Improving the Reliability of Probabilistic Multi-Step-Ahead Flood Forecasting by Fusing Unscented Kalman Filter with Recurrent Neural Network

Abstract

It is fundamentally challenging to quantify the uncertainty of data-driven flood forecasting. This study introduces a general framework for probabilistic flood forecasting conditional on point forecasts. We adopt an unscented Kalman filter (UKF) post-processing technique to model the point forecasts made by a recurrent neural network and their corresponding observations. The methodology is tested by using a long-term 6-h timescale inflow series of the Three Gorges Reservoir in China. The main merits of the proposed approach lie in: first, overcoming the under-prediction phenomena in data-driven flood forecasting; second, alleviating the uncertainty encountered in data-driven flood forecasting. Two commonly used artificial neural networks, a recurrent and a static neural network, were used to make the point forecasts. Then the UKF approach driven by the point forecasts demonstrated its competency in increasing the reliability of probabilistic flood forecasts significantly, where predictive distributions encountered in multi-step-ahead flood forecasts were effectively reduced to small ranges. The results demonstrated that the UKF plus recurrent neural network approach could suitably extract the complex non-linear dependence structure between the model’s outputs and observed inflows and overcome the systematic error so that model reliability as well as forecast accuracy for future horizons could be significantly improved.

Decline in net primary productivity caused by severe droughts: evidence from the Pearl River basin in China

“…In this study, the VIC model was verified through a comparison between the simulated stream flows and the observations. The Nash-Sutcliffe efficiency (NSE), relative error (Bias), and determination coefficient (R 2 ) were used for the evaluation of model accuracy (Zhou et al 2019(Zhou et al , 2020Kao et al 2020;Lin et al 2020). A significant coincidence rate with P , 0.05 was detected in both the calibration and validation (Figure 2), demonstrating that the VIC-based ETa is adaptable and rational for the subsequent drought analysis.…”

Predicting Outflow Hydrographs of Potential Dike Breaches in a Bifurcating River System Using NARX Neural Networks

“…A NARX is a recurrent dynamic neural network with feedback connections suitable for time series prediction [8,32]. NARX networks have widely been applied in the field of hydrology ranging from predicting groundwater levels [32] to floods within urban drainage systems [33] and rainfall-triggered flood forecasting in urban and rural areas [8,34]. This study uses NARX neural networks to predict outflow hydrographs of multiple potential dike breach locations for the first time.…”

Daily Water Flow Forecasting via Coupling Between SMAP and Deep Learning

“…Zhou et al [29] developed a forecast 4 days ahead of the inflow of the Three Gorges HPP reservoir. In this study, the unscented Kalman Filter (UKF) was applied with two DL techniques: BPNN and a non-linear auto-regressive with exogenous inputs recurrent neural network (NARX).…”