Details

Autor(en) / Beteiligte

• Kratzert, Frederik
• Klotz, Daniel
• Shalev, Guy
• Klambauer, Günter
• Hochreiter, Sepp
• Nearing, Grey

Titel

Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets

Ist Teil von

• Hydrology and earth system sciences, 2019-12, Vol.23 (12), p.5089-5110

Ort / Verlag

Katlenburg-Lindau: Copernicus GmbH

Erscheinungsjahr

2019

Link zum Volltext

Quelle

EZB Electronic Journals Library

Beschreibungen/Notizen

• Regional rainfall–runoff modeling is an old but still mostly outstanding problem in the hydrological sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone. In this paper, we propose a novel, data-driven approach using Long Short-Term Memory networks (LSTMs) and demonstrate that under a “big data” paradigm, this is not necessarily the case. By training a single LSTM model on 531 basins from the CAMELS dataset using meteorological time series data and static catchment attributes, we were able to significantly improve performance compared to a set of several different hydrological benchmark models. Our proposed approach not only significantly outperforms hydrological models that were calibrated regionally, but also achieves better performance than hydrological models that were calibrated for each basin individually. Furthermore, we propose an adaption to the standard LSTM architecture, which we call an Entity-Aware-LSTM (EA-LSTM), that allows for learning catchment similarities as a feature layer in a deep learning model. We show that these learned catchment similarities correspond well to what we would expect from prior hydrological understanding.