Mid- to long-term runoff prediction by combining the deep belief network and partial least-squares regression

Abstract

<jats:title>Abstract</jats:title> <jats:p>Data representation and prediction model design play an important role in mid- to long-term runoff prediction. However, it is challenging to extract key factors that accurately characterize the changes in the runoff of a river basin because of the complex nature of the runoff process. In addition, the low accuracy is another problem for mid- to long-term runoff prediction. With an aim to solve these problems, two improvements are proposed in this paper. First, the partial mutual information (PMI)-based approach was employed for estimating the importance of various factors. Second, a deep learning architecture was introduced by using the deep belief network (DBN) with partial least-squares regression (PLSR), together denoted as PDBN, for mid- to long-term runoff prediction, which solves the problem of parameter optimization for the DBN using PLSR. The novelty of the proposed method lies in the key factor selection and a novel forecasting method for mid- to long-term runoff. Experimental results demonstrated that the proposed method can significantly improve the effect of mid- to long-term runoff prediction. Also, compared with the results obtained by current state-of-the-art prediction methods, i.e., DBN, backpropagation neural networks, and support vector machine models, our prediction results demonstrate the performance of the proposed method.</jats:p>

A novel medium- and long-term runoff combined forecasting model based on different lag periods

“…For the convenience of analysis, they are abbreviated as a1, a2,…, a96. In addition, due to the lag effect of climate-related factors on runoff (Yue et al 2020a), this paper took 6, 12, 18 and 24-month lag as the different lag periods. Thus, the input factors are expressed as a1(t À 1), a1(t À 2),…, a1(t À T),…, a96(t À 1), a96(t À 2),…, a96(t À T ) (T ¼ 6, 12, 18, 24), including (96*T ) variables.…”

“…But there is no single standard to determine which evaluation metric is the most accurate assessment method. Therefore, to estimate the performance of the proposed model, the evaluation metrics, such as bias index (BIAS) (Najafzadeh & Sattar 2015;Barzkar et al 2021), scatter index (SI) (Najafzadeh et al 2020), mean absolute percentage error (MAPE), root-mean-square error (RMSE), mean absolute error (MAE) and deterministic coefficient (DC) (Yue et al 2020a(Yue et al , 2020b, are applied. Among them, four common evaluation metrics are adopted in this paper, including MAE, MAPE, RMSE and DC.…”

“…With the development of national economy and the adjustment of national water control policy, the gap between the existing hydrologic medium-and long-term runoff forecasting methods and the demand for production and application have been further widened. In addition, due to the increasing amount of hydrological data, it can introduce redundant and noisy information to the prediction feature or factor, which may deteriorate the performance of the mid-to long-term runoff prediction (Yue et al 2020a). Therefore, runoff prediction is not only a management issue but also a scientific problem, and accurate runoff forecasts will be of vital importance to the policymakers.…”

“…However, the determination of a suitable set of inputs is challenging due to the time lag of runoff response to the influence of large-scale atmospheric circulation (Cheng et al 2019). The existing studies on the lag selection of runoff factors are mainly carried out for 1 or 2 years (Gao 2006;Yang et al 2013;Li et al 2019;Yue et al 2020a). It is generally known that it is difficult to accurately determine the lag period since runoff flows through different field conditions to reach a point (He et al 2011).…”

A Regional Semi-Distributed Streamflow Model Using Deep Learning

“…While many hydrologic models have been developed over the past 50 years, the challenge of providing streamflow forecasts accurately, efficiently and everywhere at all times remains. Several studies have applied deep learning in water resources fields, including surface water quality (Hu et al, 2019;Zhou, 2020), streamflow forecasting (Feng et al, 2020;Li et al, 2020;Qian et al, 2020;Sarkar et al, 2020;Van et al, 2020;Yue et al, 2020), soil moisture (Fang and Shen, 2020), groundwater (Wang et al, 2020;Yu et al, 2020), hydrometeorology (Chen et al, 2020;Lee et al, 2020), and water management (Liu et al, 2019). Recent studies (Chang et al, 2015;Granata et al, 2016;Faruk, 2010;Sit and Demir, 2019) have shown that many machine learning and deep learning models could be valuable in streamflow forecasting.…”