NARX Network Research Articles

Modeling the Relationship of Precipitation and Water Level Using Grid Precipitation Products with a Neural Network Model

Modeling the relationship between precipitation and water level is of great significance in the prevention of flood disaster. In recent years, the use of machine learning algorithms for precipitation–water level prediction has attracted wide attention in flood forecasting and other fields; however, a clear method to model the relationship of precipitation and water level using grid precipitation products with a neural network model is lacking. The issues of the method include how to select a neural network model, as well as how to influence the modeling results with different types and resolutions of remote sensing data. The purpose of this paper is to provide some findings for the issues. We used the back-propagation (BP) neural network and a nonlinear autoregressive exogenous model (NARX) time series network to model the relationship between precipitation and water level, respectively. The water level of Pingshan hydrographic station at a catchment area in the Jinsha River Basin was simulated by the two network models using three different grid precipitation products. The results showed that when the ground station data are missing, the grid precipitation product is a good alternative to construct the precipitation–water level relationship. In addition, using the NARX network as a model fitting network using extra inputs was better than using the BP neural network; the Nash efficiency coefficients of the former were all higher than 97%, while the latter were all lower than 94%. Furthermore, the input of grid products with different spatial resolutions has little significant effect on the modeling results of the model.

A Nonlinear Autoregressive Modeling Approach for Forecasting Groundwater Level Fluctuation in Urban Aquifers

The application of a nonlinear autoregressive modeling approach with exogenous input (NARX) neural networks for modeling groundwater level fluctuation has been examined by several researchers. However, the suitability of NARX in modeling groundwater level dynamics in urbanized and arid aquifer systems has not been comprehensively investigated. In this study, a NARX-based modeling approach is presented to establish a robust water management tool to aid urban water managers in controlling the development of shallow water tables induced by artificial recharge activity. Temperature data series are used as exogenous inputs for the NARX network, as they better reflect the intensity of artificial recharge activities, such as excessive lawns irrigation. Input delays and feedback delays for the NARX networks are determined based on the autocorrelation and cross-correlation analyses of detrended groundwater levels and monthly temperature averages. The validation of the proposed approach is assessed through a rolling validation procedure. Four observation wells in Kuwait City are selected to test the applicability of the proposed approach. The results showed the superiority of the NARX-based approach in modeling groundwater levels in such an urbanized and arid aquifer system, with coefficient of determination (R2) values ranging between 0.762 and 0.994 in the validation period. Comparison with other statistical models applied to the same study area shows that NARX models presented here reduced the mean absolute error (MAE) of groundwater levels forecasts by 50%. The findings of this paper are promising and provide a valuable tool for the urban city planner to assist in controlling the problem of shallow water tables for similar climatic and aquifer systems.

An Optimal NARX Neural Network Identification Model for a Magnetorheological Damper With Force-Distortion Behavior

This paper presents an optimal NARX neural network identification model for a magnetorheological (MR) damper with the force-distortion behavior. An intensive experimental study is conducted for designing the NARX network architecture to enhance modeling accuracy and availability, and the activation function selection, weights and biases of the selected network are optimized by differential evolution algorithm (DEA). Different experimental training and validation samples are used for network training. The prediction capability of the optimal NARX model is verified by new measured test data. The test and comparative results show that the optimal NARX network model can satisfactorily emulate the dynamic behavior of MR damper and effectively capture its distortion behavior occurred with the increased current. The developed inverse NARX network model can effectively estimate the required current and track desired damping force. Moreover, the effects of different noise disturbance on the NARX network model performance are analyzed, and the model error varies slightly with a small noise disturbance. The accuracy of the results supports that the use of this modelling technique for identifying irregular nonlinear models of MR damper and similar devices.

Neuro-fuzzy modeling and prediction of summer precipitation with application to different meteorological stations

Research community has a growing interest in neural networks because of their practical applications in many fields for accurate modeling and prediction of the complex behavior of systems arising from engineering, economics, business, financial and metrological fields. Artificial neural networks (ANN) are very flexible function approximations tool used as universal modeling based on the separating of the past dynamics into clusters, in which we construct local models to capture the potential growth of the series depends on the previously known values. In this study, rain data of five major cities of Sindh province of Pakistan is considered, and summer rainfall of these five synoptic stations are statistically evaluated for prediction. The nonlinear autoregressive network with exogenous inputs (NARX) model for a time series is analyzed to evaluate the pattern of precipitation. We train a highly nonlinear NARX network model from randomly generated initial weights that converged to the best solution with the help of the Levenberg-Marquardt algorithm. A multi-step ahead NARX response time predictor is developed for rain forecasting. The performance of the NARX model is viable to capture nonlinear behavior with a high value of correlation coefficient R ranging from 0.70 to 0.99 for different synoptic stations. The results calculated using the proposed NARX neural network time series approach are accurate and reliable based on the coefficient of correlation and mean square error indices for rainfall forecasting.

Probabilistic electricity price forecasting with NARX networks: Combine point or probabilistic forecasts?

Recent electricity price forecasting studies have shown that decomposing a series of spot prices into a long-term trend-seasonal and a stochastic component, modeling them independently and then combining their forecasts, can yield more accurate point predictions than an approach in which the same regression or neural network model is calibrated to the prices themselves. Here, considering two novel extensions of this concept to probabilistic forecasting, we find that (i) efficiently calibrated non-linear autoregressive with exogenous variables (NARX) networks can outperform their autoregressive counterparts, even without combining forecasts from many runs, and that (ii) in terms of accuracy it is better to construct probabilistic forecasts directly from point predictions. However, if speed is a critical issue, running quantile regression on combined point forecasts (i.e., committee machines) may be an option worth considering. Finally, we confirm an earlier observation that averaging probabilities outperforms averaging quantiles when combining predictive distributions in electricity price forecasting.

Short term load forecast of Kano zone using artificial intelligent techniques

<span lang="EN-MY">Load forecast provides useful information for effective electricity dispatch, planning for future expansion and significantly enhances operational efficiency. Conventional techniques yield unsatisfactory forecast which results in high energy losses and in turn leads to high operational cost and suppressed electricity demand. This paper presents hybrid neuro fuzzy (HNF) and Nonlinear Auto-Regressive with eXogeneous input (NARX) neural network for the short term load prediction of Kano region Nigeria. Simulation results obtained demonstrated the generalization capabilities of the models in predicting the load accurately well by achieving MAPE of 0.025% and 0.6551% for the HNF model and NARX network model respectively. The models could serve as promising tool for predicting Kano Zone load demand</span>.

A new temporal prediction method of grazing pressure based on normalized difference vegetation index and precipitation using nonlinear autoregressive with exogenous input networks

AbstractRestoration of natural vegetation in arid and semi‐arid grasslands is facing severe challenges. The vegetation is easy to lose their vitality, resulting in the loss of the cover in natural grasslands under the high grazing pressure. To address this situation, this paper proposes a novel method for accurately predicting the grazing pressure using the nonlinear autoregressive with exogenous input (NARX) network based on the remote sensing data of normalized difference vegetation index (NDVI) and precipitation. The proposed method uses the NARX networks to predict the temporal variations of the NDVI with respect to the precipitation. The grazing pressure can be thus calculated using the predicted values of the NDVI. For practical application, this study investigated an arid and semi‐arid grassland with heavy grazing pressure in Hulunbuir, China. The results demonstrate that the proposed method can provide an accurate prediction of the grazing pressure (mean absolute error 0.103, root‐mean‐square error 0.122, mean absolute percentage error 8.36% and coefficient of determination 0.899 at the confidence interval of 95%). In addition, the predicted values of the grazing pressure in the study area during the years from 2016 to 2020 can be obtained using the proposed method. The proposed method can obtain a good prediction of the grazing pressure, which can be further used as a guidance for the rangeland managers to reduce the occurrence of the overgrazing.

Lithium-Ion batteries modeling and state of charge estimation using Artificial Neural Network

<span class="fontstyle0">In This paper, we propose an effective and online technique for modeling nd State of Charge (SoC) estimation of Lithium-Ion (Li-Ion) batteries using Feed Forward Neural Networks(FFNN) and Nonlinear Auto Regressive model with eXogenous input(NARX). The both Artificial Neural Network (ANN) are rained using the data collected from the batterycharging and discharging pro ess. The NARX network finds the needed battery model, where the input ariables are the battery terminal voltage, SoC at the previous sample, and the urrent, temperature at the present sample. The proposed method is imple mented on a Li-Ion battery cell to estimate online SoC. Simulation results show good estimation of the<br />SoC.</span>

Toward Better PV Panel’s Output Power Prediction; a Module Based on Nonlinear Autoregressive Neural Network with Exogenous Inputs

Much work has been carried out for modeling the output power of photovoltaic panels. Using artificial neural networks (ANNS), one could efficiently model the output power of heterogeneous photovoltaic (HPV) panels. However, due to the existing different types of artificial neural network implementations, it has become hard to choose the best approach to use for a specific application. This raises the need for studies that develop models using the different neural networks types and compare the efficiency of these different types for that specific application. In this work, two neural network types, namely, the nonlinear autoregressive network with exogenous inputs (NARX) and the deep feed-forward (DFF) neural network, have been developed and compared for modeling the maximum output power of HPV panels. Both neural networks have four exogenous inputs and two outputs. Matlab/Simulink is used in evaluating the proposed two models under a variety of atmospheric conditions. A comprehensive evaluation, including a Diebold-Mariano (DM) test, is applied to verify the ability of the proposed networks. Moreover, the work further investigates the two developed neural networks using their actual implementation on a low-cost microcontroller. Both neural networks have performed very well; however, the NARX model performance is much better compared with DFF. Using the NARX network, a prediction of PV output power could be obtained, with half the execution time required to obtain the same prediction with the DFF neural network, and with accuracy of ±0.18 W.

Control Oriented Prediction of Driver Brake Intention and Intensity Using a Composite Machine Learning Approach

Driver perception, decision, and control behaviors are easily affected by traffic conditions and driving style, showing the tendency of randomness and personalization. Brake intention and intensity are integrated and control-oriented parameters that are crucial to the development of an intelligent braking system. In this paper, a composite machine learning approach was proposed to predict driver brake intention and intensity with a proper prediction horizon. Various driving data were collected from Controller Area Network (CAN) bus under a real driving condition, which mainly contained urban and rural road types. ReliefF and RReliefF (they don’t have abbreviations) algorithms were employed as feature subset selection methods and applied in a prepossessing step before the training. The rank importance of selected predictors exhibited different trends or even negative trends when predicting brake intention and intensity. A soft clustering algorithm, Fuzzy C-means, was adopted to label the brake intention into categories, namely slight, medium, intensive, and emergency braking. Data sets with misplaced labels were used for training of an ensemble machine learning method, random forest. It was validated that brake intention could be accurately predicted 0.5 s ahead. An open-loop nonlinear autoregressive with external input (NARX) network was capable of learning the long-term dependencies in comparison to the static neural network and was suggested for online recognition and prediction of brake intensity 1 s in advance. As system redundancy and fault tolerance, a close-loop NARX network could be adopted for brake intensity prediction in the case of possible sensor failure and loss of CAN message.

Wavelet-based features for prognosis of degradation in rolling element bearing with non-linear autoregressive neural network

ABSTRACT In rotary machine, the frequently failure component is the rolling element bearing (REBs).The timely identifying the potential fault can prevent the breakdown and failure of rotary machine. A health assessment model based on Non-Linear Autoregressive Neural Network along with exponential value of Health Indicator (HIE) is proposed in this paper. The prognoses of bearing degradation estimates as: In first step, the friction torque transducer used to acquire vibration signal over the lifetime of bearing. After that, in second step, useful features are extracted after the processing of signals through continues wavelet transform (CWT). Then, exponential method is applied to remove the shortcomings into feature vectors. Finally, HIE features as input to the network; the prediction of bearing degradation is performed using optimal NAR and NARX network. An experimental result clarified that the performance of NARX network is better for the prediction of degradation. Outperform application of proposed method and conformation of degree of accuracy; it is compared with the published literature. The proposed methodology is more effective for a dataset of seeded defect and accelerated life test. The results indicate this methodology signifies the actual situation well and is able to precisely and efficiently predict the bearing degradation. Abbreviations: Bearing dynamics, Prognostics, Nonlinear Autoregressive (NAR) network, Nonlinear Autoregressive with exogenous inputs (NARX) network,Continuous wavelet transform (CWT)

A Multi-Sourced Data Retrodiction of Remotely Sensed Terrestrial Water Storage Changes for West Africa

Remotely sensed terrestrial water storage changes (TWSC) from the past Gravity Recovery and Climate Experiment (GRACE) mission cover a relatively short period (≈15 years). This short span presents challenges for long-term studies (e.g., drought assessment) in data-poor regions like West Africa (WA). Thus, we developed a Nonlinear Autoregressive model with eXogenous input (NARX) neural network to backcast GRACE-derived TWSC series to 1979 over WA. We trained the network to simulate TWSC based on its relationship with rainfall, evaporation, surface temperature, net-precipitation, soil moisture, and climate indices. The reconstructed TWSC series, upon validation, indicate high skill performance with a root-mean-square error (RMSE) of 11.83 mm/month and coefficient correlation of 0.89. The validation was performed considering only 15% of the available TWSC data not used to train the network. More so, we used the total water content changes (TWCC) synthesized from Noah driven global land data assimilation system in a simulation under the same condition as the GRACE data. The results based on this simulation show the feasibility of the NARX networks in hindcasting TWCC with RMSE of 8.06 mm/month and correlation coefficient of 0.88. The NARX network proved robust to adequately reconstruct GRACE-derived TWSC estimates back to 1979.

Short Term Residential Load Forecasting: An Improved Optimal Nonlinear Auto Regressive (NARX) Method with Exponential Weight Decay Function

The advancement in electrical load forecasting techniques with new algorithms offers reliable solutions to operators for operational cost reduction, optimum use of available resources, effective power management, and a reliable planning process. The focus is to develop a comprehensive understanding regarding the forecast accuracy generated by employing a state of the art optimal autoregressive neural network (NARX) for multiple, nonlinear, dynamic, and exogenous time varying input vectors. Other classical computational methods such as a bagged regression tree (BRT), an autoregressive and moving average with external inputs (ARMAX), and a conventional feedforward artificial neural network are implemented for comparative error assessment. The training of the applied method is realized in a closed loop by feeding back the predicted results obtained from the open loop model, which made the implemented model more robust when compared with conventional forecasting approaches. The recurrent nature of the applied model reduces its dependency on the external data and a produced mean absolute percentage error (MAPE) below 1%. Subsequently, more precision in handling daily grid operations with an average improvement of 16%–20% in comparison with existing computational techniques is achieved. The network is further improved by proposing a lightning search algorithm (LSA) for optimized NARX network parameters and an exponential weight decay (EWD) technique to control the input error weights.

Wave prediction using wave rider position measurements and NARX network in wave energy conversion

Several control methods of wave energy converters (WECs) need prediction in the future of wave surface elevation. Prediction of wave surface elevation can be performed using measurements of surface elevation at a location ahead of the controlled WEC in the upcoming wave. Artificial neural network (ANN) is a robust data-learning tool, and is proposed in this study to predict the surface elevation at the WEC location using measurements of wave elevation at ahead located sensor (a wave rider buoy). The nonlinear autoregressive with exogenous input network (NARX NN) is utilized in this study as the prediction method. Simulations show promising results for predicting the wave surface elevation. Challenges of using real measurements data are also discussed in this paper.

SOC estimation for lithium batteries based on the full parallel nonlinear autoregressive neural network with external inputs

Lithium-ion batteries are the core element in electric-vehicle systems. Because they provide a power source for the entire electric vehicle, their state of charge (SOC) is crucial to ensure the proper operation of the vehicle. Thus, a more precise estimate of the SOC should significantly improve the safety and utility of these batteries. Toward this end, we propose herein novel nonlinear autoregressive with exogenous input (NARX) and full-parallel (dual-close loop) structure NARX (FPNARX) networks to overcome the disadvantage of the traditional series-parallel (open-closed loop) structure NARX (SPNARX) network for estimating the SOC. To test the performance of the FPNARX network, we use the dynamic stress test and the urban dynamometer driving schedule discharge profiles in battery-discharge experiments. Furthermore, feed-forward neural networks and other time-series neural networks, including the time-delay neural network and SPNARX, are also implemented for the same experiments. The experimental results show that the time-series networks can estimate the SOC more precisely than the feed-forward network under non-constant-current discharge. Moreover, the applicability of the time-series networks depends on the current amplitude and frequency. However, the FPNARX network always gives the best results.

Evaluation of Seasonally Classified Inputs for the Prediction of Daily Groundwater Levels: NARX Networks Vs Support Vector Machines

Farmers and stakeholders who use groundwater for irrigation need efficient and cost-effective tools to support sustainable crop production. The variation of groundwater levels at local scale and its continuous use for agriculture intensifies the demand for reliable groundwater information. However, groundwater levels are very dynamic and difficult to predict under traditional modeling approaches, and manual monitoring of wells is costly and time-consuming. Simplified but powerful machine learning models represent a practical alternative to support groundwater management decisions at the farm scale. The predictive capacity of a nonlinear autoregressive with exogenous inputs (NARX) artificial neural network (ANN) and a support vector regression (SVR) trained with a radial basis function (RBF) algorithm were evaluated for an irrigation well located in a highly productive agricultural region in the southeastern USA. We used separately multiple years of daily historical time series classified by summer (withdrawal) and winter (recharge) seasons and evaluated the impacts of this division in the models’ predictive capability. Results showed that SVR had a better modeling performance based on the mean squared error (MSE) and prediction trend for both seasons. In addition, our study suggests that the prediction of daily levels with input time series classified by seasons provides higher accuracy than using the entire withdrawal and recharge periods as a whole. Results also indicate that the recharge season becomes a linear problem, which substantially reduces the SVR modeling computational requirements. The application of our proposed modeling approach in the management of groundwater sources for irrigation provides important information, at short time scale, for the estimation of groundwater variability at local scale.

A GNSS-based weather forecasting approach using Nonlinear Auto Regressive Approach with Exogenous Input (NARX)

The rapid variation of precipitation that occurs in the troposphere potentially affects weather conditions. Using GNSS-derived precipitable water vapour (PWV) and external input of rainfall data is useful and beneficial for the prediction of rapid changes of PWV which eventually leads to rainfall prediction in near real time. A nonlinear autoregressive approach with exogenous input (NARX) is an effective approach to statistical forecasting which is used in weather forecasting studies. Furthermore, choosing the most effective algorithm between the Levenberg Marquardt regularization and Bayesian Regularization may be ideal for predicting rainfall. Ten GNSS stations from the Malaysia real-time kinematic network (MyRTKnet) were selected. The selected GNSS stations cover Perak states in Malaysia from 1 January to 31 December 2013. While Obtained results from linear regression model show only 1% correlation between rainfall data and GNSS-derived PWV, comparing the predicted values by NARX networks and actual data show a significant improvement. Addition of GNSS-derived PWV along with daily rainfall data collected from meteorological stations significantly improves the prediction results between 30% and 59% correlation for Bayesian and Levenberg Marquardt regularization, respectively. Furthermore, the Levenberg Marquardt training algorithm may be the most accurate model among the forms of ANN used. Such a significant improvement is favourable to use NARX networks for near real time prediction.

Real Time Wave Prediction Using Neural Networks at Karwar, West Coast of India

The knowledge of ocean waves is an essential prerequisite for almost all activities in ocean. Traditional methods have disadvantages of excessive data requirement, time consumption and are tedious to carry out. ANN is being widely applied in coastal engineering field since last two decades in variety of time series forecasting. Study has been carried out to predict waves using FFBP and NARX networks. Wave data obtained from INCOIS is made use in the present study. Effect of network architecture on the performance of the model has been studied. It was found that for time series prediction NARX network outperforms FFBP.

Prediction of future evolution of solar cycle 24 using machine learning techniques

AbstractForecasting the solar activity is of great importance not only for its effect on the climate of the Earth but also on the telecommunications, power lines, space missions and satellite safety. In the present work, machine learning using Artificial Neural Networks (ANNs) called Nonlinear Autoregressive Network (NAR) with Exogenous Inputs (NARX) have been applied for the prediction of future evolution of the present sunspot cycle. NARX network is able to combine the performance of ANN algorithm with nonlinear autoregressive method to handle problems such as finding dependencies among solar indices and prediction of solar cycle evolution.

NARX Network based Driver Behavior Analysis and Prediction using Time-series Modeling

NARX Network based Driver Behavior Analysis and Prediction using Time-series Modeling