Data Mining Applied to Oil Well Using K-Means and DBSCAN

An economic evaluation of a new oil well is often required, and this evaluation depends heavily on how accurately production of the well can be estimated. Unfortunately, this kind of prediction is extremely difficult because of complex subsurface conditions of reservoirs. The industrial standard approach is to use either curve-fitting methods or complex and timeconsuming reservoir simulations. In this study, we attempted to improve upon the standard techniques by using a variety of neural network and data mining approaches. The approaches differ in terms of prediction model, data division strategy, method, tool used for implementation, and the interpretability of the models. The objective is to make use of the large amount of data readily available from private companies and public sources to enhance understanding of the petroleum production prediction task. Additional objectives include optimizing timing for initiation of advanced recovery processes and identifying candidate wells for production or injection.

Download Full-text

Data Mining and Machine Learning

10.1017/9781108564175 ◽

2020 ◽

Cited By ~ 2

Author(s):

Mohammed J. Zaki ◽

Wagner Meira, Jr

Keyword(s):

Machine Learning ◽

Data Mining

Download Full-text

The economics of selection of mail orders Drs. Zahavi and Levin are the masterminds behind the development of AMOS, a customized predictive modeling system for the Franklin Mint in Philadelphia, and GainSmarts, a general purpose data mining system that is the two-time winner of the KDD-CUP competition for the best data mining tools (1997 and 1998) sponsored by the American Association for Artificial Intelligence.

Journal of Interactive Marketing ◽

10.1002/dir.1016.abs ◽

2001 ◽

Vol 15 (3) ◽

pp. 53

Author(s):

Nissan Levin ◽

Jacob Zahavi

Keyword(s):

Artificial Intelligence ◽

Data Mining ◽

Predictive Modeling ◽

American Association ◽

General Purpose ◽

Mining System ◽

Data Mining System ◽

Mining Tools ◽

Selection Of

Download Full-text

Heart Rate Variability, Emotions, and Music

Journal of Psychophysiology ◽

10.1027/0269-8803/a000021 ◽

2010 ◽

Vol 24 (2) ◽

pp. 112-119 ◽

Cited By ~ 9

Author(s):

F. Riganello ◽

A. Candelieri ◽

M. Quintieri ◽

G. Dolce

Keyword(s):

Data Mining ◽

Heart Rate ◽

Heart Rate Variability ◽

Vegetative State ◽

Low Frequency ◽

Emotional Reactions ◽

Heart Beat ◽

Healthy Controls ◽

Frequency Spectra ◽

Emotional Value

The purpose of the study was to identify significant changes in heart rate variability (an emerging descriptor of emotional conditions; HRV) concomitant to complex auditory stimuli with emotional value (music). In healthy controls, traumatic brain injured (TBI) patients, and subjects in the vegetative state (VS) the heart beat was continuously recorded while the subjects were passively listening to each of four music samples of different authorship. The heart rate (parametric and nonparametric) frequency spectra were computed and the spectra descriptors were processed by data-mining procedures. Data-mining sorted the nu_lf (normalized parameter unit of the spectrum low frequency range) as the significant descriptor by which the healthy controls, TBI patients, and VS subjects’ HRV responses to music could be clustered in classes matching those defined by the controls and TBI patients’ subjective reports. These findings promote the potential for HRV to reflect complex emotional stimuli and suggest that residual emotional reactions continue to occur in VS. HRV descriptors and data-mining appear applicable in brain function research in the absence of consciousness.

Download Full-text