Posts

05 May 2023 / conference

Oral presentation for EGU General Assembly 2023. This is one about a certain phenomena that appears when we evaluate a model over subsets of the data. Eventually the plan is to make a technical note out of it.

10 October 2022 / paper / code

In this paper, we present the results of the “Rate My Hydrograph” study, where we compare expert ratings of simulated hydrographs with quantitative metrics.

08 August 2022 / paper
07 July 2022 / paper / code
06 June 2022 / paper / code
06 June 2022 / paper / code / dataset
05 May 2022 / conference

Oral presentation at the EGU General Assembly 2022 on a social study to compare expert rankings of simulated hydrographs with quantitative metrics.

05 May 2022 / conference
01 January 2022 / paper / code

This paper investigates the hypothesis that the lack of enforced mass conservation is the main reason that deep learning models outperform traditional hydrology models.

12 December 2021 / conference
11 November 2021 / paper / code
10 October 2021 / paper / code
08 August 2021 / paper / code
05 May 2021 / paper / code

In this paper we show the benefits of using multiple meteorological forcing products at the same time in a single LSTM-based rainfall-runoff model over just using a single product.

05 May 2021 / conference / video
05 May 2021 / conference
05 May 2021 / conference / video
04 April 2021 / paper / code
04 April 2021 / paper / code
01 January 2021 / dataset / conference

LamaH-CE contains a collection of runoff and meteorological time series as well as various (catchment) attributes for 859 gauged basins in the upper Danube catchment and Austria.

01 January 2021 / dataset
01 January 2021 / paper / code

In this study, we present a mass-conserving variant of the LSTM and its application to arithmetic tasks, traffic forecasting, modeling a pendulum and rainfall-runoff modeling.

12 December 2020 / conference / video
12 December 2020 / conference / video
12 December 2020 / workshops / video

Spotlight talk at the AI for Earth Sciences workshop of the NeurIPS 2020, presenting introduction of the world and terminology of hydrology/streamflow prediction for data scientists.

12 December 2020 / workshops / video

Spotlight talk at the AI for Earth Sciences workshop of the NeurIPS 2020, presenting a first glimpse of a new LSTM-based model that conserves mass by design: the Mass-Conserving LSTM

11 November 2020 / paper
06 June 2020 / paper / code
05 May 2020 / conference
05 May 2020 / conference

Virtual presentation at the EGU General Assembly 2020 comparing LSTMs trained for each basin individually with a single LSTM trained for all basins together.

05 May 2020 / conference
05 May 2020 / conference
04 April 2020 / workshops

Modeling entire nested river trees by integrating the river hierachy into the neural network architecture. This manuscripts proposes HydroNets, an architecture designed for modeling multiple nested gauge stations.

12 December 2019 / workshops
12 December 2019 / workshops
12 December 2019 / conference
12 December 2019 / conference
11 November 2019 / paper / code

In this manuscript we test LSTM-based rainfall-runoff models on the task of prediction in ungauged basins and show, that a single LSTM-based model does better prediction in ungauged basins than a traditional hydrological model that was specifically calibrated for each basin individually.

11 November 2019 / paper / code

This paper investigates the influence of the number of training basins and the training period length on the model performance for the EA-LSTM and XGBoost