Nonlinear Autoregressive Model (NARX) of Stationary Forbush Decrease Indices Based on Levenberg-Marquardt Feedback Algorithm

2018 ◽  
Vol 13 (S340) ◽  
pp. 323-324
Author(s):  
Sankar Narayan Patra ◽  
Subhash Chandra Panja ◽  
Amrita Prasad ◽  
Soumya Roy ◽  
Koushik Ghosh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Autoregressive Model ◽  
Forbush Decrease ◽  
Short Term ◽  
Levenberg Marquardt ◽  
Nonlinear Autoregressive Model ◽  
Feedback Algorithm ◽  
Short Term Prediction ◽  
Nonlinear Autoregressive

AbstractArtificial Neural Network based Nonlinear Autoregressive Model is designed to reconstruct and predict Forbush Decrease (FD) Data obtained from Izmiran, Russia. Result indicates that the model seems adequate for short term prediction of the FD data.

scholarly journals Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration

2019 ◽  
Vol 11 (9) ◽  
pp. 1071
Author(s):  
Minjoo Choi ◽  
Liyanarachchi Waruna Arampath De Silva ◽  
Hajime Yamaguchi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Sea Ice ◽  
Arctic Sea Ice ◽  
Short Term ◽  
Sea Ice Concentration ◽  
Arctic Sea ◽  
Ice Concentration ◽  
Short Term Prediction ◽  
Data Scheme

In this paper, we applied an artificial neural network (ANN) to the short-term prediction of the Arctic sea ice concentration (SIC). The prediction was performed using encoding and decoding processes, in which a gated recurrent unit encodes sequential sea ice data, and a feed-forward neural network model decodes the encoded input data. Because of the large volume of Arctic sea ice data, the ANN predicts the future SIC of each cell individually. The limitation of these singular predictions is that they do not use information from other cells. This results in low accuracy, particularly when there are drastic changes during melting and freezing seasons. To address this issue, we present a new data scheme including global and local SIC information, where the global information is represented by sea ice statistics. We trained ANNs using different data schemes and network architectures, and then compared their performances quantitatively and visually. The results show that, compared with a data scheme that uses only local sea ice information, the newly proposed scheme leads to a significant improvement in prediction accuracy.

Wavelet Estimation Method for Short-Term Prediction of Deep Pit Settlement

2012 ◽  
Vol 594-597 ◽  
pp. 2876-2879
Author(s):  
Jian Guo ◽  
Neng Hui Lin ◽  
Qi Mei Yang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Influencing Factor ◽  
Estimation Method ◽  
Short Term ◽  
Wavelet Estimation ◽  
Deep Pit ◽  
Actual Settlement ◽  
Artificial Neural Network Ann ◽  
Short Term Prediction

A wavelet estimation method is presented herein to estimate deep pit settlement. In this method, the pit settlement is decomposed into the trend settlement and the stochastic settlement by using Wavelet Analysis based on the characteristic of influencing factor. The model identifier is established by using artificial neural network (ANN), and trained to approximate the trend settlement. Then, the prediction controller developed could be applied for estimating the actual settlement. Finally, the verification examples show that the WIAN is an effective tool for predicting the pit settlement dynamically , high precision could be expected and achieved.

Sign in / Sign up

Export Citation Format

Share Document