Machine learning has a significant advantage for many difficulties in the oil and gas industry, especially when it comes to resolving complex challenges in reservoir characterization. Permeability is one of the most difficult petrophysical parameters to predict using conventional logging techniques. Clarifications of the work flow methodology are presented alongside comprehensive models in this study. The purpose of this study is to provide a more robust technique for predicting permeability; previous studies on the Bazirgan field have attempted to do so, but their estimates have been vague, and the methods they give are obsolete and do not make any concessions to the real or rigid in order to solve the permeability computation. To verify the reliability of training data for zone-by-zone modeling, we split the scenario into two scenarios and applied them to seven wells' worth of data. Moreover, all wellbore intervals were processed, for instance, all five units of Mishrif formation. According to the findings, the more information we have, the more accurate our forecasting model becomes. Multi-resolution graph-based clustering has demonstrated its forecasting stability in two instances by comparing it to the other five machine learning models.
The unconventional techniques called “the quick look techniques”, have been developed to present well log data calculations, so that they may be scanned easily to identify the zones that warrant a more detailed analysis, these techniques have been generated by service companies at the well site which are among the useful, they provide the elements of information needed for making decisions quickly when time is of essence. The techniques used in this paper are:
- Apparent resistivity Rwa
- Rxo /Rt
The above two methods had been used to evaluate Nasiriyah oil field formations (well-NS-3) to discover the hydrocarbon bearing formations. A compu
... Show MoreDeep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod
... Show MorePsychological research centers help indirectly contact professionals from the fields of human life, job environment, family life, and psychological infrastructure for psychiatric patients. This research aims to detect job apathy patterns from the behavior of employee groups in the University of Baghdad and the Iraqi Ministry of Higher Education and Scientific Research. This investigation presents an approach using data mining techniques to acquire new knowledge and differs from statistical studies in terms of supporting the researchers’ evolving needs. These techniques manipulate redundant or irrelevant attributes to discover interesting patterns. The principal issue identifies several important and affective questions taken from
... Show MoreMany oil and gas processes, including oil recovery, oil transportation, and petroleum processing, are negatively impacted by the precipitation and deposition of asphaltene. Screening methods for determining the stability of asphaltenes in crude oil have been developed due to the high cost of remediating asphaltene deposition in crude oil production and processing. The colloidal instability index, the Asphaltene-resin ratio, the De Boer plot, and the modified colloidal instability index were used to predict the stability of asphaltene in crude oil in this study. The screening approaches were investigated in detail, as done for the experimental results obtained from them. The factors regulating the asphaltene precipitation are different fr
... Show MorePermeability is one of the essential petrophysical properties of rocks, reflecting the rock's ability to pass fluids. It is considered the basis for building any model to predict well deliverability. Yamama formation carbonate rocks are distinguished by sedimentary cycles that separate formation into reservoir units and insulating layers, a very complex porous system caused by secondary porosity due to substitute and dissolution processes. Those factors create permeability variables and vary significantly. Three ways used for permeability calculation, the firstly was the classical method, which only related the permeability to the porosity, resulting in a weak relationship. Secondly, the flow zone indicator (FZI) was divided reservoir into
... Show MoreCorrelation equations for expressing the boiling temperature as direct function of liquid composition have been tested successfully and applied for predicting azeotropic behavior of multicomponent mixtures and the kind of azeotrope (minimum, maximum and saddle type) using modified correlation of Gibbs-Konovalov theorem. Also, the binary and ternary azeotropic point have been detected experimentally using graphical determination on the basis of experimental binary and ternary vapor-liquid equilibrium data.
In this study, isobaric vapor-liquid equilibrium for two ternary systems: “1-Propanol – Hexane – Benzene” and its binaries “1-Propanol –
... Show MoreMany consumers of electric power have excesses in their electric power consumptions that exceed the permissible limit by the electrical power distribution stations, and then we proposed a validation approach that works intelligently by applying machine learning (ML) technology to teach electrical consumers how to properly consume without wasting energy expended. The validation approach is one of a large combination of intelligent processes related to energy consumption which is called the efficient energy consumption management (EECM) approaches, and it connected with the internet of things (IoT) technology to be linked to Google Firebase Cloud where a utility center used to check whether the consumption of the efficient energy is s
... Show MoreAbstract
A surface fitting model is developed based on calorimeter data for two famous brands of household compressors. Correlation equations of ten coefficient polynomials were found as a function of refrigerant saturating and evaporating temperatures in range of (-35℃ to -10℃) using Matlab software for cooling capacity, power consumption, and refrigerant mass flow rate.
Additional correlations equations for these variables as a quick choice selection for a proper compressor use at ASHRAE standard that cover a range of swept volume range (2.24-11.15) cm3.
The result indicated that these surface fitting models are accurate with in ± 15% for 72 compressors model of cooling cap
... Show MoreToday, there are large amounts of geospatial data available on the web such as Google Map (GM), OpenStreetMap (OSM), Flickr service, Wikimapia and others. All of these services called open source geospatial data. Geospatial data from different sources often has variable accuracy due to different data collection methods; therefore data accuracy may not meet the user requirement in varying organization. This paper aims to develop a tool to assess the quality of GM data by comparing it with formal data such as spatial data from Mayoralty of Baghdad (MB). This tool developed by Visual Basic language, and validated on two different study areas in Baghdad / Iraq (Al-Karada and Al- Kadhumiyah). The positional accuracy was asses
... Show More