A procedure for the selection of neural models of dynamical processes is presented. It uses statistical tests at various levels of model reduction, in order to provide optimal tradeoffs between accuracy and parsimony. The efficiency of the method is illustrated by the modeling of a highly non-linear NARX process.

Freshwater supply is a major challenge in regions with limited water resources and extremely arid climatic conditions. The objective of this study to model the monthly demand Kuwait using nonlinear autoregressive exogenous input (NARX) neural network approach. country lacks conventional surface characterized by climate. In addition, it has one fastest growing populations. study, linear detrendi...

System identification uses measurements of a dynamic system's input and output to reconstruct mathematical model for that system. These can be mechanical, electrical, physiological, among others. Since most the systems around us exhibit some form nonlinear behavior, system techniques are tools will help gain better understanding our surroundings potentially let improve their performance. One is...

The NARX network is a dynamical neural architecture commonly used for inputoutput modeling of nonlinear dynamical systems. When applied to time series prediction, the NARX network is designed as a feedforward Time Delay Neural Network (TDNN), i.e. without the feedback loop of delayed outputs, reducing substantially its predictive performance. In this paper, we show that the original architectur...

Recurrent neural networks (RNNs) have shown success for many sequence-modeling tasks, but learning long-term dependencies from data remains difficult. This is often attributed to the vanishing gradient problem, which shows that gradient components relating a loss at time t to time t− τ tend to decay exponentially with τ . Long short-term memory (LSTM) and gated recurrent units (GRUs), the most ...

In our work, we compared two approaches for predicting changes in the concentration of one main greenhouse gases - methane. The study is based on surface methane data obtained by monitoring dynamics major Arctic Island Belyy, Russia. We used a nonlinear autoregressive neural network with an external input (NARX), and vector regression model. An artificial type NARX was more accurate changes.

The problem of chaotic time series prediction is studied in various disciplines now including engineering, medical and econometric applications. Chaotic time series are the output of a deterministic system with positive Liapunov exponent. A time series prediction is a suitable application for a neuronal network predictor. The NN approach to time series prediction is non-parametric, in the sense...

This chapter focuses on comparing the forecasting ability of the backpropagation neural network (BPNN) and the nonlinear autoregressive moving average with exogenous inputs (NARX) network trained with different algorithms; namely the quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), conjugate gradient (Fletcher-Reeves update, Polak-Ribiére update, Powell-Beale restart), and Levenberg-Marqu...

Rainfall prediction is one of the most challenging task faced by researchers over years. Many machine learning and AI based algorithms have been implemented on different datasets for better purposes, but there not a single solution which perfectly predicts rainfall. Accurate still remains question to researchers. We offer learning-based comparison evaluation rainfall models Kashmir province. Bo...