scholarly journals Artificial neural network models for reservoir-aquifer dimensionless variables: influx and pressure prediction for water influx calculation

2021 ◽  
Vol 11 (4) ◽  
pp. 1885-1904
Author(s):  
Anietie Ndarake Okon ◽  
Idongesit Bassey Ansa
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Bottom Water ◽  
Mean Square ◽  
Petroleum Reservoir ◽  
Statistical Measures ◽  
Water Influx ◽  
Ann Models ◽  
Artificial Neural

AbstractCalculation of water influx into petroleum reservoir is a tedious evaluation with significant reservoir engineering applications. The classical approach developed by van Everdingen–Hurst (vEH) based on diffusivity equation solution had been the fulcrum for water influx calculation in both finite and infinite-acting aquifers. The vEH model for edge-water drive reservoirs was modified by Allard and Chen for bottom-water drive reservoirs. Regrettably, these models solution variables: dimensionless influx ($$W_{{{\text{eD}}}}$$ W eD ) and dimensionless pressure ($$P_{D}$$ P D ) were presented in tabular form. In most cases, table look-up and interpolation between time entries are necessary to determine these variables, which makes the vEH approach tedious for water influx estimation. In this study, artificial neural network (ANN) models to predict the reservoir-aquifer variables $$W_{{{\text{eD}}}}$$ W eD and $$P_{D}$$ P D was developed based on the vEH datasets for the edge- and bottom-water finite and infinite-acting aquifers. The overall performance of the developed ANN models correlation coefficients (R) was 0.99983 and 0.99978 for the edge- and bottom-water finite aquifer, while edge- and bottom-water infinite-acting aquifer was 0.99992 and 0.99997, respectively. With new datasets, the generalization capacities of the developed models were evaluated using statistical tools: coefficient of determination (R2), R, mean square error (MSE), root-mean-square error (RMSE) and absolute average relative error (AARE). Comparing the developed finite aquifer models predicted $$W_{{{\text{eD}}}}$$ W eD with Lagrangian interpolation approach resulted in R2, R, MSE, RMSE and AARE of 0.9984, 0.9992, 0.3496, 0.5913 and 0.2414 for edge-water drive and 0.9993, 0.9996, 0.1863, 0.4316 and 0.2215 for bottom-water drive. Also, infinite-acting aquifer models (Model-1) resulted in R2, R, MSE, RMSE and AARE of 0.9999, 0.9999, 0.5447, 0.7380 and 0.2329 for edge-water drive, while bottom-water drive had 0.9999, 0.9999, 0.2299, 0.4795 and 0.1282. Again, the edge-water infinite-acting model predicted $$W_{{{\text{eD}}}}$$ W eD and Edwardson et al. polynomial estimated $$W_{eD}$$ W eD resulted in the R2 value of 0.9996, R of 0.9998, MSE of 4.740 × 10–4, RMSE of 0.0218 and AARE of 0.0147. Furthermore, the developed ANN models generalization performance was compared with some models for estimating $$P_{D}$$ P D . The results obtained for finite aquifer model showed the statistical measures: R2, R, MSE, RMSE and AARE of 0.9985, 0.9993, 0.0125, 0.1117 and 0.0678 with Chatas model and 0.9863, 0.9931, 0.1411, 0.3756 and 0.2310 with Fanchi equation. The infinite-acting aquifer model had 0.9999, 0.9999, 0.1750, 0.0133 and 7.333 × 10–3 with Edwardson et al. polynomial, then 0.9865, 09,933, 0.0143, 0.1194 and 0.0831 with Lee model and 0.9991, 0.9996, 1.079 × 10–3, 0.0328 and 0.0282 with Fanchi model. Therefore, the developed ANN models can predict $$W_{{{\text{eD}}}}$$ W eD and $$P_{D}$$ P D for the various aquifer sizes provided by vEH datasets for water influx calculation.

Detection of Biomedical Images by Using Bio-inspired Artificial Intelligent

2020 ◽  
Vol 38 (2A) ◽  
pp. 255-264
Author(s):  
Hanan A. R. Akkar ◽  
Sameem A. Salman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Average Rate ◽  
Mean Square ◽  
Performance Measurements ◽  
Artificial Intelligent ◽  
Average Mean Square Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Computer vision and image processing are extremely necessary for medical pictures analysis. During this paper, a method of Bio-inspired Artificial Intelligent (AI) optimization supported by an artificial neural network (ANN) has been widely used to detect pictures of skin carcinoma. A Moth Flame Optimization (MFO) is utilized to educate the artificial neural network (ANN). A different feature is an extract to train the classifier. The comparison has been formed with the projected sample and two Artificial Intelligent optimizations, primarily based on classifier especially with, ANN-ACO (ANN training with Ant Colony Optimization (ACO)) and ANN-PSO (training ANN with Particle Swarm Optimization (PSO)). The results were assessed using a variety of overall performance measurements to measure indicators such as Average Rate of Detection (ARD), Average Mean Square error (AMSTR) obtained from training, Average Mean Square error (AMSTE) obtained for testing the trained network, the Average Effective Processing Time (AEPT) in seconds, and the Average Effective Iteration Number (AEIN). Experimental results clearly show the superiority of the proposed (ANN-MFO) model with different features.

scholarly journals Artificial Neural Network-Cuckoo Optimization Algorithm (ANN-COA) for Optimal Control of Khorramabad Wastewater Treatment Plant, Iran

2016 ◽  
Vol 2 (11) ◽  
pp. 555-567 ◽  
Author(s):  
Samaneh Khademikia ◽  
Ali Haghizadeh ◽  
Hatam Godini ◽  
Ghodratollah Shams Khorramabadi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wastewater Treatment ◽  
Mean Square Error ◽  
Optimization Algorithm ◽  
Wastewater Treatment Plant ◽  
Treatment Plant ◽  
Mean Square ◽  
Cuckoo Optimization Algorithm ◽  
Artificial Neural

In this study a hybrid estimation model ANN-COA developed to provide an accurate prediction of a Wastewater Treatment Plant (WWTP). An effective strategy for detection of some output parameters tested on a hardware setup in WWTP. This model is designed utilizing Artificial Neural Network (ANN) and Cuckoo Optimization Algorithm (COA) to improve model performances; which is trained by a historical set of data collected during a 6 months operation. ANN-COA based on the difference between the measured and simulated values, allowed a quick revealing of the faults. The method could obtain the fault detection and used in solving continuous and discrete optimization problems, successfully. After constructing and modelling the method, selected performance indices including coefficient of Regression, Mean-Square Error, Root-Mean-Square Error and Aggregated Measure used to compare the obtained results. This analysis revealed that the hybrid ANN-COA model offers a higher degree of accuracy for predicting and control the WWTP.

scholarly journals An Artificial Neural Network Model for Highway Accident Prediction: A Case Study of Erzurum, Turkey

2015 ◽  
Vol 27 (3) ◽  
pp. 217-225 ◽  
Author(s):  
Muhammed Yasin Çodur ◽  
Ahmet Tortum
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Traffic Accidents ◽  
Model Parameters ◽  
Mean Square ◽  
Ann Model ◽  
Accident Prediction ◽  
Marquardt Algorithm ◽  
Artificial Neural

This study presents an accident prediction model of Erzurum’s Highways in Turkey using artificial neural network (ANN) approaches. There are many ANN models for predicting the number of accidents on highways that were developed using 8 years with 7,780 complete accident reports of historical data (2005-2012). The best ANN model was chosen for this task and the model parameters included years, highway sections, section length (km), annual average daily traffic (AADT), the degree of horizontal curvature, the degree of vertical curvature, traffic accidents with heavy vehicles (percentage), and traffic accidents that occurred in summer (percentage). In the ANN model development, the sigmoid activation function was employed with Levenberg-Marquardt algorithm. The performance of the developed ANN model was evaluated by mean square error (MSE), the root mean square error (RMSE), and the coefficient of determination (R2). The model results indicate that the degree of vertical curvature is the most important parameter that affects the number of accidents on highways.

scholarly journals Prediction of the Bicarbonate Amount in Drinking Water in the Region of Médéa Using Artificial Neural Network Modelling

2020 ◽  
Vol 69 (11-12) ◽  
pp. 595-602
Author(s):  
Hichem Tahraoui ◽  
Abd Elmouneïm Belhadj ◽  
Adhya Eddine Hamitouche
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Drinking Water ◽  
Mean Square Error ◽  
Correlation Coefficient ◽  
Mean Square ◽  
Ann Model ◽  
Network Modelling ◽  
Data Set ◽  
Artificial Neural

The region of Médéa (Algeria) located in an agricultural site requires a large amount of drinking water. For this purpose, the water analyses in question are imperative. To examine the evolution of the drinking water quality in this region, firstly, an experimental protocol was done in order to obtain a dataset by taking into account several physicochemical parameters. Secondly, the obtained data set was divided into two parts to form the artificial neural network, where 70 % of the data set was used for training, and the remaining 30 % was also divided into two equal parts: one for testing and the other for validation of the model. The intelligent model obtained was evaluated as a function of the correlation coefficient nearest to 1 and lowest mean square error (RMSE). A set of 84 data points were used in this study. Eighteen parameters in the input layer, five neurons in the hidden layer, and one parameter in the output layer were used for the ANN modelling. Levenberg Marquardt learning (LM) algorithm, logarithmic sigmoid, and linear transfer function were used, respectively, for the hidden and the output layers. The results obtained during the present study showed a correlation coefficient of <i>R</i> = 0.99276 with root mean square error RMSE = 11.52613 mg dm<sup>–3</sup>. These results show that obtained ANN model gave far better and more significant results. It is obviously more accurate since its relative error is small with a correlation coefficient close to unity. Finally, it can be concluded that obtained model can effectively predict the rate of soluble bicarbonate in drinking water in the Médéa region.

scholarly journals Flood Risk Prediction for a Hydropower System using Artificial Neural Network

2019 ◽  
Vol 8 (4) ◽  
pp. 6177-6181
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Water Flow ◽  
Performance Metrics ◽  
Water Discharge ◽  
Mean Square ◽  
Ann Model ◽  
Elman Neural Network ◽  
Artificial Neural

Hydropower scheme would experience issue relating to high flooding especially at low lying area due to extreme raining season. To mitigate the potential risk of flooding and improve the hydroelectric regulation, a flow prediction is needed to estimate the discharge of water flow at hydroelectric reservoirs. Artificial Neural Network (ANN) model were used in this research to forecast the water discharge of hydroelectric station. The discharge flow predictions were made based on fore bay elevation, inflow and the discharge of water flow. Elman Neural Network architecture was selected as ANN method and its performance was evaluated by considering the number of hidden nodes and training methods. ANN model performance were assessed using performance metrics such as Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE) and Sum Square Error (SSE). The result indicate that ANN model showed the best applicability for discharge prediction with small performance metric.

scholarly journals Prediction of wind speed using a new Grey-extreme learning machine hybrid algorithm: A case study

2018 ◽  
Vol 30 (1) ◽  
pp. 44-62 ◽  
Author(s):  
Mojtaba Qolipour ◽  
Ali Mostafaeipour ◽  
Mohammad Saidi-Mehrabad ◽  
Hamid R Arabnia
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Mean Square Error ◽  
Extreme Learning Machine ◽  
Hybrid Algorithm ◽  
Mean Square ◽  
Grey Systems Theory ◽  
Artificial Neural ◽  
Learning Machine

Wind energy is becoming one of the most important sources of renewable energy for many countries in the future. The purpose of this study is to predict wind speed using different algorithms. In this study, a new hybrid algorithm is developed to predict the wind speed behavior, and 24 h predictions of changes in wind speed are obtained with the aid of Homer software. The proposed algorithm is a combination of a well-known artificial neural network predictor called extreme learning machine as an artificial neural network algorithm and the Grey model (1, 1) as a method of Grey systems theory. Long-term wind speed forecasts are obtained using three-year data (2013–2016) of eight variables: TMAX, TMIN, VP, RHMIN, RHMAX, WINDSPEED, SUNSHINE HOURS, and PERCIPITATION for the Zanjan city in Iran, and 24 h wind speed forecast is obtained using 10-year data (2005–2015) pertaining to this city. The results show that proposed algorithm with relative measure of fit R2 of 0.99376 and mean square error of 0.000376 provides better predictions of wind speed in the study area than ordinary extreme learning machine algorithm with R2 of 0.98075 and mean square error of 0.00720. Also, the 24 h prediction of changes in wind speed is done using Homer software. The methodology in this research is more efficient in terms of execution performance and accuracy.

Artificial Neural Network Modelling of Green Synthesised Silver Nanoparticles in Bentonite/Starch Bio-Nanocomposite

2018 ◽  
Vol 14 (3) ◽  
pp. 239-251 ◽  
Author(s):  
Anupama Thapliyal ◽  
Roop Krishen Khar ◽  
Amrish Chandra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Silver Nanoparticles ◽  
Mean Square Error ◽  
Reduction Method ◽  
Mean Square ◽  
Ann Model ◽  
Ag Nps ◽  
Feed Forward ◽  
Artificial Neural

Background: In this study, computational Artificial Neural Network (ANN) model is applied for optimisation and evaluation of silver nanoparticles (AgNPs) size in the bionanocomposite matrix. The primary purpose of this study is used a feed-forward ANN model to create a connection between the output as the size of Ag–NPs, with four inputs variables, including AgNO3 concentration, the weight percentage of starch, Bentonite amount and Gallic acid concentration. Method: Silver nanoparticles were synthesised via biogenic green reduction method. The fast Levenberg– Marquardt (LM) backpropagation algorithm applied for the training of ANN model in this research. The optimised ANN is a multilayer perceptron (MLP) which is a kind of feed forward (4- 10-1) network has an input layer with 4 nodes, hidden layers with 10 neurones, and an output layer with 1 node found a fitness function. Results: The output results of developed computational ANN model were compared to its predictive values of the size of silver nanoparticles regarding two statistical parameters, the coefficient of determination (R2) and mean square error (MSE) of data set. It observed that ANN predicted values are close to the actual values and well fitted to the data. The mean square error(MSE) is 0.03, and a regression is about 1. Conclusion: AgNO3 concentration has the most likely factor affecting the size of silver nanoparticles (Ag–NPs) and this makes possible to develop a green reduction method for the preparation of silver nanoparticles. This study confirms that employing ANN method with LM feed forward (4-10-1) network is a useful tool with cost-effective for predicting the results of analysis and modelling of the chemical reactions.

scholarly journals The effects of demographic characteristics and public healthcare systems on COVID-19 mortality risk in the Global South: GIS-based and artificial neural network techniques

2021 ◽  
Author(s):  
Shawky Mansour ◽  
Ammar Abulibdeh ◽  
Mohammed Alahmadi ◽  
Al Nazir Ramadan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Global Health ◽  
Mean Square Error ◽  
Mortality Rates ◽  
Global South ◽  
Effective Control ◽  
Public Healthcare ◽  
Mean Square ◽  
Artificial Neural

Abstract The coronavirus disease (COVID-19) that appeared in 2019 gave rise to a major global health crisis that is topping global health, socioeconomic and intervention programme agendas in 2020. Although the outbreak of COVID-19 has substantial and devastating impacts on developed countries, the countries of Global South share a higher proportion of the epidemic’s effects as shown particularly in morbidity and mortality rates in low-income countries . Globally, as at 13th June 2020, the total number of mortality cases was 428,337 of which 9% were in Asia (38,915) and 13.5% in South America (57,896) while 1.4% were in Africa (6080). The number of infections and deaths is still increasing rapidly at the time of writing. Modelling the effects of underlying factors and disease mortality is essential to plan effective control strategies for disease transmission and risks. The relationship between COVID-19 mortality rates and socio-demographic and health determinants can highlight various epidemic fatality risks. In this research, Geographic Information Systems (GIS) and an Artificial Neural Network (ANN) Multilayer Perceptron (MLP) were adopted to model and examine variations in COVID-19 mortality rates in the Global South. The model’s performance was tested using statistical measures of Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Bias Error (MBE), and the determination coefficient R2. The findings of this study indicated that the most important variable in explaining spatial mortality rate variations was the size of the elderly (65 and above) population . This was followed first by accessibility to handwashing facilities and second by hospital beds per 1000 population. Mapping the explanatory variables and estimated mortality rates and determining the importance of each variable in explaining the spatial variation of COVID-19 death rates across countries of the Global South can shed light on how public healthcare and demographic structures can offer policymakers invaluable guidelines to planning effective intervention strategies.

scholarly journals Aplikasi Artificial Neural Network (ANN) untuk Memprediksi Masa Studi Mahasiswa Program Studi Teknik Informatika Universitas Muhammadiyah Gresik

2019 ◽  
Vol 9 (1) ◽  
pp. 88-95
Author(s):  
Henny Dwi Bhakti
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Drop Out ◽  
Mean Square ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Kualitas mahasiswa merupakan bagian penting dalam institusi pendidikan. Universitas perlu melakukan evaluasi performa mahasiswa untuk menjaga kualitas mahasiswa. Salah satu variabel indikator performa mahasiswa adalah informasi tentang lama masa studi mahasiswa. Prediksi lama masa studi dibutuhkan pihak manajemen Universitas dalam menentukan kebijakan preventif terkait pencegahan dini kasus Drop Out (DO). Artificial Neural Network (ANN) adalah suatu metode yang meniru jaringan syaraf biologis untuk mempelajari sesuatu. Salah satu implementasi ANN yang banyak digunakan adalah untuk memprediksi. Penelitian ini melakukan prediksi masa studi mahasiswa dengan menggunakan ANN dengan metode pembelajaran backpropagation. Variabel yang digunakan adalah nilai Indeks Prestasi Semester (IPS) 4 semester awal mahasiswa. Data dibagi menjadi data latih dan data uji. Dari hasil pelatihan dan pengujian didapatkan nilai Mean Square Error (MSE) dan Koefisien Relasi (R). MSE digunakan untuk melihat kesalahan rata-rata antara output jaringan dengan target. Nilai R digunakan untuk melihat kuat atau tidaknya hubungan linier antara 2 variabel. Nilai MSE dan koefisien relasi pelatihan adalah 0,016175 dan 0,94353 sedangkan nilai MSE dan koefisien relasi pengujian adalah 0,12188 dan 0,56071. Dari hasil penelitian dapat disimpulkan bahwa ANN dapat digunakan untuk memprediksi masa studi mahasiswa.

scholarly journals Fuzzy Time Series and Artificial Neural Network: Forecasting Exportation of Natural Rubber in Malaysia

2021 ◽  
Vol 6 (1) ◽  
pp. 22-30
Author(s):  
Siti Nor Nadrah Muhamad ◽  
Shafeina Hatieqa Sofean ◽  
Balkiah Moktar ◽  
Wan Nurshazelin Wan Shahidan
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Natural Rubber ◽  
Mean Square Error ◽  
Fuzzy Time Series ◽  
Mean Square ◽  
Series Method ◽  
Time Series Method ◽  
Artificial Neural

Natural rubber is one of the most important crops in Malaysia alongside palm oil, cocoa, paddy, and pineapple. Being a tropical country, Malaysia is one of the top five exporters and producers of rubber in the world. The purpose of this study is to find the forecasted value of the actual data of the number of exportations of natural rubber by using Fuzzy Time Series and Artificial Neural Network. This study is also conducted to determine the best model by making comparison between Fuzzy Time Series and Artificial Neural Network. Fuzzy Time Series has allowed to overcome a downside where the classical time series method cannot deal with forecasting problem in which values of time series are linguistic terms represented by fuzzy sets. Artificial Neural Network was introduced as one of the systematic tools of modelling which has been forecasting for about 20 years ago. The error measure that was used in this study to make comparisons were Mean Square Error, Root Mean Square Error and Mean Absolute Percentage Error. The results of this study showed that the fuzzy time series method has the smallest error value compared to artificial neural network which means it was more accurate compared to artificial neural network in forecasting exportation of natural rubber in Malaysia.

Sign in / Sign up

Export Citation Format

Share Document