Uncertainty Quantification in Machine Learning Modeling for Multi-Step Time Series Forecasting: Example of Recurrent Neural Networks in Discharge Simulations
Open Access
Abstract
As a revolutionary tool leading to substantial changes across many areas, Machine Learning (ML) techniques have obtained growing attention in the field of hydrology due to their potentials to forecast time series. Moreover, a subfield of ML, Deep Learning (DL) is more concerned with datasets, algorithms and layered structures. Despite numerous applications of novel ML/DL techniques in discharge simulation, the uncertainty involved in ML/DL modeling has not drawn much attention, although it is an important issue. In this study, a framework is proposed to quantify uncertainty contributions of the sample set, ML approach, ML architecture and their interactions to multi-step time-series forecasting based on the analysis of variance (ANOVA) theory. Then a discharge simulation, using Recurrent Neural Networks (RNNs), is taken as an example. Long Short-Term Memory (LSTM) network, a state-of-the-art DL approach, was selected due to its outstanding performance in time-series forecasting, and compared with simple RNN. Besides, novel discharge forecasting architecture is designed by combining the expertise of hydrology and stacked DL structure, and compared with conventional design. Taking hourly discharge simulations of Anhe (China) catchment as a case study, we constructed five sample sets, chose two RNN approaches and designed two ML architectures. The results indicate that none of the investigated uncertainty sources are negligible and the influence of uncertainty sources varies with lead-times and discharges. LSTM demonstrates its superiority in discharge simulations, and the ML architecture is as important as the ML approach. In addition, some of the uncertainty is attributable to interactions rather than individual modeling components. The proposed framework can both reveal uncertainty quantification in ML/DL modeling and provide references for ML approach evaluation and architecture design in discharge simulations. It indicates uncertainty quantification is an indispensable task for a successful application of ML/DL.Keywords
Funding Information
- National Natural Science Foundation of China (2018YFC0407705, 51709036, 91747102, 51879029)
This publication has 26 references indexed in Scilit:
- Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type modelsExpert Systems with Applications, 2018
- Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signalsComputers in Biology and Medicine, 2018
- LSTM network: a deep learning approach for short‐term traffic forecastIET Intelligent Transport Systems, 2017
- Exploiting Depth and Highway Connections in Convolutional Recurrent Deep Neural Networks for Speech Recognition2016
- Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information RetrievalIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Unbalanced robust ANOVA for the estimation of measurement uncertainty at reduced costAnalytical Methods, 2014
- Quantifying uncertainty sources in an ensemble of hydrological climate‐impact projectionsWater Resources Research, 2013
- An intercomparison of regional climate simulations for Europe: assessing uncertainties in model projectionsClimatic Change, 2007
- River flood forecasting with a neural network modelWater Resources Research, 1999
- Long Short-Term MemoryNeural Computation, 1997