scholarly journals Production Decline Prediction of Shale Gas using Hybrid Models

2020 ◽  
pp. 1-16
Author(s):  
P. Manda ◽  
D.B. Nkazi
Keyword(s):  
Shale Gas ◽  
Time Series Data ◽  
Moving Average ◽  
Hybrid Models ◽  
Gas Production ◽  
Series Data ◽  
Average Deviation ◽  
Exponential Decline ◽  
Ann Models ◽  
Predicted Values

Hybrid models have frequently been used for shale gas production decline prediction by manipulating the unique strength of each of the known decline models. The use of a combination of models provides a more precise predicting model for forecasting time series data as compared to an individual model. In this study, the forecasting performance of decline curve hybrid models and ANN-ARIMA hybrid models are evaluated and compared with Arps’, Duong’s, the Power Law Exponential Decline, Autoregressive Integrated Moving Average (ARIMA) and Artificial Neutral Network (ANN) models, respectively. The variable used to assess the models was the respective flow rate, q(t) monitored over a period of time (T). The results have shown that the single model approach can outperform hybrid models. The average deviation of the two best models indicates a central tendency of the production data around the mean. Subsequently, the spread in the data between the actual and predicted values is found to be less. It can thus be concluded that the ARIMA and ANN models have the best forecasting accuracy for production decline in shale gas compared to the other models.

Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm

SPE Journal ◽  
2019 ◽  
Vol 24 (06) ◽  
pp. 2423-2437 ◽  
Author(s):  
Kyungbook Lee ◽  
Jungtek Lim ◽  
Daeung Yoon ◽  
Hyungsik Jung
Keyword(s):  
Time Series ◽  
Shale Gas ◽  
Transient Flow ◽  
Time Series Data ◽  
Gas Production ◽  
Series Data ◽  
Production Data ◽  
Gas Wells ◽  
Future Production ◽  
Unseen Data

Summary Decline–curve analysis (DCA) is an easy and fast empirical regression method for predicting future well production. However, applying DCA to shale–gas wells is limited by long transient flow, a unique completion design, and high–density drilling. Recently, a long short-term-memory (LSTM) algorithm has been widely applied to the prediction of time–series data. Because shale–gas–production data are time–series data, the LSTM algorithm can be applied to predict future shale–gas production. After information for 332 shale–gas wells in Alberta, Canada, is obtained from a commercial database, the data are preprocessed in seven steps, including cutoffs for well list, data cleaning, feature extraction, train and test sets split, normalization, and sorting for input into the LSTM model. The LSTM model is trained in 405 seconds by two features of production data and a shut–in (SI) period from 300 wells. The two–feature case shows a better prediction accuracy than both the one–feature case (i.e., production data only) and the hyperbolic DCA, where the three methods are tested on unseen data from 15 wells. The two–feature case can predict future production rates according to the SI period and provide a stable result for available time–series data.

Some statistical and CI models to predict chaotic high-frequency financial data

2020 ◽  
Vol 39 (5) ◽  
pp. 6419-6430
Author(s):  
Dusan Marcek
Keyword(s):  
Time Series Data ◽  
Moving Average ◽  
Methodological Approach ◽  
Back Propagation ◽  
Large Data ◽  
Series Data ◽  
Data Set ◽  
Training Time ◽  
Optimal Population ◽  
Forecast Time

To forecast time series data, two methodological frameworks of statistical and computational intelligence modelling are considered. The statistical methodological approach is based on the theory of invertible ARIMA (Auto-Regressive Integrated Moving Average) models with Maximum Likelihood (ML) estimating method. As a competitive tool to statistical forecasting models, we use the popular classic neural network (NN) of perceptron type. To train NN, the Back-Propagation (BP) algorithm and heuristics like genetic and micro-genetic algorithm (GA and MGA) are implemented on the large data set. A comparative analysis of selected learning methods is performed and evaluated. From performed experiments we find that the optimal population size will likely be 20 with the lowest training time from all NN trained by the evolutionary algorithms, while the prediction accuracy level is lesser, but still acceptable by managers.

Forecast of COVID-19 Cases in Nigeria: An implementation of an ARIMA model (Preprint)

2020 ◽  
Author(s):  
Sanyaolu Ameye ◽  
Michael Awoleye ◽  
Emmanuel Agogo ◽  
Ette Etuk
Keyword(s):  
Predictive Model ◽  
Time Series Data ◽  
Moving Average ◽  
Arima Model ◽  
Epidemiological Data ◽  
Series Data ◽  
Global Pandemic ◽  
First Case ◽  
Epidemiological Trend ◽  
Data Points

BACKGROUND The Coronavirus disease 2019 (COVID-2019) is a global pandemic and Nigeria is not left out in being affected. Though, the disease is just over three months since first case was identified in the country, we present a predictive model to forecast the number of cases expected to be seen in the country in the next 100 days. OBJECTIVE To implement a predictive model in forecasting the near future number of positive cases expected in the country following the present trend METHODS We performed an Auto Regressive Integrated Moving Average (ARIMA) model prediction on the epidemiological data obtained from Nigerian Centre for Disease Control to predict the epidemiological trend of the prevalence and incidence of COVID-2019. RESULTS There were 93 time series data points which lacked stationarity. From our ARIMA model, it is expected that the number of new cases declared per day will keep rising and towards the early September, 2020, Nigeria is expected to have well above sixty thousand confirmed cases. CONCLUSIONS We however believe that as we have more data points our model will be better fine-tuned.

scholarly journals A Comparison of Time-Series Predictions for Healthcare Emergency Department Indicators and the Impact of COVID-19

2021 ◽  
Vol 11 (8) ◽  
pp. 3561
Author(s):  
Diego Duarte ◽  
Chris Walshaw ◽  
Nadarajah Ramesh
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Moving Average ◽  
General Regression Neural Network ◽  
Series Data ◽  
Machine Learning Model ◽  
Hospital Patients ◽  
Major Incidents ◽  
General Regression ◽  
The Impact

Across the world, healthcare systems are under stress and this has been hugely exacerbated by the COVID pandemic. Key Performance Indicators (KPIs), usually in the form of time-series data, are used to help manage that stress. Making reliable predictions of these indicators, particularly for emergency departments (ED), can facilitate acute unit planning, enhance quality of care and optimise resources. This motivates models that can forecast relevant KPIs and this paper addresses that need by comparing the Autoregressive Integrated Moving Average (ARIMA) method, a purely statistical model, to Prophet, a decomposable forecasting model based on trend, seasonality and holidays variables, and to the General Regression Neural Network (GRNN), a machine learning model. The dataset analysed is formed of four hourly valued indicators from a UK hospital: Patients in Department; Number of Attendances; Unallocated Patients with a DTA (Decision to Admit); Medically Fit for Discharge. Typically, the data exhibit regular patterns and seasonal trends and can be impacted by external factors such as the weather or major incidents. The COVID pandemic is an extreme instance of the latter and the behaviour of sample data changed dramatically. The capacity to quickly adapt to these changes is crucial and is a factor that shows better results for GRNN in both accuracy and reliability.

scholarly journals VN-INDEX TREND PREDICTION USING LONG-SHORT TERM MEMORY NEURAL NETWORKS

2019 ◽  
Vol 17 (12.2) ◽  
pp. 61
Author(s):  
Nguyen Ngoc Tra ◽  
Ho Phuoc Tien ◽  
Nguyen Thanh Dat ◽  
Nguyen Ngoc Vu
Keyword(s):  
Time Series Data ◽  
Short Term Memory ◽  
Moving Average ◽  
Future Trend ◽  
Series Data ◽  
Short Term ◽  
Trend Prediction ◽  
Temporal Dependence ◽  
Term Memory ◽  
Long Short Term Memory

The paper attemps to forecast the future trend of Vietnam index (VN-index) by using long-short term memory (LSTM) networks. In particular, an LSTM-based neural network is employed to study the temporal dependence in time-series data of past and present VN index values. Empirical forecasting results show that LSTM-based stock trend prediction offers an accuracy of about 60% which outperforms moving-average-based prediction.

scholarly journals Studying monthly rainfall over Dibrugarh, Assam: Use of SARIMA approach

MAUSAM ◽  
2021 ◽  
Vol 68 (2) ◽  
pp. 349-356
Author(s):  
J. HAZARIKA ◽  
B. PATHAK ◽  
A. N. PATOWARY
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Moving Average ◽  
Demand Management ◽  
Arima Model ◽  
Monthly Rainfall ◽  
Series Data ◽  
Data Set ◽  
Modeling And Forecasting ◽  
Moving Average Model

Perceptive the rainfall pattern is tough for the solution of several regional environmental issues of water resources management, with implications for agriculture, climate change, and natural calamity such as floods and droughts. Statistical computing, modeling and forecasting data are key instruments for studying these patterns. The study of time series analysis and forecasting has become a major tool in different applications in hydrology and environmental fields. Among the most effective approaches for analyzing time series data is the ARIMA (Autoregressive Integrated Moving Average) model introduced by Box and Jenkins. In this study, an attempt has been made to use Box-Jenkins methodology to build ARIMA model for monthly rainfall data taken from Dibrugarh for the period of 1980- 2014 with a total of 420 points.  We investigated and found that ARIMA (0, 0, 0) (0, 1, 1)12 model is suitable for the given data set. As such this model can be used to forecast the pattern of monthly rainfall for the upcoming years, which can help the decision makers to establish priorities in terms of agricultural, flood, water demand management etc.  

scholarly journals Effectiveness and Forecasting of Interest Rate Reversal BI 7-Day Repo Rate in Indonesia: Lower Bound on Monetary Policy?

2018 ◽  
Vol 9 (1) ◽  
pp. 171-180
Author(s):  
I Gede Sanica ◽  
I Ketut Nurcita ◽  
I Made Mastra ◽  
Desak Made Sukarnasih
Keyword(s):  
Monetary Policy ◽  
Interest Rate ◽  
Time Series Data ◽  
Moving Average ◽  
Series Data ◽  
Autoregressive Integrated Moving Average ◽  
Implementation Of Monetary Policy ◽  
Repo Rate ◽  
The Right ◽  
The Impact

AbstractThis study aims to analyze effectivity and forecast of interest rate BI 7-Day Repo Rate as policy reference in the implementation of monetary policy. The method was used in this study contains Vector Autoregression (VAR) to estimate effectivity of BI 7-Day Repo Rate and Autoregressive Integrated Moving Average (ARIMA) to forecast of BI 7-Day Repo Rate. Period of observation in this study used time series data during 2016.4 until 2017.6. The result of this research shows that the transformation of the BI Rate to BI 7-Day Repo Rate is the right step in the monetary policy operation in the effort to reach deepening of the financial market and strengthen the interbank money market structure so that it will decrease loan interest rate and encourage credit growth. The effectiveness of the use of BI 7 Day-Repo Rate on price stability is indicated by the positive relationship between the benchmark interest rate and inflation compared to the BI Rate. The impact of BI 7-Day Repo Rate on economic growth that tends to be positive. Forecasting the use of BI 7-Day Repo Rate shows good results with declining value levels, so this will encourage deepening the financial markets.

scholarly journals Prediction of Rainfall Using Intensified LSTM Based Recurrent Neural Network with Weighted Linear Units

Atmosphere ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 668 ◽  
Author(s):  
S. Poornima ◽  
M. Pushpalatha
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Time Series Data ◽  
Short Term Memory ◽  
Moving Average ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Rainfall Prediction ◽  
Long Short Term Memory

Prediction of rainfall is one of the major concerns in the domain of meteorology. Several techniques have been formerly proposed to predict rainfall based on statistical analysis, machine learning and deep learning techniques. Prediction of time series data in meteorology can assist in decision-making processes carried out by organizations responsible for the prevention of disasters. This paper presents Intensified Long Short-Term Memory (Intensified LSTM) based Recurrent Neural Network (RNN) to predict rainfall. The neural network is trained and tested using a standard dataset of rainfall. The trained network will produce predicted attribute of rainfall. The parameters considered for the evaluation of the performance and the efficiency of the proposed rainfall prediction model are Root Mean Square Error (RMSE), accuracy, number of epochs, loss, and learning rate of the network. The results obtained are compared with Holt–Winters, Extreme Learning Machine (ELM), Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network and Long Short-Term Memory models in order to exemplify the improvement in the ability to predict rainfall.

scholarly journals Signal Design to Suppress Coupling in the Polarimetric Phased Array Radar

2014 ◽  
Vol 31 (5) ◽  
pp. 1063-1077 ◽  
Author(s):  
D. S. Zrnić ◽  
R. J. Doviak ◽  
V. M. Melnikov ◽  
I. R. Ivić
Keyword(s):  
Time Series Data ◽  
Signal Transmission ◽  
Cross Coupling ◽  
Series Data ◽  
Acquisition Time ◽  
Signal Design ◽  
Doppler Data ◽  
Orthogonal Components ◽  
Data Acquisition Time ◽  
Predicted Values

AbstractExamined are two related modes of polarimetric signal transmission that reduce coupling between the orthogonal components of received signals. For the surveillance scan with large unambiguous range and the simultaneous mode of horizontal (H) and vertical (V) transmission, pulse-to-pulse coding is suggested. It relaxes conditions on cross-coupling isolation from about 45 to about 25 dB while preserving the unambiguous range of over 460 km. For application to systematic codes during Doppler data acquisition, time-multiplexed (back to back) H and V pulses are proposed. This approach also relaxes the cross-coupling isolation to about 25 dB. These theoretically predicted values agree with those obtained by emulating the two schemes using oversampled time series data.

Sign in / Sign up

Export Citation Format

Share Document