Multi-Class Taxonomy of Well Integrity Anomalies Applying Inductive Learning Algorithms: Analytical Approach for Artificial-Lift Wells

Abstract Well integrity has become a crucial field with increased focus and being published intensively in industry researches. It is important to maintain the integrity of the individual well to ensure that wells operate as expected for their designated life (or higher) with all risks kept as low as reasonably practicable, or as specified. Machine learning (ML) and artificial intelligence (AI) models are used intensively in oil and gas industry nowadays. ML concept is based on powerful algorithms and robust database. Developing an efficient classification model for well integrity (WI) anomalies is now feasible because of having enormous number of well failures and well barrier integrity tests, and analyses in the database. Circa 9000 dataset points were collected from WI tests performed for 800 wells in Gulf of Suez, Egypt for almost 10 years. Moreover, those data have been quality-controlled and quality-assured by experienced engineers. The data contain different forms of WI failures. The contributing parameter set includes a total of 23 barrier elements. Data were structured and fed into 11 different ML algorithms to build an automated systematic tool for calculating imposed risk category of any well. Comparison analysis for the deployed models was performed to infer the best predictive model that can be relied on. 11 models include both supervised and ensemble learning algorithms such as random forest, support vector machine (SVM), decision tree and scalable boosting techniques. Out of 11 models, the results showed that extreme gradient boosting (XGB), categorical boosting (CatBoost), and decision tree are the most reliable algorithms. Moreover, novel evaluation metrics for confusion matrix of each model have been introduced to overcome the problem of existing metrics which don't consider domain knowledge during model evaluation. The innovated model will help to utilize company resources efficiently and dedicate personnel efforts to wells with the high-risk. As a result, progressive improvements on business, safety, environment, and performance of the business. This paper would be a milestone in the design and creation of the Well Integrity Database Management Program through the combination of integrity and ML.

Techniques for Detecting Malware Traffic: A Comprehensive Approach to Feature Selection and Classification

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.39088 ◽

2021 ◽

Vol 9 (12) ◽

pp. 1-10

Author(s):

Harsha A K

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Random Forest ◽

Learning Algorithms ◽

Malware Detection ◽

Gradient Boosting ◽

Support Vector ◽

Steady Increase ◽

Abstract: Since the advent of encryption, there has been a steady increase in malware being transmitted over encrypted networks. Traditional approaches to detect malware like packet content analysis are inefficient in dealing with encrypted data. In the absence of actual packet contents, we can make use of other features like packet size, arrival time, source and destination addresses and other such metadata to detect malware. Such information can be used to train machine learning classifiers in order to classify malicious and benign packets. In this paper, we offer an efficient malware detection approach using classification algorithms in machine learning such as support vector machine, random forest and extreme gradient boosting. We employ an extensive feature selection process to reduce the dimensionality of the chosen dataset. The dataset is then split into training and testing sets. Machine learning algorithms are trained using the training set. These models are then evaluated against the testing set in order to assess their respective performances. We further attempt to tune the hyper parameters of the algorithms, in order to achieve better results. Random forest and extreme gradient boosting algorithms performed exceptionally well in our experiments, resulting in area under the curve values of 0.9928 and 0.9998 respectively. Our work demonstrates that malware traffic can be effectively classified using conventional machine learning algorithms and also shows the importance of dimensionality reduction in such classification problems. Keywords: Malware Detection, Extreme Gradient Boosting, Random Forest, Feature Selection.

Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9090507 ◽

2020 ◽

Vol 9 (9) ◽

pp. 507

Author(s):

Sanjiwana Arjasakusuma ◽

Sandiaga Swahyu Kusuma ◽

Stuart Phinn

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Learning Algorithms ◽

Principal Component ◽

Hyperspectral Data ◽

Gradient Boosting ◽

Support Vector ◽

Forest Height ◽

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

Comparison of Approaches for Urban Functional Zones Classification Based on Multi-Source Geospatial Data: A Case Study in Yuzhong District, Chongqing, China

Sustainability ◽

10.3390/su11030660 ◽

2019 ◽

Vol 11 (3) ◽

pp. 660 ◽

Cited By ~ 6

Author(s):

Kai Cao ◽

Hui Guo ◽

Ye Zhang

Keyword(s):

Rapid Development ◽

Geospatial Data ◽

Classification Model ◽

Gradient Boosting ◽

Support Vector ◽

Night Time ◽

Heat Map ◽

Functional Zones

Accurate and timely classification and monitoring of urban functional zones prove to be significant in rapidly developing cities, to better understand the real and varying urban functions of cities to support urban planning and management. Many efforts have been undertaken to identify urban functional zones using various classification approaches and multi-source geospatial datasets. The complexity of this category of classification poses tremendous challenges to these studies especially in terms of classification accuracy, but on the opposite, the rapid development of machine learning technologies provides us with new opportunities. In this study, a set of commonly used urban functional zones classification approaches, including Multinomial Logistic Regression, K-Nearest Neighbors, Decision Tree, Support Vector Machine (SVM), and Random Forest, are examined and compared with the newly developed eXtreme Gradient Boosting (XGBoost) model, using the case study of Yuzhong District, Chongqing, China. The investigation is based on multi-variate geospatial data, including night-time imagery, geotagged Weibo data, points of interest (POI) from Gaode, and Baidu Heat Map. This study is the first endeavor of implementing the XGBoost model in the field of urban functional zones classification. The results suggest that the XGBoost classification model performed the best and was able to achieve an accuracy of 88.05%, which is significantly higher than the other commonly used approaches. In addition, the integration of night-time imagery, geotagged Weibo data, POI from Gaode, and Baidu Heat Map has also demonstrated their values for the classification of urban functional zones in this case study.

Modelos de machine learning para predição do sucesso de startups

Revista de Gestão e Projetos ◽

10.5585/gep.v12i2.18942 ◽

2021 ◽

Vol 12 (2) ◽

pp. 28-55

Author(s):

Fabiano Rodrigues ◽

Francisco Aparecido Rodrigues ◽

Thelma Valéria Rocha Rodrigues

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Random Forest ◽

Decision Tree ◽

Initial Public Offering ◽

Gradient Boosting ◽

Support Vector ◽

Trade Offs ◽

Public Offering

Este estudo analisa resultados obtidos com modelos de machine learning para predição do sucesso de startups. Como proxy de sucesso considera-se a perspectiva do investidor, na qual a aquisição da startup ou realização de IPO (Initial Public Offering) são formas de recuperação do investimento. A revisão da literatura aborda startups e veículos de financiamento, estudos anteriores sobre predição do sucesso de startups via modelos de machine learning, e trade-offs entre técnicas de machine learning. Na parte empírica, foi realizada uma pesquisa quantitativa baseada em dados secundários oriundos da plataforma americana Crunchbase, com startups de 171 países. O design de pesquisa estabeleceu como filtro startups fundadas entre junho/2010 e junho/2015, e uma janela de predição entre junho/2015 e junho/2020 para prever o sucesso das startups. A amostra utilizada, após etapa de pré-processamento dos dados, foi de 18.571 startups. Foram utilizados seis modelos de classificação binária para a predição: Regressão Logística, Decision Tree, Random Forest, Extreme Gradiente Boosting, Support Vector Machine e Rede Neural. Ao final, os modelos Random Forest e Extreme Gradient Boosting apresentaram os melhores desempenhos na tarefa de classificação. Este artigo, envolvendo machine learning e startups, contribui para áreas de pesquisa híbridas ao mesclar os campos da Administração e Ciência de Dados. Além disso, contribui para investidores com uma ferramenta de mapeamento inicial de startups na busca de targets com maior probabilidade de sucesso.

Systematic Evaluation of Machine Learning Algorithms for Neuroanatomically-Based Age Prediction in Youth

10.1101/2021.11.24.469888 ◽

2021 ◽

Author(s):

Mandana Modabbernia ◽

Heather C Whalley ◽

David Glahn ◽

Paul M. Thompson ◽

Rene S. Kahn ◽

...

Keyword(s):

Machine Learning ◽

Computational Efficiency ◽

Learning Algorithms ◽

Sensitivity Analyses ◽

Gradient Boosting ◽

Support Vector ◽

Age Related ◽

Brain Age

Application of machine learning algorithms to structural magnetic resonance imaging (sMRI) data has yielded behaviorally meaningful estimates of the biological age of the brain (brain-age). The choice of the machine learning approach in estimating brain-age in children and adolescents is important because age-related brain changes in these age-groups are dynamic. However, the comparative performance of the multiple machine learning algorithms available has not been systematically appraised. To address this gap, the present study evaluated the accuracy (Mean Absolute Error; MAE) and computational efficiency of 21 machine learning algorithms using sMRI data from 2,105 typically developing individuals aged 5 to 22 years from five cohorts. The trained models were then tested in an independent holdout datasets, comprising 4,078 pre-adolescents (aged 9-10 years). The algorithms encompassed parametric and nonparametric, Bayesian, linear and nonlinear, tree-based, and kernel-based models. Sensitivity analyses were performed for parcellation scheme, number of neuroimaging input features, number of cross-validation folds, and sample size. The best performing algorithms were Extreme Gradient Boosting (MAE of 1.25 years for females and 1.57 years for males), Random Forest Regression (MAE of 1.23 years for females and 1.65 years for males) and Support Vector Regression with Radial Basis Function Kernel (MAE of 1.47 years for females and 1.72 years for males) which had acceptable and comparable computational efficiency. Findings of the present study could be used as a guide for optimizing methodology when quantifying age-related changes during development.

KDClassifier: A urinary proteomic spectra analysis tool based on machine learning for the classification of kidney diseases

Aging Pathobiology and Therapeutics ◽

10.31491/apt.2021.09.064 ◽

2021 ◽

Vol 3 (3) ◽

pp. 63-72

Author(s):

Wanjun Zhao ◽

Keyword(s):

Kidney Disease ◽

Kidney Diseases ◽

Confusion Matrix ◽

Gradient Boosting ◽

Support Vector ◽

Diagnostic Model ◽

Analysis Tool ◽

Data Set ◽

Background: We aimed to establish a novel diagnostic model for kidney diseases by combining artificial intelligence with complete mass spectrum information from urinary proteomics. Methods: We enrolled 134 patients (IgA nephropathy, membranous nephropathy, and diabetic kidney disease) and 68 healthy participants as controls, with a total of 610,102 mass spectra from their urinary proteomic profiles. The training data set (80%) was used to create a diagnostic model using XGBoost, random forest (RF), a support vector machine (SVM), and artificial neural networks (ANNs). The diagnostic accuracy was evaluated using a confusion matrix with a test dataset (20%). We also constructed receiver operating-characteristic, Lorenz, and gain curves to evaluate the diagnostic model. Results: Compared with the RF, SVM, and ANNs, the modified XGBoost model, called Kidney Disease Classifier (KDClassifier), showed the best performance. The accuracy of the XGBoost diagnostic model was 96.03%. The area under the curve of the extreme gradient boosting (XGBoost) model was 0.952 (95% confidence interval, 0.9307–0.9733). The Kolmogorov-Smirnov (KS) value of the Lorenz curve was 0.8514. The Lorenz and gain curves showed the strong robustness of the developed model. Conclusions: The KDClassifier achieved high accuracy and robustness and thus provides a potential tool for the classification of kidney diseases

Machine Learning Application for Gas Lift Performance and Well Integrity

10.2118/205134-ms ◽

2021 ◽

Author(s):

Mostafa Sa'eed Yakoot ◽

Adel Mohamed Salem Ragab ◽

Omar Mahmoud

Keyword(s):

Machine Learning ◽

Business Performance ◽

Risk Level ◽

Gradient Boosting ◽

Support Vector ◽

Risk Category ◽

K Nearest Neighbors ◽

Failure Data ◽

Well Integrity ◽

Gas Lift

Abstract Constructing and maintaining integrity for different types of wells requires accurate assessment of posed risk level, especially when one barrier element or group of barriers fails. Risk assessment and well integrity (WI) categorization is conducted typically using traditional spreadsheets and in-house software that contain their own inherent errors. This is mainly because they are subjected to the understanding and the interpretation of the assigned team to WI data. Because of these limitations, industrial practices involve the collection and analysis of failure data to estimate risk level through certain established probability/likelihood matrices. However, those matrices have become less efficient due to the possible bias in failure data and consequent misleading assessment. The main objective of this work is to utilize machine learning (ML) algorithms to develop a powerful model and predict WI risk category of gas-lifted wells. ML algorithms implemented in this study are; logistic regression, decision trees, random forest, support vector machines, k-nearest neighbors, and gradient boosting algorithms. In addition, those algorithms are used to develop physical equation to predict risk category. Three thousand WI and gas-lift datasets were collected, preprocessed, and fed into the ML model. The newly developed model can predict well risk level and provide a unique methodology to convert associated failure risk of each element in the well envelope into tangible value. This shows the total potential risk and hence the status of well-barrier integrity overall. The implementation of ML can enhance brownfield asset operations, reduce intervention costs, better control WI through the field, improve business performance, and optimize production.

Bionic Electronic Nose Based on MOS Sensors Array and Machine Learning Algorithms Used for Wine Properties Detection

Sensors ◽

10.3390/s19010045 ◽

2018 ◽

Vol 19 (1) ◽

pp. 45 ◽

Cited By ~ 19

Author(s):

Huixiang Liu ◽

Qing Li ◽

Bin Yan ◽

Lei Zhang ◽

Yu Gu

Keyword(s):

Machine Learning ◽

Electronic Nose ◽

Optimal Algorithm ◽

Learning Algorithms ◽

Oxide Semiconductor ◽

Gradient Boosting ◽

Support Vector ◽

Fermentation Processes ◽

In this study, a portable electronic nose (E-nose) prototype is developed using metal oxide semiconductor (MOS) sensors to detect odors of different wines. Odor detection facilitates the distinction of wines with different properties, including areas of production, vintage years, fermentation processes, and varietals. Four popular machine learning algorithms—extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and backpropagation neural network (BPNN)—were used to build identification models for different classification tasks. Experimental results show that BPNN achieved the best performance, with accuracies of 94% and 92.5% in identifying production areas and varietals, respectively; and SVM achieved the best performance in identifying vintages and fermentation processes, with accuracies of 67.3% and 60.5%, respectively. Results demonstrate the effectiveness of the developed E-nose, which could be used to distinguish different wines based on their properties following selection of an optimal algorithm.

A Comparative Analysis of Machine Learning Models for Prediction of Insurance Uptake in Kenya

10.20944/preprints202010.0186.v1 ◽

2020 ◽

Author(s):

Nelson Yego ◽

Juma Kasozi ◽

Joseph Nkrunziza

Keyword(s):

Machine Learning ◽

Random Forest ◽

Characteristic Curve ◽

Confusion Matrix ◽

Gradient Boosting ◽

Support Vector ◽

Sampled Data ◽

Learning Models ◽

Machine Learning Models

The role of insurance in financial inclusion as well as in economic growth is immense. However, low uptake seems to impede the growth of the sector hence the need for a model that robustly predicts uptake of insurance among potential clients. In this research, we compared the performances of eight (8) machine learning models in predicting the uptake of insurance. The classifiers considered were Logistic Regression, Gaussian Naive Bayes, Support Vector Machines, K Nearest Neighbors, Decision Tree, Random Forest, Gradient Boosting Machines and Extreme Gradient boosting. The data used in the classification was from the 2016 Kenya FinAccess Household Survey. Comparison of performance was done for both upsampled and downsampled data due to data imbalance. For upsampled data, Random Forest classifier showed highest accuracy and precision compared to other classifiers but for down sampled data, gradient boosting was optimal. It is noteworthy that for both upsampled and downsampled data, tree-based classifiers were more robust than others in insurance uptake prediction. However, in spite of hyper-parameter optimization, the area under receiver operating characteristic curve remained highest for Random Forest as compared to other tree-based models. Also, the confusion matrix for Random Forest showed least false positives, and highest true positives hence could be construed as the most robust model for predicting the insurance uptake. Finally, the most important feature in predicting uptake was having a bank product hence bancassurance could be said to be a plausible channel of distribution of insurance products.

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

Remote Sensing ◽

10.3390/rs12142234 ◽

2020 ◽

Vol 12 (14) ◽

pp. 2234 ◽

Cited By ~ 6

Author(s):

Mostafa Emadi ◽

Ruhollah Taghizadeh-Mehrjardi ◽

Ali Cherati ◽

Majid Danesh ◽

Amir Mosavi ◽

...

Keyword(s):

Machine Learning ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Composite Surface ◽

Auxiliary Data ◽

Estimation of the soil organic carbon (SOC) content is of utmost importance in understanding the chemical, physical, and biological functions of the soil. This study proposes machine learning algorithms of support vector machines (SVM), artificial neural networks (ANN), regression tree, random forest (RF), extreme gradient boosting (XGBoost), and conventional deep neural network (DNN) for advancing prediction models of SOC. Models are trained with 1879 composite surface soil samples, and 105 auxiliary data as predictors. The genetic algorithm is used as a feature selection approach to identify effective variables. The results indicate that precipitation is the most important predictor driving 14.9% of SOC spatial variability followed by the normalized difference vegetation index (12.5%), day temperature index of moderate resolution imaging spectroradiometer (10.6%), multiresolution valley bottom flatness (8.7%) and land use (8.2%), respectively. Based on 10-fold cross-validation, the DNN model reported as a superior algorithm with the lowest prediction error and uncertainty. In terms of accuracy, DNN yielded a mean absolute error of 0.59%, a root mean squared error of 0.75%, a coefficient of determination of 0.65, and Lin’s concordance correlation coefficient of 0.83. The SOC content was the highest in udic soil moisture regime class with mean values of 3.71%, followed by the aquic (2.45%) and xeric (2.10%) classes, respectively. Soils in dense forestlands had the highest SOC contents, whereas soils of younger geological age and alluvial fans had lower SOC. The proposed DNN (hidden layers = 7, and size = 50) is a promising algorithm for handling large numbers of auxiliary data at a province-scale, and due to its flexible structure and the ability to extract more information from the auxiliary data surrounding the sampled observations, it had high accuracy for the prediction of the SOC base-line map and minimal uncertainty.