scholarly journals Neural Network Model to Predict a Storm Surge

2009 ◽  
Vol 48 (1) ◽  
pp. 143-155 ◽  
Author(s):  
Marilia M. F. de Oliveira ◽  
Nelson Francisco F. Ebecken ◽  
Jorge Luiz Fernandes de Oliveira ◽  
Isimar de Azevedo Santos
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Sea Level ◽  
Storm Surge ◽  
Network Model ◽  
Neural Network Model ◽  
Tide Gauge ◽  
Low Frequency ◽  
Coastal Sea ◽  
The Relationship

Abstract The southeastern coast of Brazil is frequently affected by meteorological disturbances such as cold fronts, which are sometimes associated with intense extratropical cyclones. These disturbances cause oscillations on the sea surface, generating low-frequency motions. The relationship of these meteorologically driven forces in low frequency to the storm-surge event is investigated in this work. A method to predict coastal sea level variations related to meteorological events that use a neural network model (NNM) is presented here. Pressure and wind values from NCEP–NCAR reanalysis data and tide gauge time series from the Cananéia reference station in São Paulo State, Brazil, were used to analyze the relationship between these variables and to use them as input to the model. Meteorological influences in the sea level fluctuations can be verified by filtering the astronomical tide frequencies for periods lower than tidal cycles (periods higher than 24 h). Thus, a low-pass filter was applied in the tide gauge and meteorological time series for periods lower than tides to identify more readily the interactions between coastal sea level response and atmospheric-driven forces. Statistical analyses on time and frequency domain were used. Maxima correlations and coherence between the low-frequency sea level and meteorological series could be defined using the time lag of the NNM input variables. The model was tested for 6-, 12-, 18-, and 24-hourly forecasts, and the results were compared with filtered sea level values. The results show that this model is able to capture the effects of atmospheric and oceanic interactions. It can be considered to be an efficient model for predicting the nontidal residuals and can effectively complement the standard constant harmonic analysis model. A case study of a storm that impacted coastal areas of southeastern Brazil in March 1998 was analyzed and indicates that the neural network model can be effectively utilized in the Cananéia region.

An improved self-organizing incremental neural network model for short-term time-series load prediction

2021 ◽  
Vol 292 ◽  
pp. 116912
Author(s):  
Rong Wang Ng ◽  
Kasim Mumtaj Begam ◽  
Rajprasad Kumar Rajkumar ◽  
Yee Wan Wong ◽  
Lee Wai Chong
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Network Model ◽  
Neural Network Model ◽  
Load Prediction ◽  
Short Term ◽  
Self Organizing

Digital twin of the chip formation process

2020 ◽  
pp. 81-86
Author(s):  
Yu.G. Kabaldin ◽  
D.A. Shatagin ◽  
M.S. Anosov ◽  
A.M. Kuz'mishina
Keyword(s):  
Neural Network ◽  
Control System ◽  
Crystal Lattice ◽  
Network Model ◽  
Intelligent Control ◽  
Neural Network Model ◽  
Formation Process ◽  
Chip Formation ◽  
Intelligent Control System ◽  
The Relationship

The formation of chips during the processing of various materials was studied. The relationship between the type of chips, the type of crystal lattice of the material and the number of sliding systems is shown. A neural network model of chip formation is developed, which allows predicting the type of chips. An intelligent control system for the process of chip formation during cutting is proposed. Keywords: chip formation, crystal lattice, neural network model, type of chips. [email protected]

Prediction model for the mechanical properties of compacted poplar powder generated via hot-pressing

BioResources ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. 4947-4962
Author(s):  
Jin Yan ◽  
Jianan Liu ◽  
Liqiang Zhang ◽  
Zhili Tan ◽  
Haoran Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Network Model ◽  
Process Parameters ◽  
Neural Network Model ◽  
Hot Pressing ◽  
Process Conditions ◽  
Wood Powder ◽  
Single Factor ◽  
The Relationship

The influence of the process parameters on the mechanical properties of compact wood powder generated via hot-pressing was analyzed through a single-factor experiment. The mechanical properties exhibited a nonlinear trend relative to the process conditions of hot-pressed compact wood powder. The relationship models between the process parameters and the mechanical properties for the compact wood powder were established by applying a multiple regression analysis and neural network methods combined with data from an orthogonal array design. A comparison between experimental and predicted results was made to investigate the accuracy of the established models by applying several data groups among the single-factor experiments. The results showed that the accuracy of the neural network model in terms of predicting the mechanical properties was greater compared with the multiple regression model. This demonstrates that the established neural network model had a better prediction performance, and it can accurately map the relationship between the process conditions and the mechanical properties of the compact wood powder.

Performance Assessment of GNSS-R Polarimetric Observations for Sea Level Monitoring

2021 ◽  
Author(s):  
Mahmoud Rajabi ◽  
Mstafa Hoseini ◽  
Hossein Nahavandchi ◽  
Maximilian Semmling ◽  
Markus Ramatschi ◽  
...  
Keyword(s):  
Time Series ◽  
Circular Polarization ◽  
Sea Level ◽  
Tide Gauge ◽  
Satellite System ◽  
Sea Surface ◽  
Analysis Tool ◽  
Lower Accuracy ◽  
Coastal Sea ◽  
Global Navigation Satellite

<p>Determination and monitoring of the mean sea level especially in the coastal areas are essential, environmentally, and as a vertical datum. Ground-based Global Navigation Satellite System Reflectometry (GNSS-R) is an innovative way which is becoming a reliable alternative for coastal sea-level altimetry. Comparing to traditional tide gauges, GNSS-R can offer different parameters of sea surface, one of which is the sea level. The measurements derived from this technique can cover wider areas of the sea surface in contrast to point-wise observations of a tide gauge.  </p><p>We use long-term ground-based GNSS-R observations to estimate sea level. The dataset includes one-year data from January to December 2016. The data was collected by a coastal GNSS-R experiment at the Onsala space observatory in Sweden. The experiment utilizes three antennas with different polarization designs and orientations. The setup has one up-looking, and two sea-looking antennas at about 3 meters above the sea surface level. The up-looking antenna is Right-Handed Circular Polarization (RHCP). The sea-looking antennas with RHCP and Left-Handed Circular Polarization (LHCP) are used for capturing sea reflected Global Positioning System (GPS) signals. A dedicated reflectometry receiver (GORS type) provides In-phase and Quadrature (I/Q) correlation sums for each antenna based on the captured interferometric signal. The generated time series of I/Q samples from different satellites are analyzed using the Least Squares Harmonic Estimation (LSHE) method. This method is a multivariate analysis tool which can flexibly retrieve the frequencies of a time series regardless of possible gaps or unevenly spaced sampling. The interferometric frequency, which is related to the reflection geometry and sea level, is obtained by LSHE with a temporal resolution of 15 minutes. The sea level is calculated based on this frequency in six modes from the three antennas in GPS L1 and L2 signals.</p><p>Our investigation shows that the sea-looking antennas perform better compared to the up-looking antenna. The highest accuracy is achieved using the sea-looking LHCP antenna and GPS L1 signal. The annual Root Mean Square Error (RMSE) of 15-min GNSS-R water level time series compared to tide gauge observations is 3.7 (L1) and 5.2 (L2) cm for sea-looking LHCP, 5.8 (L1) and 9.1 (L2) cm for sea-looking RHCP, 6.2 (L1) and 8.5 (L2) cm for up-looking RHCP. It is worth noting that the GPS IIR block satellites show lower accuracy due to the lack of L2C code. Therefore, the L2 observations from this block are eliminated.</p>

Wavelet neural network model for river flow time series

2012 ◽  
Vol 165 (8) ◽  
pp. 425-439 ◽  
Author(s):  
Budu Krishna ◽  
Yellamelli Ramji Satyaji Rao ◽  
Purna Chandra Nayak
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Network Model ◽  
Neural Network Model ◽  
River Flow ◽  
Flow Time ◽  
Wavelet Neural Network

scholarly journals Predicting Wins, Losses and Attributes’ Sensitivities in the Soccer World Cup 2018 Using Neural Network Analysis

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3213 ◽  
Author(s):  
Amr Hassan ◽  
Abdel-Rahman Akl ◽  
Ibrahim Hassan ◽  
Caroline Sunderland
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Average Distance ◽  
Deep Understanding ◽  
The Neural Network ◽  
Testing Error ◽  
Training Error ◽  
Using Data ◽  
The Relationship

Predicting the results of soccer competitions and the contributions of match attributes, in particular, has gained popularity in recent years. Big data processing obtained from different sensors, cameras and analysis systems needs modern tools that can provide a deep understanding of the relationship between this huge amount of data produced by sensors and cameras, both linear and non-linear data. Using data mining tools does not appear sufficient to provide a deep understanding of the relationship between the match attributes and results and how to predict or optimize the results based upon performance variables. This study aimed to suggest a different approach to predict wins, losses and attributes’ sensitivities which enables the prediction of match results based on the most sensitive attributes that affect it as a second step. A radial basis function neural network model has successfully weighted the effectiveness of all match attributes and classified the team results into the target groups as a win or loss. The neural network model’s output demonstrated a correct percentage of win and loss of 83.3% and 72.7% respectively, with a low Root Mean Square training error of 2.9% and testing error of 0.37%. Out of 75 match attributes, 19 were identified as powerful predictors of success. The most powerful respectively were: the Total Team Medium Pass Attempted (MBA) 100%; the Distance Covered Team Average in zone 3 (15–20 km/h; Zone3_TA) 99%; the Team Average ball delivery into the attacking third of the field (TA_DAT) 80.9%; the Total Team Covered Distance without Ball Possession (Not in_Poss_TT) 76.8%; and the Average Distance Covered by Team (Game TA) 75.1%. Therefore, the novel radial based function neural network model can be employed by sports scientists to adapt training, tactics and opposition analysis to improve performance.

Sign in / Sign up

Export Citation Format

Share Document