Predictability of Monthly Streamflow Time Series and its Relationship with Basin Characteristics: an Empirical Study Bas
- PDF / 1,429,881 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 182 Views
Predictability of Monthly Streamflow Time Series and its Relationship with Basin Characteristics: an Empirical Study Based on the MOPEX Basins Ran-Ran He 1,2 & Yuanfang Chen 1 & Qin Huang 1 & Zheng-Wei Pan 2 & Yong Liu 3 Received: 1 April 2020 / Accepted: 2 November 2020/ # Springer Nature B.V. 2020
Abstract
Machine learning (ML) models have been applied to monthly streamflow forecasting in recent decades. In this study, forecasting skills of eight ML models are evaluated based on the Model Parameter Estimation Experiment (MOPEX) dataset. We consider two skill scores, i.e., the Nash–Sutcliffe efficiency (NSE) and the adjusted NSE (ANSE), and the latter is the skill score based on the interannual mean monthly value (MMV) as the reference (benchmark) model. Furthermore, NSE of the MMV model (NSEmmv) is used as a measure of the seasonality of monthly streamflow, as it is the ratio of variance explained by the MMV process. An important result is that forecasting skills of ML models for monthly streamflow are largely controlled by NSEmmv. Moreover, based on comparisons of different ML models, we have found that the selection of models is not a dominating factor impacting the final skill. Three key factors influencing NSE, i.e., NSEmmv, the base flow index (BFI) and the aridity index (AI), are explored in this paper. Specifically, NSEmmv impacts NSE directly and is the predominant factor; BFI influences the memory of the monthly streamflow and therefore influences NSE. The relationship between AI and NSE is much complex and indirect. Firstly, basins with higher AI tend to have lower NSEmmv, and this will lead to lower NSE; secondly, basins with higher AI tend to have lower BFI, which will also lead to lower NSE; thirdly, for a given BFI level, basins with higher AI tend to have higher memory and higher NSE. For ANSE, basins with AI between 1 and 2 show higher ANSE, which corresponds to higher autocorrelation coefficients. Keywords Monthly streamflow forecasting . Machine learning . Aridity index . Streamflow seasonality . Predictability
* Yuanfang Chen [email protected]
1
College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China
2
College of Civil Engineering, Bengbu University, Bengbu 233030 Anhui, China
3
State Key Lab of Hydrology-Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing 210029, China
He R.-R. et al.
1 Introduction Skillful hydrological forecasting is useful for water resources management and early warning of water hazards such as floods and droughts (Gong et al. 2010). Hydrological time series forecasting is a traditional problem for hydrological scientists, and stochastic models like the autoregressive integrated moving average (ARIMA) model are often used for this task. As machine learning (ML) models can also be used for time series forecasting (Ahmed et al. 2010; Bontempi et al. 2013), ML models have been frequently used for monthly streamflow modelling and forecasting in recent decades (Wu and Chau 2010; Abudu et al. 2010;
Data Loading...
