Poster presentation at the EGU General Assembly 2019 on uncertainty estimation using MC-Dropout and LSTMs.
Abstract
All forms of hydrological endeavors are pervaded by uncertainty. Therefore it is of little surprise that obtaining realistic estimates of prediction uncertainties has become a persistent ambition. m This contribution analyzes the capability of using a specific regularization-mechanism, called dropout, for uncertainty estimation of a neural network based rainfall-runoff models.
The particular form of network under examination is based on the Long Short-Term Memory (LSTM) architecture, which was explicitly designated for time series applications (Hochreiter, citation). Recently, Kratzert el al.(2018a) have shown that LSTM based modeling approaches can be used as data-driven models for describing the rainfall-runoff relationship. The authors envisioned future applications for task like online prediction, where the model would be used in conjunction with a stack of other models. We believe that this envisioned application will only be possible if the networks will earn the trustworthiness from the wider hydrological community by exhibiting properties that go beyond mere performance. One potential avenue for cashing-out on this point is to open the black-box and analyze if the neural network reproduced internally (known) hydrological patterns (such as snow-accumulation and depletion processes, see Kratzert 2018b). A complementary approach, which is extremely important for any environmental model, is to characterize the uncertainty of a given prediction/simulation.
Abstract Link
Poster
Link will follow
Citation
@inproceedings{{klotz2019towards,
title={Towards the quantification of uncertainty for deep learning based rainfall-runoff models},
author={Klotz, Daniel and Kratzert, Frederik and Herrnegger, Mathew and Hochreiter, Sepp and Klambauer, G{\"u}nter},
booktitle={Geophysical Research Abstracts, Vol. 21, EGU2019-10708-2, EGU General Assembly},
venue={Vienna, Austria},
date={8-12 Apr},
year={2019}
}