| Abstrakt: |
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 single-well models, where one model is trained for each well separately. However, recent developments in neighbouring disciplines including hydrology (rainfall-runoff-modelling) have shown that global models, being able to incorporate data of several wells, may have advantages. These models are often called entity-aware models, as they usually rely on static data to differentiate the entities, i.e. groundwater wells in hydrogeology or catchments in surface hydrology.We test two kinds of static information to characterize the groundwater wells in a global, entity-aware deep learning model setup, first, environmental features that are continuously available and thus theoretically allow spatial generalization (regionalization), and second, timeseries features that are derived from the past time series at the respective well. Moreover, we test random integer features as entity information for comparison.We use a published dataset of 108 groundwater wells in Germany, and evaluate the models' performances in terms of Nash-Sutcliffe efficiency (NSE) in an in-sample and an out-of-sample setting, representing temporal and spatial generalization. Our results show, that entity-aware models work well with a mean performance of NSE > 0.8 in an in-sample setting, thus being comparable to, or even outperforming single-well models. However, they do not generalize well spatially in an out-of-sample setting (mean NSE < 0.7, i.e. lower than a global model without entity information). The reason for this potentially lies in the small number of wells in the dataset, which might not be enough to take full advantage of global models. However, also more research is needed to find meaningful static features for ML in hydrogeology. [ABSTRACT FROM AUTHOR] |
