摘要 :
Several time series generated from agriculture can be effectively modelled using various time-series modelling techniques such as ARIMA (Box-Jenkins) modelling technique, State-Space modelling technique, Structural Time Series mod...
展开
Several time series generated from agriculture can be effectively modelled using various time-series modelling techniques such as ARIMA (Box-Jenkins) modelling technique, State-Space modelling technique, Structural Time Series modelling and other timeseries modelling depend on the properties of the given time series. Modelling and related forecasting for thetime serieswere performed using Autoregressive Moving Average (ARIMA), Autoregressive Neural Network(ARNN) and ARIMA-ARNN hybrid models. First,to maintain the stationarity property of the data (1950-51 to 2017-18)as a necessary step, the datasetwas tested,and thefirst order difference series were considered for modelling using the Box-Jenkins approach. ARIMA (0,1,1) were found suitable for theproduction and yield databased on the least value of Schwarz-Bayesian Criterion (SBC). Secondly, Autoregressive Neural Network (ARNN) of orderARNN (2,2) wasselected for both the dataset. Lastly, ARIMA (0,1,1) - ARNN (4,6) for both production and yield were found suitable. All the three models were tested for their forecast accuracy using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Accordingly, the ARIMA-ARNN hybrid model was found to be best as compared to the individual ARIMA and ARNN model. Based on the ARIMA-ARNN model, the forecasting of the production and yield for the year 2050 was found to be 35.84 million tonnes and 1062.01 kg/ha, respectively of pulses in India.
收起
摘要 :
Forecasting peak electrical energy consumption is important because it allows utilities to properly plan for the production and distribution of electrical energy. This reduces operating costs and avoids power outages. In addition,...
展开
Forecasting peak electrical energy consumption is important because it allows utilities to properly plan for the production and distribution of electrical energy. This reduces operating costs and avoids power outages. In addition, it can help reduce environmental impact by allowing for more efficient power generation and reducing the need for additional fossil fuels during periods of high demand. In the current work, electric power consumption data from “Compagnie Electrique du Benin (CEB)” was used to deduce the peak electric power consumption at peak hours. The peak consumption of electric power was predicted using hybrid approaches based on traditional time series prediction methods (autoregressive integrated moving average (ARIMA)) and deep learning methods (long short-term memory (LSTM), gated recurrent unit (GRU)). The ARIMA approach was used to model the trend term, while deep learning approaches were employed to interpret the fluctuation term, and the outputs from these models were combined to provide the final result. The hybrid approach, ARIMA-LSTM, provided the best prediction performance with root mean square error (RMSE) of 7.35, while for the ARIMA-GRU hybrid approach, the RMSE was 9.60. Overall, the hybrid approaches outperformed the single approaches, such as GRU, LSTM, and ARIMA, which exhibited RMSE values of 18.11, 18.74, and 49.90, respectively.
收起
摘要 :
The Auto Regressive Moving Average (ARIMA) model deals with only one single time series and did not allow the inclusion of other information in the model and forecasts. One way to solve this predicament is to use regression with A...
展开
The Auto Regressive Moving Average (ARIMA) model deals with only one single time series and did not allow the inclusion of other information in the model and forecasts. One way to solve this predicament is to use regression with ARIMA errors and provides all the advantages of regression with the powerful time series features of an ARIMA model. This study aims to develop a simple linear regression model with ARIMA errors to yearly production of wheat in India for the period of 1960-2016, where explanatory variable represents time. It is observed that our fitted model is more accurate to our data than ARIMA model.
收起
摘要 :
From the day one, mankind has always been interested in to the future. As the civilization advanced with growing sophistication in all phases of life, the need to look in to the future also grew with it. Today every government, pu...
展开
From the day one, mankind has always been interested in to the future. As the civilization advanced with growing sophistication in all phases of life, the need to look in to the future also grew with it. Today every government, public private organizations, as well as an individual would like to predict and plan for the future. In order to attain a better growth in the economy of a country, modeling and forecasting is the most important tool now a day, this can be done by one of the statistical technique called a Time series analysis. In this paper we tried to build a time series model called ARIMA (Auto Regressive Integrated Moving Average) model with particular reference of Box and Jenkins approach on annually total Imports and Exports of Pakistan from the year 1947 to the year 2013 with useful statistical software R. Validity of the fitted model is tested using standard statistical techniques. The fitted model is then use to forecast some future values of Imports and export of Pakistan. It is found that an ARIMA (2, 2, 2) and ARIMA (1, 2, 2) model looks suitable to forecast the annual Imports and Exports of Pakistan respectively. We also found an increasing trend both in case of Imports and Exports during this study.
收起
摘要 :
Space time data is a data which is containing both information about time and location. The series of time in space time data can be approached by time series analysis. ARIMA-X and VARMA-X are time series modeling that are involvi...
展开
Space time data is a data which is containing both information about time and location. The series of time in space time data can be approached by time series analysis. ARIMA-X and VARMA-X are time series modeling that are involving exogenous variables. This research aims to find the best model of rice price to milled dry grain price by using ARIMA-X and VARMA-X model. The result shows that the rice price in one province of Java is influenced by one month earlier of rice price in other provinces of Java location, milled dry grain's price in the same province, and milled dry grain's price in other provinces. By comparing the models show that VARMA-X (1,1) without restriction was better model than ARIMA-X with analysis simultaneously to all location.
收起
摘要 :
The object of the present study is to develop a new forecasting model for the atmospheric temperature of the continental United States. We shall analyze the pattern of the temperature time series, and illustrate the usefulness of ...
展开
The object of the present study is to develop a new forecasting model for the atmospheric temperature of the continental United States. We shall analyze the pattern of the temperature time series, and illustrate the usefulness of the duplicated mean of the signal. Removing the duplicated mean time series from the original temperature recording series simplifies the forecasting process. The accuracy of this proposed methodology will be demonstrated in comparison with the classical multiplicative Autoregressive Integrated Moving Average, ARIMA, model that is often used.
收起
摘要 :
Reliable modeling of novel commutative cases of COVID-19 (CCC) is essential for determining hospitalization needs and providing the benchmark for health-related policies. The current study proposes multi-regional modeling of CCC c...
展开
Reliable modeling of novel commutative cases of COVID-19 (CCC) is essential for determining hospitalization needs and providing the benchmark for health-related policies. The current study proposes multi-regional modeling of CCC cases for the first scenario using autoregressive integrated moving average (ARIMA) based on automatic routines (AUTOARIMA), ARIMA with maximum likelihood (ARIMAML), and ARIMA with generalized least squares method (ARIMAGLS) and ensembled (ARIMAML-ARIMAGLS). Subsequently, different deep learning (DL) models viz: long short-term memory (LSTM), random forest (RF), and ensemble learning (EML) were applied to the second scenario to predict the effect of forest knowledge (FK) during the COVID-19 pandemic. For this purpose, augmented Dickey–Fuller (ADF) and Phillips–Perron (PP) unit root tests, autocorrelation function (ACF), partial autocorrelation function (PACF), Schwarz information criterion (SIC), and residual diagnostics were considered in determining the best ARIMA model for cumulative COVID-19 cases (CCC) across multi-region countries. Seven different performance criteria were used to evaluate the accuracy of the models. The obtained results justified both types of ARIMA model, with ARIMAGLS and ensemble ARIMA demonstrating superiority to the other models. Among the DL models analyzed, LSTM-M1 emerged as the best and most reliable estimation model, with both RF and LSTM attaining more than 80% prediction accuracy. While the EML of the DL proved merit with 96% accuracy. The outcomes of the two scenarios indicate the superiority of ARIMA time series and DL models in further decision making for FK.
收起
摘要 :
According to the severe shortage of water resources in Iran, water resources forecast is one of the most important issues in the national policies. The purpose of this study was to evaluate the efficiency of the Singular Spectrum ...
展开
According to the severe shortage of water resources in Iran, water resources forecast is one of the most important issues in the national policies. The purpose of this study was to evaluate the efficiency of the Singular Spectrum Analysis model in forecasting the amount of groundwater resources in Iran versus ARIMA model. Singular spectrum analysis is a method which is suitable for analysis of nonlinear and stationary time series. For this purpose, water resources time series from 1983 to 2015 were used annually and the short-term and medium-term forecasts obtained from the two models were compared. According to the results, the SSA method was able to perform better in short and medium term predictions compared to the ARIMA model. Correspondingly the results showed 70% improvement in prediction of one step ahead up to 88% improvement in prediction of 3 steps ahead.
收起
摘要 :
According to the Green Deal, the carbon neutrality of the European Union (EU) should be reached partly by the transition from fossil fuels to alternative renewable sources. However, fossil fuels still play an essential role in ene...
展开
According to the Green Deal, the carbon neutrality of the European Union (EU) should be reached partly by the transition from fossil fuels to alternative renewable sources. However, fossil fuels still play an essential role in energy production, and are widely used in the world with no alternative to be completely replaced with, so far. In recent years, we have observed the rapidly growing prices of commodities such as oil or gas. The analysis of past fossil fuels consumption might contribute significantly to the responsible formulation of the energy policy of each country, reflected in policies of related organisations and the industrial sector. Over the years, a number of papers have been published on modelling production and consumption of fossil and renewable energy sources on the level of national economics, industrial sectors and households, exploiting and comparing a variety of approaches. In this paper, we model the consumption of fossil fuels (gas and coal) in Slovakia based on the annual data during the years 1965–2020. To our knowledge, no such model, which analyses historical data and provides forecasts for future consumption of gas and coal, respectively, in Slovakia, is currently available in the literature. For building the model, we have used the Box–Jenkins methodology. Because of the presence of trend in the data, we have considered the autoregressive integrated moving average (ARIMA (p,d,q)) model. By fitting models with various combinations of parameters p, d, q, the best fitting model has been chosen based on the value of Akaike’s information criterion. According to this, the model for coal consumption is ARIMA(0, 2, 1) and for gas consumption it is ARIMA(2, 2, 2).
收起