Modeling the relationship between rainfall and runoff is a longstanding challenge in hydrology and is crucial for informed water management decisions. Recently, Deep Learning models, particularly Long short-term memory (LSTM), have shown promising results in simulating this relationship. The Transformer, a newly proposed deep learning architecture, has also demonstrated the ability to outperform LSTM in machine translation, text classification, etc. However, there has been limited research on applying Transformers for rainfall-runoff modeling. The research examined the performance of using Transformer architecture, including its time series forecasting variants, to develop rainfall-runoff models using the CAMELS (US) data set. These models were compared to the LSTM regional rainfall-runoff models, with a particular focus on snow-driven basins as the attention mechanism in Transformer is believed to allow it to attend to the earlier precipitation events in the meteorological forcing. Additionally, the Transformer's potential as a global rainfall-runoff model was also tested using the global Caravan data to determine if it could learn and generalize a wide range of rainfall-runoff behaviors, allowing it to potentially be applied in ungauged basins. The results suggest that while Transformer and its variants may not be able to fully replace LSTM for rainfall-runoff modeling, the variant called Reformer has shown promise for daily discharge forecasting in snow-driven basins, particularly in terms of peak flow and low flow prediction. However, using the global Caravan data for building a global rainfall-runoff model was not successful due to uncertainty in the forcing data, particularly precipitation. The code for Transformer-based rainfall-runoff modeling is available publicly at https://github.com/Numpy-Panda/neuralhydrology_Transformer.

Floods are the most frequent natural disaster and due to climate change the frequency and intensity of these events are increasing. Therefore, it is becoming increasingly important to obtain accurate estimations of extreme discharges. Statistical modelling is widely used to estimate extreme discharges by fitting observed extreme discharges to an extreme value distribution. However, limited historical data makes it difficult to confidently model the tail behavior of extremes. Additionally, several modelling assumptions impact extreme discharge estimates including selection of the nonstationary method, extreme value distribution, parameter estimation method, and the impact of seasonality. In an effort to reduce uncertainties, a new method has been developed to derive design discharges for the Meuse in the Netherlands. This method, GRADE (Generator of Rainfall and Discharge Extremes) consists of three components: a stochastic weather generator, a hydrological model, and an extreme value analysis (EVA). However, the stochastic weather generator is not capable of producing daily rainfall that exceeds the range of historical data. Therefore, a physically based climate model, RACMO, is now being studied. RACMO is capable of generating 1,040 years of synthetic meteorological data that can be routed in a hydrological model to obtain 1,040 years of synthetic discharges. The physically based climate model makes it possible to capture the underlying physical processes of extreme events and the hydrological model can provide discharge information at locations where there are no observations. This thesis evaluates the impact various modelling assumptions have on estimated discharges using synthetic data generated by the RACMO through application of a case study in the Meuse.

Under future warmer climates, drought events are projected to occur more frequently with increasing impacts in many regions and river basins. This study focuses on exploring the potential of the LSTM deep learning (DL) approach for operational streamflow drought forecasting for the Rhine River at Lobith with a lead time (LT) of up to 46 days. The research investigates optimal spatial resolution, input and target variables, and loss functions. Four LSTM-based model architectures are developed and tested, incorporating both historical observation and forecast data to generate 46-step forecasts simultaneously. The robustness and stability of the models are assessed through cross-validation, and their performances are compared. Subsequently, the performance of the LSTM-based model is compared to the physically-based models, namely Wflow-Rhine and FEWS-Rhine, in forecasting streamflow drought. The results suggest that utilizing a subbasin spatial resolution, including historical discharge as input, and training the model on time-differenced data enhance the forecast skill. Among the evaluated models, the model architecture with two LSTMs in cascade exhibits stable and robust performance across the forecast horizon and is considered for operational use in this study. Comparisons between the DL model and physically-based models indicate that: 1) When using observed meteorology forcing from ERA5, the DL model demonstrates a notable performance compared to Wflow-Rhine simulation using the same forcing data. 2) When utilizing SEAS5 for forecasting, the DL model demonstrates skill over Wflow-Rhine in predicting discharge levels during the dry season up to 10 days ahead, as well as for discharges between 950 and 2200 m3/s across the entire forecast horizon. However, for discharges between 700 and 950 m3/s with longer LTs beyond 20 days, Wflow-Rhine shows skill over the DL model. 3) While FEWS-Rhine successfully forecasts drought events in 2018 throughout the forecast horizon, it tends to produce more Type I errors (false positives). The DL model, forecasting with SEAS5, accurately predicts drought events in 2018 for LTs up to 30 days and generally has higher precision values. Despite using different forcing datasets, the DL model can predict the timing and trend of past drought events, indicating its potential in capturing streamflow patterns. This study contributes to operational water management in the Netherlands by employing the LSTM deep learning approach in an operational framework for drought forecasting. By leveraging historical observation data and forecasted meteorology forcing data, these models achieve skillful performances for streamflow drought forecasts. Future research could focus on further enhancing model performance, exploring the applicability of the LSTM-based models in other river basins, and validating the results in real operational settings.