 This paper proposes a new data-driven approach to rainfall runoff modeling by using a long short-term memory, LSTM, network, a type of recurrent neural network. This approach was tested on 241 catchments of the freely available camels data set and compared to the Sacramento soil moisture accounting model, SACSMA, coupled with the SNO-17 SNO routine. The results showed that the LSTM outperformed the SACSMA model in terms of accuracy and precision. Additionally, the LSTM was able to transfer knowledge gained from regional scale to individual catchments, resulting in improved model performance. These findings suggest that the LSTM can be used as a powerful tool for rainfall runoff modeling. This article was authored by F. Krotzert, F. Krotzert, D. Klotz, and others.