österreichische Wasser- und Abfallwirtschaft, 73(7), 308-328

  24. 2021

    LamaH-CE: LArge-SaMple DAta for Hydrology and Environmental Sciences for Central Europe.

    Christoph Klingler, Karsten Schulz, Mathew Herrnegger

    Earth System Science Data, 13(9), 4529-4565

  25. 2021

    LamaH | Large-Sample Data for Hydrology: big data for hydrology and environmental sciences.

    Christoph Klingler, Karsten Schulz, Mathew Herrnegger

    Österreichische Wasser- und Abfallwirtschaft, 73(7), 244-269

  26. 2021

    A Near Real-Time Hydrological Information System for the Upper Danube Basin.

    Thomas Pulka, Ignacio Martin Santos, Karsten Schulz, Mathew Herrnegger

    Hydrology, 8(4), 144

  27. 2021

    Systematic analysis and comparison of commercial seizure-detection software.

    Johannes Peter Koren, Sebastian Hafner, Moritz Feigl, Christoph Baumgartner

    Epilepsia, 62(2), 426-438

  28. 2020

    Function Space Optimization: A symbolic regression method for estimating parameter transfer

    Moritz Feigl, Mathew Herrnegger, Daniel Klotz, Karsten Schulz

    functions for hydrological models. Water Resources Research, 56(10), e2020WR027385

  29. 2020

    Local hydrological modelling containing global, alternative data sets.

    Christoph Klingler, Matthias Bernhardt, Johannes, Wesemann, Karsten Schulz, Mathew, Herrnegger

    Hydrologie und Wasserbewirtschaftung, 64(4), 166-187

  30. 2020

    On the Ability of LIDAR Snow Depth Measurements to Determine or Evaluate the HRU

    Michael Weber, Moritz Feigl, Karsten Schulz, Matthias Bernhardt

    Discretization in a Land Surface Model. Hydrology, 7(2), 20

  31. 2020

    Genome-wide association study of germline copy number variations reveals an

    Stefanie Brezina, Moritz Feigl, Tanja Gumpenberger, Ricarda Staudinger, Andreas Baierl, Andrea Gsur

    association with prostate cancer aggressiveness. Mutagenesis, 35(3), 283-290

  32. 2018

    The importance of Alpine research catchments for model evaluation and for the improvement of remote sensing products.

    Matthias Bernhardt, Stefan Härer, Moritz Feigl, Karsten Schulz

    Österreichische Wasser- und Abfallwirtschaft, 70(9), 515-528

Presentations 22

  1. 2024

    AI in the sector of water management – Short introduction and use cases.

    Moritz Feigl, Christoph Klingler

    7th Get-together of the group “Young Water Management” of the Austrian Water and Waste Management Association (ÖWAV), Vienna

  2. 2024

    Contribution of glacier melt to runoff under climate change using a conceptual hydrological model in selected high alpine regions in Austria.

    Caroline Ehrendorfer, Franziska Koch, Sophie Lücking, Thomas Pulka, Hubert Holzmann, P. Maier, F. Lehner, Herbert Formayer, Mathew Herrnegger

    EGU General Assembly 2024, Vienna

  3. 2023

    Austria-wide prediction of low-flow characteristics with machine learning.

    Moritz Feigl

    Austrian Society for Hydrology (ÖGH): When water becomes scarce, Vienna

  4. 2023

    Evaluation of precipitation corrections to improve reservoir inflow predictions by a conceptual hydrological model in the Malta Valley, Austria.

    Thomas Pulka, Mathew Herrnegger, Caroline Ehrendorfer, Sophie Lücking, Karsten Schulz, Franziska Koch

    HydroCarpath 2023, Sopron

  5. 2023

    Utilization of snow depth patterns to derive spatially distributed precipitation correction factors for operational hydrological modelling.

    Thomas Pulka, Franziska Koch, Mathew Herrnegger, Karsten Schulz

    EGU General Assembly 2023, Vienna

  6. 2023

    Coupled snow-hydrological modelling for two high alpine Austrian catchments.

    Caroline Ehrendorfer, Franziska Koch, Sophie Lücking, Thomas Pulka, Hubert Holzmann, P. Maier, F. Lehner, Herbert Formayer, Mathew Herrnegger

    HydroCarpath 2023, Sopron

  7. 2023

    Machbarkeitsstudie für einen WebGIS basierten Hydrologischen Atlas Österreichs | eHAO.

    Mathew Herrnegger, Oliver Konold, Thomas Pulka, Josef Fürst

    Austrian Society for Hydrology (ÖGH): eHydrologie – When paper gets scarce, Vienna

  8. 2022

    Machine Learning in the field of Hydrology

    Moritz Feigl, Christoph Klingler

    . Workshop for Digital Engineering – Association for networking and supporting digitization in engineering, Hirschwang Rax

  9. 2022

    Simulation of water retention by lakes to reduce the risk of flooding – Use case lake Mondsee.

    Max Preiml, Christoph Klingler

    DRD22 – Disaster Research Days, Innsbruck

  10. 2022

    AI and machine learning in hydrological sciences.

    Moritz Feigl

    BOKU Big Data Day, Vienna

  11. 2022

    Erfassung des Verbesserungspotentials operationeller Zuflussprognosen für Wasserkraft-Speicherseen in hochalpinen Kopfeinzugsgebieten mit Fokus auf die Schneedeckenmodellierung.

    Thomas Pulka, Franziska Koch, Mathew Herrnegger, Francesco Avanzi, S. Gabellani, Karsten Schulz

    4th Workshop zur Alpinen Hydrologie, University centre Obergurgl

  12. 2022

    Impact of snow hydrologic model complexity on snow-melt-driven runoff generation for operational reservoir inflow predictions in a high-alpine catchment.

    Thomas Pulka, Franziska Koch, Francesco Avanzi, S. Gabellani, Karsten Schulz

    3rd International Conference on Snow Hydrology

  13. 2021

    Catchment to model space mapping – learning transfer functions from data by symbolic regression.

    Moritz Feigl, Robert Schweppe, Stephan Thober, Mathew Herrnegger, Luis Samaniego, Karsten Schulz

    EGU General Assembly 2021

  14. 2021

    LamaH: Large-sample Data for Hydrology in Central Europe.

    Christoph Klingler, Frederik Kratzert, Karsten Schulz, Mathew Herregger

    EGU General Assembly 2021

  15. 2021

    Learning from mistakes – Assessing the performance and uncertainty in process-based models.

    Moritz Feigl, Benjamin Roesky, Mathew Herrnegger, Karsten Schulz, Masaki Hayashi

    KGML21 – 2nd Workshop on Knowledge Guided Machine Learning

  16. 2021

    Learning from mistakes – Assessing the performance and uncertainty in process-based models.

    Benjamin Roesky, Moritz Feigl, Mathew Herrnegger, Karsten Schulz, Masaki Hayashi

    EGU General Assembly 2021

  17. 2021

    Variability across scales – exploring methods for predicting soil properties from multiple sources.

    Hanna Zeitfogel, Moritz Feigl, Karsten Schulz

    EGU General Assembly 2021

  18. 2021

    Large-scale river network modeling using Graph Neural Networks.

    Frederik Kratzert, Daniel Klotz, Martin Gauch, Christoph Klingler, Grey Nearing, Sepp Hochreiter

    EGU General Assembly 2021

  19. 2021

    Auswertung von Satellitendaten zum Thema Gletscherrückgang.

    Franziska Koch, Thomas Pulka, R. Stolz

    PerspektivForum Zukunftsfragen „Klimawandel im alpinen Raum“ der Stiftung Jugend forscht e. V., Garmisch Partenkirchen

  20. 2020

    Automatic Estimation of Parameter Transfer Functions for Distributed Hydrological Models –

    Moritz Feigl, Robert Schweppe, Stephan Thober, Mathew Herrnegger, Luis Samaniego, Karsten Schulz

    Function Space Optimization Applied on the mHM Model. AGU Fall Meeting 2020, San Francisco

  21. 2020

    Automatic estimation of parameter transfer functions for distributed hydrological models –

    Moritz Feigl, Stephan Thober, Mathew Herrnegger, Luis Samaniego, Karsten Schulz

    a case study with the mHM model. EGU General Assembly 2020, Vienna

  22. 2019

    Function Space Optimization (FSO): A novel method for estimating parameter

    Moritz Feigl, Mathew Herrnegger, Daniel Klotz, Karsten Schulz

    transfer functions for hydrological models. AGU Fall Meeting 2019, San Francicso

Interviews 1

  1. 2022

    baseflow.ai: Applying Machine Learning in Hydrology.

    Moritz Feigl

    Austrian AI Podcast by Manuel Pasieka

Datasets 3

  1. 2025

    Study “Water availability in Austria’s streams”

    Moritz Feigl, Christoph Klingler, Andrea Bichler

    – Digital appendix. Ministry for Agriculture and Forestry, Climate and Environmental Protection, Regions and Water Management

  2. 2022

    Prediction of runoff characteristics in ungauged basins in Central Europe with machine learning – files.

    Christoph Klingler, Moritz Feigl, Florian Borgwardt, Mathew Herrnegger

    Version 1.0, Zenodo

  3. 2021

    LamaH-CE: LArge-SaMple DAta for Hydrology and Environmental Sciences for Central Europe – files.

    Christoph Klingler, Frederik Kratzert, Karsten Schulz, Mathew Herrnegger

    Version 1.0, Zenodo