Frederik Kratzert, Mathew Herrnegger, Daniel Klotz, Sepp Hochreiter, and Günter Klambauer
Despite the huge success of Long Short-Term Memory networks, their applications in environmental sciences are scarce. We argue that one reason is the difficulty to interpret the internals of trained networks. In this study, we look at the application of LSTMs for rainfall-runoff forecasting, one of the central tasks in the field of hydrology, in which the river discharge has to be predicted from meteorological observations. LSTMs are particularly well-suited for this problem since memory cells can represent dynamic reservoirs and storages, which are essential components in state-space modelling approaches of the hydrological system. On basis of two different catchments, one with snow influence and one without, we demonstrate how the trained model can be analyzed and interpreted. In the process, we show that the network internally learns to represent patterns that are consistent with our qualitative understanding of the hydrological system.
in Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer, doi.org/10.1007/978-3-030-28954-6_19, see preprint at arXiv, 1903.07903v1, 2019-03-19.