scholarly journals Stochastic modeling of artificial neural networks for real-time hydrological forecasts based on uncertainties in transfer functions and ANN weights

2021 ◽  
Author(s):  
Shiang-Jen Wu ◽  
Chih-Tsung Hsu ◽  
Che-Hao Chang
Keyword(s):  
Real Time ◽  
Transfer Functions ◽  
Prediction Interval ◽  
Forecast Error ◽  
Correction Method ◽  
Study Data ◽  
Water Levels ◽  
Model Verification ◽  
The Real ◽  
Artificial Neural

Abstract This study proposes a stochastic artificial neural network (named ANN_GA-SA_MTF), in which the parameters of the multiple transfer functions considered are calibrated by the modified genetic algorithm (GA-SA), to effectively provide the real-time forecasts of hydrological variates and the associated reliabilities under the observation and predictions given (model inputs); also, the resulting forecasts can be adjusted through the real-time forecast-error correction method (RTEC_TS&KF) based on difference between real-time observations and forecasts. The observed 10-days rainfall depths and water levels (i.e., hydrological estimates) from 2008 to 2018 recorded within the Shangping sub-basin in northern Taiwan are adopted as the study data and their stochastic properties are quantified for simulating 1,000 sets of rainfall and water levels at 36 10-days periods as the training datasets. The results from the model verification indicate that the observed 10-days rainfall depths and water levels are obviously located at the prediction interval (i.e., 95% confidence interval), revealing that the proposed ANN_GA-SA_MTF model can capture the temporal behavior of 10-days rainfall depths and water levels within the study area. In spite of the resulting forecasts with an acceptable difference from the observation, their real-time corrections have evident agreement with the observations, namely, the resulting adjusted forecasts with high accuracy.

scholarly journals Stochastic Modeling for Estimating Real-Time Inundation Depths at Roadside IoT Sensors Using the ANN-Derived Model

Water ◽  
2021 ◽  
Vol 13 (21) ◽  
pp. 3128
Author(s):  
Shiang-Jen Wu ◽  
Chih-Tsu Hsu ◽  
Che-Hao Chang
Keyword(s):  
Real Time ◽  
Transfer Functions ◽  
High Reliability ◽  
Correction Method ◽  
Water Levels ◽  
Lead Times ◽  
Generation Model ◽  
Inundation Depth ◽  
Simulated Rain ◽  
Northern Taiwan

This paper aims to develop a stochastic model (SM_EID_IOT) for estimating the inundation depths and associated 95% confidence intervals at the specific locations of the roadside water-level gauges, i.e., Internet of Things (IoT) sensors under the observed water levels/rainfalls and the precipitation forecasts given. The proposed SM_EID_IOT model is an ANN-derived one, a modified artificial neural network model (i.e., the ANN_GA-SA_MTF) in which the associated ANN weights are calibrated via a modified genetic algorithm with a variety of transfer functions considered. To enhance the reliability and accuracy of the proposed SM_EID_IOT model in the estimations of the inundation depths at the IoT sensors, a great number of the rainfall induced flood events as the training and validation datasets are simulated by the 2D hydraulic dynamic (SOBEK) model with the simulated rain fields via the stochastic generation model for the short-term gridded rainstorms. According to the results of model demonstration, Nankon catchment, located in northern Taiwan, the proposed SM_EID_IOT model can estimate the inundation depths at the various lead times with high reliability in capturing the validation datasets. Moreover, through the integrated real-time error correction method integrated with the proposed SM_EID_IOT model, the resulting corrected inundation-depth estimates exhibit a good agreement with the validated ones in time under an acceptable bias.

Design and Application of Aeolian Vibration Monitoring System for Overhead Transmission Line

2012 ◽  
Vol 239-240 ◽  
pp. 456-461
Author(s):  
Bu Sheng Tong ◽  
Yu Xiang Lv ◽  
Bei Ge Yang ◽  
Hui Xue ◽  
Shan Zhi
Keyword(s):  
Transmission Line ◽  
Real Time ◽  
Monitoring System ◽  
Theoretical Models ◽  
Correction Method ◽  
Fatigue Tests ◽  
Least Square ◽  
Vibration Monitoring ◽  
The Real ◽  
Aeolian Vibration

Aim at the shortage of traditional Aeolian vibration fatigue tests and theoretical models for transmission line, the Aeolian vibration monitoring system of transmission line based on the ZigBee wireless network was designed. The system transfer real-time field data of meteorological factors, tension of conductor and acceleration of monitoring nodes to background computer. The line vibration curve integrated directly from the acceleration sensor recorded data will present a serious problem of baseline drift. Therefore, based on least-square theory, a new baseline correction method is proposed to eliminate effect on drifts, and then obtain distortion less vibration curve of transmission line by twice integrations. The system running results show that track fitted with monitoring data is in good agreement with the real recorded trajectory. The system can satisfy the needs of the real time monitoring on transmission line site and be well applied to the calculation of conductor fatigue damage.

scholarly journals Multi-Time Scale Rolling Economic Dispatch for Wind/Storage Power System Based on Forecast Error Feature Extraction

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 2124 ◽  
Author(s):  
Li Han ◽  
Rongchang Zhang ◽  
Xuesong Wang ◽  
Yu Dong
Keyword(s):  
Power System ◽  
Real Time ◽  
Wind Power ◽  
Power Unit ◽  
Time Scale ◽  
Forecast Error ◽  
Thermal Power ◽  
Time Error ◽  
The Real ◽  
The Impact

This paper looks at the ability to cope with the uncertainty of wind power and reduce the impact of wind power forecast error (WPFE) on the operation and dispatch of power system. Therefore, several factors which are related to WPFE will be studied. By statistical analysis of the historical data, an indicator of real-time error based on these factors is obtained to estimate WPFE. Based on the real-time estimation of WPFE, a multi-time scale rolling dispatch model for wind/storage power system is established. In the real-time error compensation section of this model, the previous dispatch plan of thermal power unit is revised according to the estimation of WPFE. As the regulating capacity of thermal power unit within a short time period is limited, the estimation of WPFE is further compensated by using battery energy storage system. This can not only decrease the risk caused by the wind power uncertainty and lessen wind spillage, but also reduce the total cost. Thereby providing a new method to describe and model wind power uncertainty, and providing economic, safe and energy-saving dispatch plan for power system. The analysis in case study verifies the effectiveness of the proposed model.

scholarly journals Image Tracking for the High Similarity Drug Tablets Based on Light Intensity Reflective Energy and Artificial Neural Network

2014 ◽  
Vol 2014 ◽  
pp. 1-19 ◽  
Author(s):  
Zhongwei Liang ◽  
Liang Zhou ◽  
Xiaochu Liu ◽  
Xiaogang Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Light Intensity ◽  
Real Time ◽  
High Speed ◽  
High Similarity ◽  
Image Frame ◽  
The Real ◽  
Image Tracking ◽  
Artificial Neural

It is obvious that tablet image tracking exerts a notable influence on the efficiency and reliability of high-speed drug mass production, and, simultaneously, it also emerges as a big difficult problem and targeted focus during production monitoring in recent years, due to the high similarity shape and random position distribution of those objectives to be searched for. For the purpose of tracking tablets accurately in random distribution, through using surface fitting approach and transitional vector determination, the calibrated surface of light intensity reflective energy can be established, describing the shape topology and topography details of objective tablet. On this basis, the mathematical properties of these established surfaces have been proposed, and thereafter artificial neural network (ANN) has been employed for classifying those moving targeted tablets by recognizing their different surface properties; therefore, the instantaneous coordinate positions of those drug tablets on one image frame can then be determined. By repeating identical pattern recognition on the next image frame, the real-time movements of objective tablet templates were successfully tracked in sequence. This paper provides reliable references and new research ideas for the real-time objective tracking in the case of drug production practices.

Research of Surrounding Rock Classification Correction Method

2015 ◽  
Vol 777 ◽  
pp. 74-84
Author(s):  
Hong Liang Deng ◽  
Si Miao Wang ◽  
Ge Chen ◽  
Yang Guo
Keyword(s):  
Real Time ◽  
Measurement Data ◽  
Stable State ◽  
Principal Component ◽  
Correction Method ◽  
Surrounding Rock ◽  
Design Phase ◽  
Rock Classification ◽  
The Real ◽  
Tunnel Convergence

At present, both at home and abroad of tunnel surrounding rock classification methods and standards are all aimed at tunnel survey and design phase. It is the cause of that surrounding rock classification are very different between design phase and tunnel construction because of the limits of investigation techniques and geological data. It is the key to the real-time construction design problem that Sentenced to a stable state of surrounding rock based on the monitoring data. This paper determines the influence factors of tunnel convergence value clearance and obtained the tunnel convergence value clearance of principal component factor and power based on the statistical analysis of a lot of tunnel monitoring measurement data. It is put forward correction formula of dynamic classification of surrounding rock according to the theory of probability and statistics. The results show that based on the real-time monitoring of tunnel surrounding rock classification method is quite coincident with the actual situation of tunnel excavation in engineering applications.

scholarly journals Application of Artificial Neural Networks for Accuracy Enhancements of Real-Time Flood Forecasting in the Imjin Basin

Water ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 1626 ◽  
Author(s):  
Aida Jabbari ◽  
Deg-Hyo Bae
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Real Time ◽  
Bias Correction ◽  
Weather Prediction ◽  
Statistical Error ◽  
Flood Forecasting ◽  
The Real ◽  
Model Complex ◽  
Artificial Neural

Hydrometeorological forecasts provide future flooding estimates to reduce damages. Despite the advances and progresses in Numerical Weather Prediction (NWP) models, they are still subject to many uncertainties, which cause significant errors forecasting precipitation. Statistical postprocessing techniques can improve forecast skills by reducing the systematic biases in NWP models. Artificial Neural Networks (ANNs) can model complex relationships between input and output data. The application of ANN in water-related research is widely studied; however, there is a lack of studies quantifying the improvement of coupled hydrometeorological model accuracy that use ANN for bias correction of real-time rainfall forecasts. The aim of this study is to evaluate the real-time bias correction of precipitation data, and from a hydrometeorological point of view, an assessment of hydrological model improvements in real-time flood forecasting for the Imjin River (South and North Korea) is performed. The comparison of the forecasted rainfall before and after the bias correction indicated a significant improvement in the statistical error measurement and a decrease in the underestimation of WRF model. The error was reduced remarkably over the Imjin catchment for the accumulated Mean Areal Precipitation (MAP). The performance of the real-time flood forecast improved using the ANN bias correction method.

scholarly journals Hydrodynamic and Wave Responses During Storm Surges on the Southern Brazilian Coast: A Real-Time Forecast System

Water ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3397
Author(s):  
Arslaan Khalid ◽  
Andre de Souza de Lima ◽  
Felicio Cassalho ◽  
Tyler Miesse ◽  
Celso Ferreira
Keyword(s):  
Water Level ◽  
Real Time ◽  
Extreme Weather ◽  
Coastal Areas ◽  
Water Levels ◽  
Coastal Communities ◽  
Economic Losses ◽  
Forecast System ◽  
The Real ◽  
Daily Weather

Coastal flooding is a global phenomenon that results in severe economic losses, threatens lives, and impacts coastal communities worldwide. While recent developments in real-time flood forecasting systems provide crucial information to support coastal communities during coastal disasters, there remains a challenge to implement such systems in data-poor regions. This study demonstrates an operational real-time coupled surge wave guidance system for the coastal areas of Southern Brazil. This system is based on the recently developed integrated flood (iFLOOD) model, which utilizes the coupled hydrodynamic and phase-averaged ADCIRC–SWAN wave numerical model, driven by astronomical tides and atmospheric forcing from the Global Forecast System (GFS). This numerical modeling framework can simulate water levels and waves with a lead time of 84 h. A version of the coupled ADCIRC–SWAN model calibrated for Brazil, i.e., iFLOOD-Brazil, was operationally implemented (i.e., twice a day) over a period of 4 months (April to September 2020) for normal daily weather validation, as well as during a recent “bomb” cyclone that strongly impacted the southern coast of the country in June 2020. The real-time water levels and waves forecasted by iFLOOD-Brazil showed promising results against observations, with root mean square error (RMSE) values of 0.32 m and 0.68 m, respectively, for normal daily weather. Additionally, the RMSE values were 0.23 m for water levels and 1.55 m for waves during extreme weather, averaged over eight water level and two wave recording stations. In order to improve real-time predictions, a bias correction scheme was introduced and was shown to improve the water level and wave forecasts by removing the known systematic errors resulting from underestimation of astronomical tides and inadequate initial boundary conditions. The bias-corrected forecasts showed significant improvements in forecasted wave heights (0.47 m, 0.35 m) and water levels (0.17 m, 0.28 m) during daily and extreme weather conditions. The real-time iFLOOD-Brazil forecast system is the first step toward developing an accurate prediction model to support effective emergency management actions, storm mitigation, and planning in order to protect these economically valuable and socially vulnerable coastal areas.

scholarly journals Methods of the Real-time Runoff Account under the Conditions of the Bed Silting (the Matyra River in the village of Krutoye range as a study case)

2017 ◽  
Author(s):  
Keyword(s):  
Real Time ◽  
Discharge Rate ◽  
Water Discharge ◽  
Water Levels ◽  
Accounting Data ◽  
The Real ◽  
Discharge Rates ◽  
Auto Correlation Function ◽  
The Village ◽  
Adequate Reliability

This paper presents the updated method of the real-time runoff calculation in conditions of river channel silting based on the method of optimal extrapolation. The Matyra river used as the example. The results of the analysis of the data obtained by observations of the Matyra River water regime during the period from 1994 to 2013 have been presented. We have analyzed all specific features of the hydrologic regime characteristics alterations under the influence of meteorological factors over the periods of the bed silting. The proposed decisions for real-time runoff account employ basic many-year dependence of the water discharge rates on water levels that have been exactly defined by the latest measurements of the water discharge rate through introduction of corrections that characterize changing of the bed passage ability of the year under consideration. These changes are calculated by the method of optimal extrapolation of the series of relative deviations from many-year water discharge curve calculated over the year under consideration. Assessment of the statistic characteristics of the relative deviation series such as auto-correlation function, dispersion and expectation value has been done to calculate weight coefficients in the optimal extrapolation formulas. Assessment of the proposals effectiveness has been carried out on the basis of the data of realtime and regime runoff accounting over the 2008-2013 period. Root mean square deviations from the regime accounting data were 5–10 %. The obtained results enable to make a conclusion on adequate reliability of the real-time runoff accounting data obtained with the use of the developed methods and to recommend it for real-time accounting of the small and medium-sized considerably silted rivers runoff.

Sign in / Sign up

Export Citation Format

Share Document