We show the results of the 2022 Groundwater Time Series Modelling Challenge; 15 teams applied data-driven models to simulate hydraulic heads, and three model groups were identified: lumped, machine learning, and deep learning. For all wells, reasonable performance was obtained by at least one team from each group. There was not one team that performed best for all wells. In conclusion, the challenge was a successful initiative to compare different models and learn from each other.

Geoscientists commonly use various potential evapotranpiration (PET) formulas for environmental studies, which can be prone to errors and sensitive to climate change. PyEt, a tested and open-source Python package, simplifies the application of 20 PET methods for both time series and gridded data, ensuring accurate and consistent PET estimations suitable for a wide range of environmental applications.

Recession models (RM) are crucial for observing the low flow behavior of a catchment. We developed two novel RM, which are designed to represent slowly draining catchment conditions. With a newly designed low flow prediction procedure we tested the prediction capability of these two models and three others from literature. One of our novel products delivered the best results, because it best represents the slowly draining catchment conditions.

CAMELS-CH is an open large-sample hydro-meteorological data set that covers 331 catchments in hydrologic Switzerland from 1 January 1981 to 31 December 2020. It comprises (a) daily data of river discharge and water level as well as meteorologic variables like precipitation and temperature; (b) yearly glacier and land cover data; (c) static attributes of, e.g, topography or human impact; and (d) catchment delineations. CAMELS-CH enables water and climate research and modeling at catchment level.

Hybrid forecasting systems combine data-driven methods with physics-based weather and climate models to improve the accuracy of predictions for meteorological and hydroclimatic events such as rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. We review recent developments in hybrid forecasting and outline key challenges and opportunities in the field.

This paper introduced PyEt, a Python package for the estimation of daily potential evapotranspiration (PET). The package enables the inclusion of model uncertainty and climate change into the estimation of PET in a consistent, tested, and reproducible environment. With PyEt, users can estimate PET using 20 different methods for both 1D and 3D data, allowing a more sophisticated and comprehensive consideration of PET in hydrological studies, particularly those related to climate change.

This study explores the use of nonlinear transfer function noise (TFN) models to simulate groundwater levels and estimate groundwater recharge from observed groundwater levels. A nonlinear recharge model is implemented in a TFN model to compute the recharge. The estimated recharge rates are shown to be in good agreement with the recharge observed with a lysimeter present at the case study site in Austria. The method can be used to obtain groundwater recharge rates at sub-yearly timescales.