scholarly journals Annual Runoff Forecasting Based on Multi-Model Information Fusion and Residual Error Correction in the Ganjiang River Basin

Water ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2086
Author(s):  
Peibing Song ◽  
Weifeng Liu ◽  
Jiahui Sun ◽  
Chao Wang ◽  
Lingzhong Kong ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Error Correction ◽  
River Basin ◽  
Information Fusion ◽  
Principal Components ◽  
Annual Runoff ◽  
Forecasting Model ◽  
Runoff Forecasting ◽  
Ganjiang River Basin

Accurate forecasting of annual runoff time series is of great significance for water resources planning and management. However, considering that the number of forecasting factors is numerous, a single forecasting model has certain limitations and a runoff time series consists of complex nonlinear and nonstationary characteristics, which make the runoff forecasting difficult. Aimed at improving the prediction accuracy of annual runoff time series, the principal components analysis (PCA) method is adopted to reduce the complexity of forecasting factors, and a modified coupling forecasting model based on multiple linear regression (MLR), back propagation neural network (BPNN), Elman neural network (ENN), and particle swarm optimization-support vector machine for regression (PSO-SVR) is proposed and applied in the Dongbei Hydrological Station in the Ganjiang River Basin. Firstly, from two conventional factors (i.e., rainfall, runoff) and 130 atmospheric circulation indexes (i.e., 88 atmospheric circulation indexes, 26 sea temperature indexes, 16 other indexes), principal components generated by linear mapping are screened as forecasting factors. Then, based on above forecasting factors, four forecasting models including MLR, BPNN, ENN, and PSO-SVR are developed to predict annual runoff time series. Subsequently, a coupling model composed of BPNN, ENN, and PSO-SVR is constructed by means of a multi-model information fusion taking three hydrological years (i.e., wet year, normal year, dry year) into consideration. Finally, according to residual error correction, a modified coupling forecasting model is introduced so as to further improve the accuracy of the predicted annual runoff time series in the verification period.

scholarly journals Research on GDP Forecast Analysis Combining BP Neural Network and ARIMA Model

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shaobo Lu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Model ◽  
Error Correction ◽  
Relative Error ◽  
Bp Neural Network ◽  
Arima Model ◽  
Forecast Model ◽  
Price Prediction ◽  
The Neural Network

Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model. First, the focus is on the ARMA model in the univariate time series. However, in real life, forecasts are often affected by many factors, so the following introduces the ARIMAX model in the multivariate time series. In the prediction process, the network structure and various parameters of the neural network are not given in a systematic way, so the operation of the neural network is affected by many factors. Each forecasting method has its scope of application and also has its own weaknesses caused by the characteristics of its own model. Secondly, this paper proposes an effective combination method according to the GDP characteristics and builds an improved algorithm BP neural network price prediction model, the research on the combination of GDP prediction model is currently mostly focused on the weighted form, and this article proposes another combination, namely, error correction. According to the price characteristics, we determine the appropriate number of hidden layer nodes and build a BP neural network price prediction model based on the improved algorithm. Validation of examples shows that the error-corrected GDP forecast model is also better than the weighted GDP forecast model, which shows that error correction is also a better combination of forecasting methods. The forecast results of BP neural network have lower errors and monthly prices. The relative error of prediction is about 2.5%. Through comparison with the prediction results of the ARIMA model, in the daily price prediction, the relative error of the BP neural network prediction is 1.5%, which is lower than the relative error of the ARIMA model of 2%.

scholarly journals Assessment of Hydrological Changes and Their Influence on the Aquatic Ecology over the last 58 Years in Ganjiang Basin, China

2019 ◽  
Vol 11 (18) ◽  
pp. 4882 ◽  
Author(s):  
Yinghou Huang ◽  
Binbin Huang ◽  
Tianling Qin ◽  
Hanjiang Nie ◽  
Jianwei Wang ◽  
...  
Keyword(s):  
River Basin ◽  
Human Activities ◽  
Hydrological Regime ◽  
Aquatic Organisms ◽  
Annual Runoff ◽  
Habitat Model ◽  
Fall Rate ◽  
Flood Season ◽  
Daily Precipitation Data ◽  
Ganjiang River Basin

Runoff is the key driving factor of the Ganjiang River ecosystem. Human activities such as reservoir construction have greatly changed the state of runoff. In order to analyze the influence of Ganjiang Reservoir on the hydrological regime, the following paper is based on the daily precipitation data of 53 rainfall stations in Ganjiang River Basin from 1959 to 2016, and the daily runoff data of three stations in Dongbei, Ji’an, and Waizhou from 1959 to 2016. The Mann–Kendall test (MK) was used to analyze the trend of precipitation and runoff in Ganjiang River Basin. The Sliding t-Test (ST) was used to determine the abrupt change time of runoff in flood season within typical cross-sections of upper, middle, and lower reaches of Ganjiang River Basin, Ji’an, and Waizhou. Indicators of hydrological change (IHA), range of variability approach (RVA), and other methods were used to analyze the changes of 32 hydrological indicators in Ganjiang River Basin. The results showed that (1) The annual and flood season precipitation in Ganjiang River Basin increased from 1992 to 2016, but it did not reach a significant level. The change of annual runoff at Dongbei and Waizhou Stations was the same as that of the annual precipitation in Ganjiang River Basin. The runoff of Dongbei Station in flood season decreased from 1986 to 2016, and the runoff of Waizhou Railway Station in flood season decreased from 2008 to 2016. It showed that precipitation had a great influence on annual runoff, and human activities made the annual runoff distribution process more uniform; (2) The abrupt changes of runoff in flood season at three hydrological stations in Ganjiang River Basin occurred in 1991, and reached a significant level of 0.01; (3) There were five hydrological indicators of Dongbei Station which had reached height change. The change degree of low (l) pulse duration was −92.24%, the change degree of high (h) pulse count was −86.8%, the change degree of flow rise rate was 87.06%, the change degree of fall rate was −92.24%, and the change degree of number of reversals was −100%. Four hydrological indicators of Ji’an Station had reached high change degree, the count and duration of high pulse changes were −73.33% and −73.65%, the change degree of fall rate was −79%, and the change degree of number of reversals was −100%. Waizhou Station did not reach the high change indicator. The hydrological regime of the upper and middle reaches of Ganjiang River has changed greatly, while the hydrological regime of the lower reaches has changed little. The hydrological regime in the upper and middle reaches of Ganjiang River Basin has been highly changed by human activities such as dam construction. The change of hydrological conditions in the upper and middle reaches of Ganjiang River Basin may reduce the area of aquatic organisms’ habitat, be harmful to the spawning, migration, and survival of aquatic organisms, reduce the interception of organic matter in floodplains, and increase the drought pressure of plants. The reservoir ecological operation of rivers with numerous reservoirs should be considered, joint reservoir dispatching schemes should be formulated for the study area so as to maximize the comprehensive benefits. This study provides a reference for water resources management and reservoir operation in Ganjiang River Basin. The next step is to use a habitat model to simulate the habitat of Ganjiang River Basin.

Sign in / Sign up

Export Citation Format

Share Document