Search

Geochemical study of Kazhdumi and Pabdeh Formations as potential source rocks in Gachsaran Oilfield demonstrates that the Kazhdumi Formation has a fair to good capability of hydrocarbon generation and predominately contains type II-III kerogen. On the other hand, the Pabdeh Formation has a poor to good petroleum potential and contains different kerogen types, including type II, type II-III, type III and even for one sample, type IV, indicating different depositional conditions for this formation. The geochemical log of the Kazhdumi Formation shows that there is a close correlation between different geological parameters as noticed prominently in well number 55, which suggests the more extensive the anoxic condition, the higher the petroleum potential is for Kazhdumi Formation. By contrast, a poor correlation between TOC and other Rock–Eval-derived parameters for the Pabdeh Formation at a depth of more than 2100 m may demonstrate the inert organic matter and mineral matrix effects at this depth interval. However, biomarkers show differences in lithology and depositional environment for the Kazhdumi Formation in well numbers 55 and 83. On the other hand, the Pabdeh Formation has a mixed lithology (carbonate-shale) deposited in a marine setting under suboxic–anoxic condition. Moreover, thermal maturity indicators suggest that Pabdeh and Kazhdumi Formations are immature and early mature, respectively.

The current study is the first report of estimating kerogen type from petrophysical well logs implementing various machine learning techniques. The methodology is explained through a case study from the Perth Basin, Western Australia. Firstly, the statistical relationships between the petrophysical data (including gamma ray (GR), sonic (DTCO), neutron (NEUT) and density (RHOB) logs) and the Rock-Eval derived hydrogen index (HI) and oxygen index (OI) are investigated. Afterwards, the various machine learning (ML) techniques, including radial basis function (RBF) and multi-layer perceptron (MLP) artificial neural networks, random forest (RF), support vector machine (SVM) and decision tree (DT), are applied to estimate the hydrogen and oxygen index values. Additionally, the MLP network is optimized by the grey wolf optimization (GWO), genetic algorithm (GA) and particle swarm optimization (PSO). The outputs of the various ML approaches are integrated, employing both simple averaging and weighted averaging committee machines. Three statistical parameters of root mean square error (RMSE), mean absolute error (MAE) and correlation coefficient (R) are employed to evaluate and compare the performance of the machine learning ensembles. In general, employing optimization algorithms on the MLP network reinforces the network's performance for the hydrogen index (HI) estimation by increasing overall R and decreasing RMSE and MAE for test data. Likewise, RMSE and MAE values of test data for the oxygen index (OI) decrease using all three optimizers, although R values decrease as well. However, GWO is the most efficient optimizer in diminishing RMSE and MAE and rising R values of test data for the hydrogen index estimation. This algorithm also provides the minimum RMSE and MAE for the oxygen index (OI) estimation. Ultimately, among the proposed intelligent approaches, the weighted averaging committee machine (WACM) provides the maximum correlation coefficient (R) and minimum errors (RMSE and MAE) for both hydrogen index (HI) and oxygen index (OI) estimating. The estimated oxygen and hydrogen indices values are then successfully employed to predict the kerogen types based on the van Krevelen diagram.

Solid scales can cause significant problems in oil production and transmission systems such as oil flow rate reduction. Wax is one of the most critical substances that are highly prone to precipitate and deposit in oil pipelines. This occurrence typically happens in low temperatures, and can extremely affect the flow rate. In the wax deposition process, wax disappearance temperature (WDT) is a crucial factor since it denotes the lowest temperature, at which wax deposits melt and the consequences of wax deposition vanish. In this research, smart models were utilized to predict WDT as a function of molar mass and pressure according to a comprehensive database. The proposed intelligent models are radial basis function (RBF) and multilayer perceptron (MLP) neural networks, adaptive neuro-fuzzy inference system (ANFIS), random forest (RF), extra tree (ET), and decision tree (DT). The MLP networks were trained with Bayesian Regularization (BR) and Levenberg-Marquardt (LM) algorithms, and the ANFIS models were coupled with three optimization algorithms, namely Cultural Algorithm (CA), Biogeography-based Optimization (BBO), and Teaching-Learning-Based Optimization (TLBO). Results demonstrate that the developed RF model could present an outstanding performance and provide predictions for WDT with the lowest average absolute percent relative error (AAPRE = 0.246%), the maximum coefficient of determination (for predicting = 0.993), and minimum root mean squared error (RMSE = 1.01). Trend analysis showed that increasing pressure and molar mass leads to wax disappearance temperature increase. Lastly, outlier discovery was performed using the Leverage approach to recognize the suspected data points. The outlier detection found that only 6 points (out of 346) are located in the upper and lower suspected data zones.

In this study several major source rocks: Kazhdumi, Pabdeh, and Gurpi formations, along with crude oils from the Asmari and Bangestan reservoirs in the Gachsaran oilfield, southwestern Iran, were investigated from the organic geochemistry point of view. Results indicate that the Kazhdumi and Pabdeh formations have excellent generation potential and are mature and immature source rocks, respectively. In contrast, the Gurpi Formation has lower petroleum generation potential. The organic matter in the Kazhdumi and Pabdeh formations in the neighboring synclines within the Gachsaran oilfield is in the late and peak oil generation stages, respectively. SARA composition by Liquid Chromatography performed on four crude oils produced from these source rocks suggest a paraffinic-naphthenic composition. The source rocks had carbonate and shale lithology. Distinct biomarkers point to an open marine environment characterized by marine kerogen Type II and mixed Types II/III deposited under anoxic-suboxic depositional conditions, although. The presence of relatively high amounts of oleanane in the oils points to contribution from a terrigenous source. Based on biomarkers, the four oils exhibit similar thermal maturity, which is equivalent to the primary stage of oil generation. The star diagrams of various normal alkanes and biomarker ratios show that the four crude oil have high similarities, which suggests a single source origin. Nonetheless, utilizing different ML methods of K-means Clustering, Fuzzy C-means clustering (FCM), Comptlayar Neural Network, Construction of agglomerative clusters, and the obtained dendrogram all suggest that there are two oil families in the Gachsaran oil field. Furthermore, geochemical parameters including specific biomarkers denote the contribution of the Kazhdumi and Pabdeh formations in the Gachsaran oil field whereby charges of mixed origins at different reservoir horizons of Asmari and Bangestan can be identified. Ultimately, two scenarios for the presence of oleanane in Bangestan reservoir are envisaged: 1) connectivity of the Asmari and Bangestan reservoirs as a result of natural fracturing, and 2) emplacement of the Pabdeh Formation near the vicinity of the Bangestan reservoir as a result of thrust faulting. Overall, this study demonstrated that integration of data analytics (ML) methods with conventional geochemical techniques can precisely delineate the correlation between the generated oil and the source rocks.