scholarly journals Uncertainty analysis of monthly river flow modeling in consecutive hydrometric stations using integrated data-driven models

2021 ◽  
Author(s):  
Karim Amininia ◽  
Seyed Mahdi Saghebian
Keyword(s):  
Data Processing ◽  
Uncertainty Analysis ◽  
Mississippi River ◽  
River Flow ◽  
Ensemble Empirical Mode Decomposition ◽  
Multivariate Adaptive Regression Splines ◽  
Applied Model ◽  
Flood Warning ◽  
Mode Decomposition ◽  
Artificial Intelligence Models

Abstract The flow assessment in a river is of vital interest in hydraulic engineering for flood warning and evacuation measures. To operate water structures more efficiently, models that forecast river discharge are desired to be of high precision and certain degree of accuracy. Therefore, in this study, two artificial intelligence models, namely kernel extreme learning machine (KELM) and multivariate adaptive regression splines (MARS), were applied for the monthly river flow (MRF) modeling. For this aim, Mississippi river with three consecutive hydrometric stations was selected as case study. Using the previous MRF values during the period of 1950–2019, several models were developed and tested under two scenarios (i.e. modeling based on station's own data or previous station's data). Wavelet transform (WT) and ensemble empirical mode decomposition (EEMD) as data processing approaches were used for enhancing modeling capability. Obtained results indicated that the integrated models resulted in more accurate outcomes. Data processing enhanced the model's capability up to 25%. It was observed that the previous station's data could be applied successfully for MRF modeling when the station's own data were not available. The best-applied model dependability was assessed via uncertainty analysis, and an allowable degree of uncertainty was found in MRF modeling.

scholarly journals Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm

Energies ◽  
2019 ◽  
Vol 12 (8) ◽  
pp. 1416 ◽  
Author(s):  
Mohammad Rezaie-Balf ◽  
Niloofar Maleki ◽  
Sungwon Kim ◽  
Ali Ashrafian ◽  
Fatemeh Babaie-Miri ◽  
...  
Keyword(s):  
Solar Radiation ◽  
Search Algorithm ◽  
Ensemble Empirical Mode Decomposition ◽  
Multivariate Adaptive Regression Splines ◽  
Regression Splines ◽  
Mode Decomposition ◽  
Mars Model ◽  
Adaptive Regression ◽  
Adaptive Noise ◽  
Adaptive Regression Splines

The precise forecasting of daily solar radiation (DSR) is receiving prominent attention among thriving solar energy studies. In this study, three standalone models, including gene expression programing (GEP), multivariate adaptive regression splines (MARS), and self-adaptive MARS (SaMARS), were evaluated to forecast DSR. A SaMARS model was classified as MARS model when using the crow search algorithm (CSA). In addition, to overcome the limitations of the standalone models, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was employed to enhance the accuracy of DSR forecasting. Therefore, three hybrid models including CEEMDAN-GEP, CEEMDAN-MARS, and CEEMDAN-SaMARS were proposed to forecast DSR in Busan and Incheon stations in South Korea. The performance of proposed models were evaluated and affirmed that the accuracy of the CEEMDAN-SaMARS model (NSE = 0.878–0.883) outperformed CEEMDAN-MARS (NSE = 0.819–0.818), CEEMDAN-GEP (NSE = 0.873–0.789), SaMARS (NSE = 0.846–0.769), MARS (NSE = 0.819–0.758), and GEP (NSE = 0.814–0.755) models at both stations. Therefore, it can be concluded that the optimized CEEMDAN-SaMARS model significantly enhanced the accuracy of DSR forecasting compared to that of standalone models.

scholarly journals Deep Learning-Based Predictive Framework for Groundwater Level Forecast in Arid Irrigated Areas

Water ◽  
2021 ◽  
Vol 13 (18) ◽  
pp. 2558
Author(s):  
Wei Liu ◽  
Haijiao Yu ◽  
Linshan Yang ◽  
Zhenliang Yin ◽  
Meng Zhu ◽  
...  
Keyword(s):  
Feature Selection ◽  
Deep Learning ◽  
Uncertainty Analysis ◽  
Groundwater Level ◽  
Performance Metrics ◽  
Simulation Models ◽  
Northwest China ◽  
Ensemble Empirical Mode Decomposition ◽  
Mode Decomposition ◽  
Highly Nonlinear

An accurate groundwater level (GWL) forecast at multi timescales is vital for agricultural management and water resource scheduling in arid irrigated areas such as the Hexi Corridor, China. However, the forecast of GWL in these areas remains a challenging task owing to the deficient hydrogeological data and the highly nonlinear, non-stationary and complex groundwater system. The development of reliable groundwater level simulation models is necessary and profound. In this study, a novel ensemble deep learning GWL predictive framework integrating data pro-processing, feature selection, deep learning and uncertainty analysis was constructed. Under this framework, a hybrid model equipped with currently the most effective algorithms, including the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) for data decomposition, the genetic algorithm (GA) for feature selection, the deep belief network (DBN) model, and the quantile regression (QR) for uncertainty evaluation, denoted as CEEMDAN-GA-DBN, was proposed for the 1-, 2-, and 3-month ahead GWL forecast at three GWL observation wells in the Jiuquan basin, northwest China. The capability of the CEEMDAN-GA-DBN model was compared with the hybrid CEEMDAN-DBN and the standalone DBN model in terms of the performance metrics including R, MAE, RMSE, NSE, RSR, AIC and the Legates and McCabe’s Index as well as the uncertainty criterion including MPI and PICP. The results demonstrated the higher degree of accuracy and better performance of the objective CEEMDAN-GA-DBN model than the CEEMDAN-DBN and DBN models at all lead times and all the wells. Overall, the CEEMDAN-GA-DBN reduced the RMSE of the CEEMDAN-DBN and DBN models in the testing period by about 9.16 and 17.63%, while it improved their NSE by about 6.38 and 15.32%, respectively. The uncertainty analysis results also affirmed the slightly better reliability of the CEEMDAN-GA-DBN method than the CEEMDAN-DBN and DBN models at the 1-, 2- and 3-month forecast horizons. The derived results proved the ability of the proposed ensemble deep learning model in multi time steps ahead of GWL forecasting, and thus, can be used as an effective tool for GWL forecasting in arid irrigated areas.

scholarly journals Uncertainty Analysis of a 1D River Hydraulic Model with Adaptive Calibration

Water ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 561
Author(s):  
Mohammed Amine Bessar ◽  
Pascal Matte ◽  
François Anctil
Keyword(s):  
Uncertainty Analysis ◽  
Water Level ◽  
River Flow ◽  
Performance Metrics ◽  
Latin Hypercube Sampling ◽  
Hydraulic Model ◽  
Good Reliability ◽  
Flood Warning ◽  
Adaptive Calibration ◽  
Independent Events

Water level modeling is a critical component of flood warning systems. A high-quality forecast requires the development of a hydraulic model that reliably accounts for the main sources of uncertainty. In this paper, a 1D hydraulic model with adaptive flow-based calibration was developed. This calibration resulted in roughness-flow relationships that allow Manning coefficients to be updated as a function of river flow, to limit errors throughout the flood cycle. An uncertainty analysis is then conducted for independent events, considering as the main source of uncertainty the error in the estimated input flows (upstream and lateral), and in the calibrated roughness coefficients. A set of parameters is generated by Latin Hypercube Sampling (LHS) from the characterization of these errors to evaluate their propagation to the variables of interest, namely water level and flow. These are evaluated by performance metrics (scores) such as the reliability diagram and the continuous rank probability score (CRPS). The adaptive flow-based calibration considerably reduced the error of the 1D model and improved its performance over time and throughout the flood events. The uncertainty analysis resulted in consistent accuracy improvements over a deterministic simulation with gains of 20% to 32%, depending on the combined parameters. Good reliability is also reached for most stations, with resulting spreads and Root Mean Square Error (RMSE) close to one another. The proposed methodology has the potential to improve the descriptive capability of 1D river hydraulic models and to increase their reliability when included in forecasting systems.

scholarly journals A comparative study of wavelet- and empirical mode decomposition-based GPR models for river discharge relationship modeling at consecutive hydrometric stations

2021 ◽  
Author(s):  
Kiyoumars Roushangar ◽  
Masoumeh Chamani ◽  
Roghayeh Ghasempour ◽  
Hazi Mohammad Azamathulla ◽  
Farhad Alizadeh
Keyword(s):  
Empirical Mode Decomposition ◽  
Flow Characteristics ◽  
Ensemble Empirical Mode Decomposition ◽  
The State ◽  
Applied Model ◽  
River Stage ◽  
Mode Decomposition ◽  
Model Efficiency ◽  
Processing Techniques ◽  
State 1

Abstract River stage-discharge relationship has an important impact on modeling, planning, and management of river basins and water resources. In this study, the capability of Gaussian Process Regressions (GPR) kernel-based approach was assessed in predicting the daily river stage-discharge (RSD) relationship. Three successive hydrometric stations of Housatonic River were considered and based on the flow characteristics during the period of 2002–2006 several models were developed and tested via GPR. To enhance the applied model efficiency, two pre-processing techniques namely Wavelet Transform (WT) and Ensemble Empirical Mode Decomposition (EEMD) were used. Also, two states of the RSD modeling were investigated. In the state 1, each station's own data was used and in the state 2, the upstream stations’ datasets were used as input to model the RSD at downstream of the river. The single and integrated models results showed that the integrated WT- and EEMD-GPR models resulted in more accurate outcomes. Data processing enhanced the models capability between 25 and 40%. The results showed that the RSD modeling in the state 1 led to better results; however, when the stations’ own data were not available the integrated methods could be applied successfully for the RSD modeling using the previous stations’ data.

scholarly journals Analysis method of the cavitation vibration signals in poppet valve based on EEMD

2021 ◽  
Vol 13 (2) ◽  
pp. 168781402199811
Author(s):  
Beibei Li ◽  
Qiao Zhao ◽  
Huaiyi Li ◽  
Xiumei Liu ◽  
Jichao Ma ◽  
...  
Keyword(s):  
Ensemble Empirical Mode Decomposition ◽  
Center Frequency ◽  
Analysis Method ◽  
Vibration Signals ◽  
Poppet Valve ◽  
Mode Decomposition ◽  
Marginal Spectrum ◽  
Cavitation Intensity ◽  
Eemd Method ◽  
Peak Value

To study the vibration characteristics of the poppet valve induced by cavitation, the signal analysis method based on the ensemble empirical mode decomposition (EEMD) method was studied experimentally. The component induced by cavitation was separated from the vibration signals through the EEMD method. The results show that the IMF2 component has the largest amplitude and energy of all components. The root mean square (RMS) value, peak value of marginal spectrum, and center frequency of marginal spectrum of the IMF2 component were studied in detail. The RMS value and the peak value of the marginal spectrum decrease with a decrease of cavitation intensity. The center frequency of marginal spectrum is between 12 kHz and 20 kHz, and the center frequency first increases and then decreases with a decrease of cavitation intensity. The change rate of the center frequency also decreases with an increase of inlet pressure.

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

Sign in / Sign up

Export Citation Format

Share Document