Seasonal Artificial Neural Networks Research Articles

Intercomparison of deep learning models in predicting streamflow patterns: insight from CMIP6

This research was carried out to predict daily streamflow for the Swat River Basin, Pakistan through four deep learning (DL) models: Feed Forward Artificial Neural Networks (FFANN), Seasonal Artificial Neural Networks (SANN), Time Lag Artificial Neural Networks (TLANN) and Long Short-Term Memory (LSTM) under two Shared Socioeconomic Pathways (SSPs) 585 and 245. Taylor Diagram, Random Forest, and Gradient Boosting techniques were used to select the best combination of General Circulation Models (GCMs) for Multi-Model Ensemble (MME) computation. MME was computed via the Random Forest technique for Maximum Temperature (Tmax), Minimum Temperature (Tmin), and precipitation for the aforementioned three techniques. The best MME for Tmax, Tmin, and precipitation was rendered by Compromise Programming. The DL models were trained and tested using observed precipitation and temperature as independent variables and discharge as dependent variables. The results of deep learning models were evaluated using statistical performance indicators such as root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). The TLANN demonstrated superior performance compared to the other models based on RMSE, MSE, MAE, and R2 during training (65.25 m3/s, 4256.97 m3/s, 46.793 m3/s and 0.7978) and testing (72.06 m3/s, 5192.95 m3/s, 51.363 m3/s and 0.7443) respectively. Subsequently, TLANN was utilized to make predictions based on MME of SSP245 and SSP585 scenarios for future streamflow until the year 2100. These results can be used for planning, management, and policy-making regarding water resources projects in the study area.

Machine Learning based IoT Flood Rediction Using Data Modeling and Decision Support System

An essential step in supplying data for climate impact studies and evaluations of hydrological processes is rainfall prediction. However, rainfall events are complex phenomenon’s that continue to be difficult to forecast. In this paper , we present unique hybrid models for the prediction of monthly precipitation that include Seasonal Artificial Neural Networks and Discrete wavelet transforms are two pre-processing methods, together with Artificial Neural Networks have two feed forward neural networks. The temporal series of observed monthly rainfall from Vietnam’s Ca Mau hydrological station were decomposed into three subsets by seasonal decomposition and five sub signals and four levels by wavelet analysis. The methods for predicting rainfall that use feed forward artificial neural networks (ANN) and seasonal artificial neural network (SANN) were fed with the processed data. The classic genetic method and simulated annealing method backed by using an integrated moving average and autoregressive moving was contrasted with the predicted models for model evaluation. The results showed that non-stationary regarding issues with non-linear time series, such forecasting rainfall could be satisfactorily simulated. The SANN model was integrated with the wavelet transform and seasonal decomposition are both used. Techniques, however the wavelet transform method produced the most accurate monthly rainfall data, Predictions. Due to the effects of climate change, nations including the Japan, China, the United States of America, and Taiwan, etc., have recently experienced severe and devastating natural disasters. One of the biggest causes of the destruction in Asian nations like china, India, Bangladesh, Sri Lanka, etc. is the flood. The danger of fatality from these floods is increased by 78% as information technology advances; there is a demand for simple access to massive amounts of cloud storage and computing capacity.

Demand forecasting using modelling and comparison of series and parallel structures of SARIMA and SMLP

One of the problems in demand management is the change in demand, which causes uncertainty in the amount of production. Therefore, companies forecast demand in order to eliminate the uncertainty. There are several ways to predict demand. Series and parallel composition structures are the most important and accurate of these methods in prediction. The purpose of this paper is to model two series and parallel structures and compare the performance of these structures with each other and with their individual models. In this study, using a combination of seasonal autoregressive integrated moving average (SARIMA) and seasonal artificial neural network (SANN) widely used models, demand forecasting has been done in two Taiwan machinery dataset and soft drinks dataset. The results show that the performance of the proposed hybrid model is more accurate than the one-component models and also in the comparison of series and parallel structures, it is observed that on average the performance of the parallel structure in the field of demand forecasting produces more accurate results.

Comparison of the Performance of the SANN, SARIMA and ARIMA Models for Forecasting Quarterly GDP of Nigeria

This research aimed at modelling and forecasting the quarterly GDP of Nigeria using the Seasonal Artificial Neural Network (SANN), SARIMA and Box-Jenkins models as well as comparing their predictive performance. The three models mentioned earlier were successfully fitted to the data set. Tentative architecture for the SANN was suggested by varying the number of neurons in the hidden layer while that of the input and output layer remained constant at 4. It was observed that the best architecture was when the hidden layer had 10 neurons and thus SANN (4-10-4) was chosen as the best. In fitting the ARIMA/SARIMA models, the Augmented Dickey Fuller (ADF) test was used to check for stationarity. Variance stabilization and Stationarity were achieved after logarithm transformation and first regular differencing. The ARIMA/SARIMA model with lowest AIC, BIC and HQIC values was chosen as the best amongst the competing models and fitted to the data. The adequacy of the fitted models was confirmed observing the correlogram of the residuals and the Ljung-Box Chi-Squared test result. The SANN model performed better than the SARIMA and ARIMA models as it had a Mean Squared Error value of 0.004 while SARIMA and ARIMA had mean squared errors of 0.527 and 0.705 respectively. It was concluded that the SANN which is a non-linear model be used in modelling the quarterly GDP of Nigeria. Hybrid models which combine the strength of individual models are recommended for further research.

Comparing SANN and SARIMA for forecasting frequency of monthly rainfall in Umuahia

This paper adopted the use of artificial neural network (ANN) which is also a nonlinear model in contributing to the debate of comparing different methods of forecasting frequency of rainfall in Umuahia, Abia State of Nigeria. The choice of ANN is informed by articles in literature which have shown that Neural Network models outperform some traditional statistical models in modelling meteorological time series. The data used for the research was obtained from the National Root Crop Research Institute, Umudike, Abia State and it spanned from 2006 to 2016. The forecasting performance of seasonal autoregressive integrated moving average (SARIMA) model and that of seasonal artificial neural network (SANN) were compared with four forecast performance measures:- Forecast Error (FE), Mean Forecast Error (MFE), Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). Results from the study showed that the SARIMA had lower error indicators in forecast performance and thus was adjudged better than SANN in forecasting frequency of rainfall in Umuahia, Abia State. A t-test for significant difference showed that there is no statistical significant difference between both forecast values. Hence, the authors conclude that the two methods can be successfully used as substitutes. Farmers, Construction Companies, Government agencies working in Umuahia are therefore advised to choose SARIMA modelling of monthly rainfall frequency over that of SANN. This study also confirms that ANNs are not utterly better than the traditional statistical models as seen in other works in literature.

Improved Rainfall Prediction Using Combined Pre-Processing Methods and Feed-Forward Neural Networks

Rainfall prediction is a fundamental process in providing inputs for climate impact studies and hydrological process assessments. Rainfall events are, however, a complicated phenomenon and continues to be a challenge in forecasting. This paper introduces novel hybrid models for monthly rainfall prediction in which we combined two pre-processing methods (Seasonal Decomposition and Discrete Wavelet Transform) and two feed-forward neural networks (Artificial Neural Network and Seasonal Artificial Neural Network). In detail, observed monthly rainfall time series at the Ca Mau hydrological station in Vietnam were decomposed by using the two pre-processing data methods applied to five sub-signals at four levels by wavelet analysis, and three sub-sets by seasonal decomposition. After that, the processed data were used to feed the feed-forward Neural Network (ANN) and Seasonal Artificial Neural Network (SANN) rainfall prediction models. For model evaluations, the anticipated models were compared with the traditional Genetic Algorithm and Simulated Annealing algorithm (GA-SA) supported by Autoregressive Moving Average (ARMA) and Autoregressive Integrated Moving Average (ARIMA). Results showed both the wavelet transform and seasonal decomposition methods combined with the SANN model could satisfactorily simulate non-stationary and non-linear time series-related problems such as rainfall prediction, but wavelet transform along with SANN provided the most accurately predicted monthly rainfall.

Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network

Electricity is one of the most important end-user energy types in today’s world and has an effective role in development of societies and economies. Stability of electricity supply is provided by matching of generated and consumed electricity amount during the all-day. So, electricity consumption forecasting is an essential issue for electric utilities. In this study, the monthly electricity demand of Turkey has been predicted. To model the effects of seasonality and trend, four different ANN models have been developed and selected the superior one. In addition, the selected ANN model has been compared with SARIMA model in order to increase the acceptability and reliability of the ANN model. The monthly electricity demand of Turkey has been predicted between 2015 and 2018 via the ANN model that can make successful and high-accuracy predictions according to the performance measures. The forecasting values will help in determining the medium-term and stable energy policies.

Seasonal artificial neural network model for water quality prediction via a clustering analysis method in a wastewater treatment plant of China

For recovering the water quality of a river, it is a key factor to improve purifying capacity of wastewater in wastewater treatment plants (WTPs). The relational model for some key parameters of WTP processes is important for it can reveal the current situation and handling ability of the WTP and offer managers more useful information to design the processes for the optimized operation. The seasonal artificial neural network (ANN) models were designed for improving purifying ability of wastewater in a WTP of Harbin, northeast of China. The ANN models revealed the relationship of raw water quality, energy consumption, and effluent water quality. The effluent water quality could be predicted by the models. The clustering analysis method, an important data mining method, was used to classify the WTP data for building seasonal models. Meanwhile, an annual model was built by the whole data. It indicates that the prediction accuracy of seasonal models is better than the annual model by contrasting the errors. Seasonal models should be a more effective tool to reveal the relationship of WTP data. So it can offer managers more precise information to control and design the processes of WTPs, which result in better purifying ability of wastewater.

Drought frequency projection using regional climate scenarios reconstructed by seasonal artificial neural network model

The climate change impacts on drought in the Korean peninsula were projected using Global Climate Model (GCM) output reconstructed regionally by an artificial neural network (ANN) model. The reconstructed model outputs were subsequently used as an input to project drought severity evaluated by Standard Precipitation Index (SPI). The original GCM output corresponds to the CGCM3.1/T63 under the 20C3M reference scenario and the IPCC A1B, A2 and B1 projection scenarios. Because in general GCM shows limitation in capturing typhoon generation occurred at sub-grid scale, the training and validation of the ANN model utilized a precipitation data set with typhoon-generated rainfall eliminated for enhancing the ANN's computational performance. The non-stationarity characteristics of SPI was examined using the Mann–Kendall test. The projection was implemented for the near future period (2011–2040), mid-term (2041–2070) and long-term (2071–2100) future periods. The results indicated mitigated drought severity under all scenarios in terms of frequency, magnitude and drought spells even for the mildest B1 scenario. The SDF (severity-duration-frequency) curves illustrate the common patterns of alleviated drought severity for most future scenarios and elongated drought duration. The reconstructed GCM projection recovers the underestimated precipitation and provided more realistic drought projection even though there would be still uncertainties of spatial and temporal variability.

Optimization of Short Load Forecasting in Electricity Market of Iran Using Artificial Neural Networks

Accurate short-term load forecasting (STLF) is one of the essential requirements for power systems. In this paper, two different seasonal artificial neural networks (ANNs) are designed and compared in terms of model complexity, robustness, and forecasting accuracy. Furthermore, the performance of ANN partitioning is evaluated. The first model is a daily forecasting model which is used for forecasting hourly load of the next day. The second model is composed of 24 sub-networks which are used for forecasting hourly load of the next day. In fact, the second model is partitioning of the first model. Time, temperature, and historical loads are taken as inputs for ANN models. The neural network models are based on feed-forward back propagation which are trained and tested using data from electricity market of Iran during 2003 to 2005. Results show a good correlation between actual data and ANN outcomes. Moreover, it is shown that the first designed model consisting of single ANN is more appropriate than the second model consisting of 24 distinct ANNs. Finally ANN results are compared to conventional regression models. It is observed that in most cases ANN models are superior to regression models in terms of mean absolute percentage error (MAPE).