Application of Class-Based Machine Learning for Potential Hydrocarbon Zones Identification: A Case Study

At times, petrophysicists are expected to evaluate potential of the well in time-constraint situations while maintaining consistency of the parameters and interpretation. Other than that, some challenges may also occur when working with older wells where the dataset are not as complete as current wells and processing parameters are not transferable. In this case study, class-based machine learning (CBML) approach is used to perform petrophysical evaluation to identify potential hydrocarbon zones in the target wells. The objective is to find solution to improve efficiency and consistency in those challenging situations. A class-based machine learning (CBML) workflow uses cross-entropy clustering (CEC)-Gaussian mixture model (GMM)- hidden Markov model (HMM) workflow that identifies locally stationary zones sharing similar statistical properties in logs, and then propagates zonation information from training wells to other wells (Jain, et al., 2019). The workflow is divided into two (2) main steps: training and prediction. Key wells which best represent the formation in the field are used to train the model. This approach automatically generates the number of cluster (class) using unsupervised or supervised depending on the input data. The model from key wells data is then used to reconstruct inputs and outputs along with uncertainty and outlier flags. This allows expert to QC and validate the generated class which is the most crucial part of the workflow. Once the model from the key wells has been built, it is applied to predict the same set of zones in the new wells that require interpretation and predict output curves. The result matched well over the good data interval with the petrophysical interpretation result from conventional approach. While in the bad interval, some discrepancies can be observed. The discrepancy was identified easily from the uncertainty and outlier flags which helps petrophysicists to identify which interval to fix or re-evaluate. Some requirements to condition the input were observed (no missing value over the input and outlier) to get the best result. A number of inputs used in the model need to be consistent over the set of wells used in the training and prediction target. This machine learning workflow speeds-up the petrophysical analysis process, reduce analyst bias and improve consistency result between one well to another within the same field. This machine learning application can also generate auto log QC, zonation class for rock typing also reconstructed logs which enrich the petrophysical interpretation even for wells with limited logs availability. This paper offers practical examples and lessons learned of CBML approach application to perform petrophysical evaluation and identify potential zones while being in time-constrained and limited resource situations.

Exploration of Hidden Hydrocarbons in Old Wells Magid Field - Sirte Basin, Libya

It is increasingly important to improve field productivity in today's competitive market. One way to achieve this, is to add new wells which are expensive and time consuming. The other alternative is to identify bypassed hydrocarbons, track changes in saturations and detect movement of reservoir fluid contacts from existing well bores already in place. It is considerably more cost effective and often more environmentally friendly to explore for those hidden hydrocarbons in old wells rather than drill new wells. As the field matures, there is a need to reevaluate the formation in older reservoirs and to focus the development strategy and approach on bypassed oil pockets and depletion levels in producing intervals. The ability to acquire essential logging data behind casing adds a new dimension to cased hole formation evaluation for locating and evaluating potential hydrocarbon zones in a mature field as in Magid field. A basic petrophysical evaluation was performed incorporating the data recorded behind casing by applying {Cased Hole Formation Resistivity Logging (CHFRL)} in each of these wells. Based on the analysis of cased hole formation evaluation results. The un-depleted intervals were commercially exploited adding reserve to the asset. Keywards: Hydrocarbon zones, Majid Field, Sirte Basin, Libya, CHFRL

Petrophysical Evaluation of Mauddud Formation in Selected Wells from Ratawi Oil Field, Southern Iraq

The objective of this paper is determining the petrophysical properties of the Mauddud Formation (Albian-Early Turonian) in Ratawi Oil Field depending on the well logs data by using interactive petrophysical software IP (V4.5). We evaluated parameters of available logs that control the reservoir properties of the formation, including shale volume, effective porosity, and water saturation. Mauddud Formation is divided into five units, which are distinguished by various reservoir characteristics. These units are A, B, C, D, and E. Through analyzing results of the computer processed interpretation (CPI) of available wells, we observed that the main reservoir units are B and D, being distinguished by elevated values of effective porosity (10%-32%) and oil saturation (95%-30%) with low shale content (6%-30%). Whereas, units A, C, and E were characterized by low or non-reservoir properties, due to high water saturation and low values of effective porosity caused by increased volume shale.

Petrophysical characterization for Thebes and Mutulla reservoirs in Rabeh East Field, Gulf of Suez Basin, via well logging interpretation

The current work assesses the sandstones of the Mutulla Formation as well as the limestone of the Thebes Formation for being promising new oil reservoirs in Rabeh East field at the southern portion of the Gulf of Suez Basin. This assessment has been achieved through petrophysical evaluation of wireline logs for three wells (RE-8, RE-22 and RE-25). The visual analysis of well logs data revealed that RE-25 Well is the only well demonstrating positive criteria in five zones for being potential oil reservoirs. The favourable zone within Thebes Formation locates between depths 5084 ft and 5100 ft (Zone A). However, the other positive zones in Mutulla Formation occur between depths: 5403.5–5413.5 ft (Zone B), 5425.5–5436 ft (Zone C), 5488–5498 ft (Zone D) and 5558.5–5563.5 ft (Zone E). The quantitative evaluation shows that the Zone A of Thebes Formation is the best oil-bearing zone in RE-25 Well in terms of reservoir quality since it exhibits lowest shale volume (0.07), minimum water saturation (0.23) and lowest bulk volume of water (0.03). These limestone beds include type of secondary porosity beside the existing primary porosity. On the other hand, the sandstones of Mutulla Formation in RE-25 contain four reservoir zones (B, C, D and E) with the total net pay thickness of 35.5 ft. Moreover, the obtained results revealed that it is expected for zones B, C and D to produce oil without water but Zone E will produce oil with water.

Petrophysical evaluation of sandstone gas reservoir using integrated well logs and core data for the Lower Cretaceous Kharita formation, Western Desert, Egypt

This study aims to evaluate Kharita gas reservoir to enhance the production. The increase in water-cut ratio reduces the left hydrocarbons’ amount behind pipe. Accurate determination of pore throats, pores connectivity and fluid distribution are central elements in improved reservoir description. The integration of core and logging data responses is often used to draw inferences about lithology, depositional sequences, facies, and fluid content. These inferences are based on petrophysical models utilizing correlations among tools’ responses as well as rocks and fluids properties. Upper Kharita Formation produces gas and condensate from the clastic sandstone in Badr-3 field, western desert of Egypt. It consists mainly of sandstone with shale intercalations. It is subdivided into three sub-units Kharita A, Kharita B and Kharita C that are in pressure communication. Hence, a new further investigation and review for the previously calculated GIIP (gas initially in place) was initiated. The results of this study yielded that the main uncertainty in the volumetric calculations was the petrophysical evaluation; subsequently, a new unconventional petrophysical evaluation approach was performed. The sands thickness in Upper Kharita Formation varies between more than 9 up and more than 61 m with average porosity values range between 0.08 and 0.17 PU while the average permeability values range between 1.89 and 696.66 mD. The average hydrocarbon saturation values range between 46 and 97%. The sands thickness in Upper Kharita Formation varies between more than 9 up and more than 61 m with average porosity values range between 0.08 and 0.17 PU while the average permeability values range between 1.89 and 696.66 mD. The average hydrocarbon saturation values range between 46 and 97%. Reservoir shale cutoff of 55% by using cross-plot between shale volume and porosity (Toby Darling concept) was utilized to discriminate the reservoir from non-reservoir sections. The porosity model was used to calculate reservoir porosity, using the density log. The Archie and saturation/height function models were used to calculate the water saturation and used to calibrate the water saturation in the transition zone. The porosity–permeability (POR-PERM) transform equation was used to estimate the reservoir connectivity (absolute permeability) for the four petrophysical facies (High Quality Reservoir, Moderate Quality Reservoir, Low Quality Reservoir and Highly Shale Reservoir). Core data have shown variations in reservoir quality parameters (porosity and permeability) from one well to the other. Integration of all the reservoir pressures indicated that there are different fluid types (oil, gas and water) in the Upper Kharita Formation level. The saturation/height function model was used to calibrate the saturation in the transition zone. The integration of geological core and geophysical log data helped to conduct a comprehensive petrophysical assessment of Upper Kharita Formation for a better estimation of the reservoir and to achieve a better understanding of the water encroachment in the Upper Kharita reservoir. The big challenge is the determination of the most correct model for calculating porosity, permeability and water saturation in this reservoir of different quality sand. The new petrophysical evaluation resulted in doubling the volumes in Upper Kharita reservoir and so a perforation campaign was performed to confirm the new volumetric calculations, which showed a good match with the model results. Hence, a new well was drilled targeting the low quality sand and found them with high pressure almost near virgin pressure.

Reservoir modeling and petrophysical evaluation of kanga field onshore Niger delta.

Reservoir sands from seven wells in Kanga Field in the Onshore Niger Delta was subjected to both petrophysical evaluation and reservoir modeling. Methodologies used are standard methods used in reservoir modeling and petrophysical evaluation. Results from reservoir modeling, shows that six synthetics and four antithetic faults have been identified and these faults are the main structural closure for hydrocarbon accumulation in Kanga Field. Petrophysical analysis showed porosity ranging from (25-27%), (16-27%) and (11-17%) for J100, K100 and L100 respectively. Modeled porosity showed high porosity in J100 and the central part of K100 reservoir. While, low porosity/; is recorded in L100. Water saturation ranges from 20 to 90% in the J100 reservoir, the lowest water saturation value was at the NE, NW and central part of the reservoir. Oil water contact reveals pockets of hydrocarbon in J100 and L100 reservoir. The bulk volume of hydrocarbon saturation closure is (21,954.37) arceft, (209,613.7) acreft and 46,025.51) acreft for J100, K100, and L100 reservoirs respectively. The estimated volumetric for P90 are (4,648,755.06) STB, (16,545,452.38) STB and (9,976,551.38) STB respectively. This study de that the field is viable for hydrocarbon exploration.