Carbonate reservoir rock type classification using comparison of Naïve Bayes and Random Forest method in field “S” East Java

Abstract The Harash Formation was previously known as the Ruaga A and is considered to be one of the most productive reservoirs in the Zelten field in terms of reservoir quality, areal extent, and hydrocarbon quantity. To date, nearly 70 wells were drilled targeting the Harash reservoir. A few wells initially naturally produced but most had to be stimulated which reflected the field drilling and development plan. The Harash reservoir rock typing identification was essential in understanding the reservoir geology implementation of reservoir development drilling program, the construction of representative reservoir models, hydrocarbons volumetric calculations, and historical pressure-production matching in the flow modelling processes. The objectives of this study are to predict the permeability at un-cored wells and unsampled locations, to classify the reservoir rocks into main rock typing, and to build robust reservoir properties models in which static petrophysical properties and fluid properties are assigned for identified rock type and assessed the existed vertical and lateral heterogeneity within the Palaeocene Harash carbonate reservoir. Initially, an objective-based workflow was developed by generating a training dataset from open hole logs and core samples which were conventionally and specially analyzed of six wells. The developed dataset was used to predict permeability at cored wells through a K-mod model that applies Neural Network Analysis (NNA) and Declustring (DC) algorithms to generate representative permeability and electro-facies. Equal statistical weights were given to log responses without analytical supervision taking into account the significant log response variations. The core data was grouped on petrophysical basis to compute pore throat size aiming at deriving and enlarging the interpretation process from the core to log domain using Indexation and Probabilities of Self-Organized Maps (IPSOM) classification model to develop a reliable representation of rock type classification at the well scale. Permeability and rock typing derived from the open-hole logs and core samples analysis are the main K-mod and IPSOM classification model outputs. The results were propagated to more than 70 un-cored wells. Rock typing techniques were also conducted to classify the Harash reservoir rocks in a consistent manner. Depositional rock typing using a stratigraphic modified Lorenz plot and electro-facies suggest three different rock types that are probably linked to three flow zones. The defined rock types are dominated by specifc reservoir parameters. Electro-facies enables subdivision of the formation into petrophysical groups in which properties were assigned to and were characterized by dynamic behavior and the rock-fluid interaction. Capillary pressure and relative permeability data proved the complexity in rock capillarity. Subsequently, Swc is really rock typing dependent. The use of a consistent representative petrophysical rock type classification led to a significant improvement of geological and flow models.

Download Full-text

Penerapan Klasifikasi Kueri untuk Meningkatkan Efektivitas Mesin Pencari

Seminar Nasional Official Statistics ◽

10.34123/semnasoffstat.v2021i1.914 ◽

2021 ◽

Vol 2021 (1) ◽

pp. 1012-1018

Author(s):

Handy Geraldy ◽

Lutfi Rahmatuti Maghfiroh

Keyword(s):

Machine Learning ◽

Random Forest ◽

Naive Bayes ◽

Naïve Bayes ◽

Gradient Boosting

Dalam menjalankan peran sebagai penyedia data, Badan Pusat Statistik (BPS) memberikan layanan akses data BPS bagi masyarakat. Salah satu layanan tersebut adalah fitur pencarian di website BPS. Namun, layanan pencarian yang diberikan belum memenuhi harapan konsumen. Untuk memenuhi harapan konsumen, salah satu upaya yang dapat dilakukan adalah meningkatkan efektivitas pencarian agar lebih relevan dengan maksud pengguna. Oleh karena itu, penelitian ini bertujuan untuk membangun fungsi klasifikasi kueri pada mesin pencari dan menguji apakah fungsi tersebut dapat meningkatkan efektivitas pencarian. Fungsi klasifikasi kueri dibangun menggunakan model machine learning. Kami membandingkan lima algoritma yaitu SVM, Random Forest, Gradient Boosting, KNN, dan Naive Bayes. Dari lima algoritma tersebut, model terbaik diperoleh pada algoritma SVM. Kemudian, fungsi tersebut diimplementasikan pada mesin pencari yang diukur efektivitasnya berdasarkan nilai precision dan recall. Hasilnya, fungsi klasifikasi kueri dapat mempersempit hasil pencarian pada kueri tertentu, sehingga meningkatkan nilai precision. Namun, fungsi klasifikasi kueri tidak memengaruhi nilai recall.

Download Full-text

Predicting heart ailment in patients with varying number of features using data mining techniques

International Journal of Informatics and Communication Technology (IJ-ICT) ◽

10.11591/ijict.v8i1.pp56-62 ◽

2019 ◽

Vol 8 (1) ◽

pp. 56

Author(s):

T R Stella Mary ◽

Shoney Sebastian

Keyword(s):

Data Mining ◽

Heart Disease ◽

Random Forest ◽

Naive Bayes ◽

Heart Diseases ◽

Naïve Bayes ◽

Bayes Classifier ◽

Data Mining Techniques ◽

Using Data ◽

Almost All

<span>Data mining can be defined as a process of extracting unknown, verifiable and possibly helpful data from information. Among the various ailments, heart ailment is one of the primary reason behind death of individuals around the globe, hence in order to curb this, a detailed analysis is done using Data Mining. Many a times we limit ourselves with minimal attributes that are required to predict a patient with heart disease. By doing so we are missing on a lot of important attributes that are main causes for heart diseases. Hence, this research aims at considering almost all the important features affecting heart disease and performs the analysis step by step with minimal to maximum set of attributes using Data Mining techniques to predict heart ailments. The various classification methods used are Naïve Bayes classifier, Random Forest and Random Tree which are applied on three datasets with different number of attributes but with a common class label. From the analysis performed, it shows that there is a gradual increase in prediction accuracies with the increase in the attributes irrespective of the classifiers used and Naïve Bayes and Random Forest algorithms comparatively outperforms with these sets of data.</span>

Download Full-text

Sequence Based Prediction of DNA-Binding Proteins Based on Hybrid Feature Selection Using Random Forest and Gaussian Naïve Bayes

PLoS ONE ◽

10.1371/journal.pone.0086703 ◽

2014 ◽

Vol 9 (1) ◽

pp. e86703 ◽

Cited By ~ 81

Author(s):

Wangchao Lou ◽

Xiaoqing Wang ◽

Fan Chen ◽

Yixiao Chen ◽

Bo Jiang ◽

...

Keyword(s):

Feature Selection ◽

Random Forest ◽

Dna Binding ◽

Binding Proteins ◽

Naive Bayes ◽

Dna Binding Proteins ◽

Naïve Bayes

Download Full-text

Preliminary Screening of COVID-19 Infection Employing Machine Learning Techniques From Simple Blood Profile

International Journal of Quantitative Structure-Property Relationships ◽

10.4018/ijqspr.2021070103 ◽

2021 ◽

Vol 6 (3) ◽

pp. 35-47

Author(s):

Anirudh Reddy Cingireddy ◽

Robin Ghosh ◽

Supratik Kar ◽

Venkata Melapu ◽

Sravanthi Joginipeli ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Naive Bayes ◽

Albert Einstein ◽

Naïve Bayes ◽

Machine Learning Techniques ◽

Support Vector ◽

Blood Profile ◽

Molecular Tests ◽

Large Populations

Frequent testing of the entire population would help to identify individuals with active COVID-19 and allow us to identify concealed carriers. Molecular tests, antigen tests, and antibody tests are being widely used to confirm COVID-19 in the population. Molecular tests such as the real-time reverse transcription-polymerase chain reaction (rRT-PCR) test will take a minimum of 3 hours to a maximum of 4 days for the results. The authors suggest using machine learning and data mining tools to filter large populations at a preliminary level to overcome this issue. The ML tools could reduce the testing population size by 20 to 30%. In this study, they have used a subset of features from full blood profile which are drawn from patients at Israelita Albert Einstein hospital located in Brazil. They used classification models, namely KNN, logistic regression, XGBooting, naive Bayes, decision tree, random forest, support vector machine, and multilayer perceptron with k-fold cross-validation, to validate the models. Naïve bayes, KNN, and random forest stand out as the most predictive ones with 88% accuracy each.

Download Full-text