A novel model for predicting tight sandstone reservoir permeability

2022 ◽  
Vol 29 (1) ◽  
pp. 75
Author(s):  
Lili Sun ◽  
Xining Hao ◽  
Hongen Dou ◽  
Caspar Daniel Adenutsi ◽  
Wenli Liu
Keyword(s):  
Tight Sandstone ◽  
Reservoir Permeability ◽  
Sandstone Reservoir ◽  
Novel Model

A novel model for predicting tight sandstone reservoir permeability

2022 ◽  
Vol 29 (1) ◽  
pp. 75
Author(s):  
Wenli Liu ◽  
Hongen Dou ◽  
Caspar Daniel Adenutsi ◽  
Lili Sun ◽  
Xining Hao
Keyword(s):  
Tight Sandstone ◽  
Reservoir Permeability ◽  
Sandstone Reservoir ◽  
Novel Model

scholarly journals Permeability Predictions for Tight Sandstone Reservoir Using Explainable Machine Learning and Particle Swarm Optimization

Geofluids ◽  
2022 ◽  
Vol 2022 ◽  
pp. 1-15
Author(s):  
Jing-Jing Liu ◽  
Jian-Chao Liu
Keyword(s):  
Machine Learning ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Learning Models ◽  
Tight Sandstone ◽  
Swarm Optimization ◽  
Permeability Prediction ◽  
Reservoir Permeability ◽  
Sandstone Reservoir ◽  
Sandstone Reservoirs

High-precision permeability prediction is of great significance to tight sandstone reservoirs. However, while considerable progress has recently been made in the machine learning based prediction of reservoir permeability, the generalization of this approach is limited by weak interpretability. Hence, an interpretable XGBoost model is proposed herein based on particle swarm optimization to predict the permeability of tight sandstone reservoirs with higher accuracy and robust interpretability. The porosity and permeability of 202 core plugs and 6 logging curves (namely, the gamma-ray (GR) curve, the acoustic curve (AC), the spontaneous potential (SP) curve, the caliper (CAL) curve, the deep lateral resistivity (RILD) curve, and eight lateral resistivity (RFOC) curve) are extracted along with three derived variables (i.e., the shale content, the AC slope, and the GR slope) as data sets. Based on the data preprocessing, global and local interpretations are performed according to the Shapley additive explanations (SHAP) analysis, and the redundant features in the data set are screened to identify the porosity, AC, CAL, and GR slope as the four most important features. The particle swarm optimization algorithm is then used to optimize the hyperparameters of the XGBoost model. The prediction results of the PSO-XGBoost model indicate a superior performance compared with that of the benchmark XGBoost model. In addition, the reliable application of the interpretable PSO-XGBoost model in the prediction of tight sandstone reservoir permeability is examined by comparing the results with those of two traditional mathematical regression models, five machine learning models, and three deep learning models. Thus, the interpretable PSO-XGBoost model is shown to have more advantages in permeability prediction along with the lowest root mean square error, thereby confirming the effectiveness and practicability of this method.

scholarly journals A reservoir quality evaluation approach for tight sandstone reservoirs based on the gray correlation algorithm: A case study of the Chang 6 layer in the W area of the as oilfield, Ordos Basin

2021 ◽  
pp. 014459872199851
Author(s):  
Yuyang Liu ◽  
Xiaowei Zhang ◽  
Junfeng Shi ◽  
Wei Guo ◽  
Lixia Kang ◽  
...  
Keyword(s):  
Quality Evaluation ◽  
Comprehensive Evaluation ◽  
Ordos Basin ◽  
Reservoir Quality ◽  
Pore Throat ◽  
Tight Sandstone ◽  
Evaluation Approach ◽  
Correlation Algorithm ◽  
Gray Correlation ◽  
Sandstone Reservoir

As an important type of unconventional hydrocarbon, tight sandstone oil has great present and future resource potential. Reservoir quality evaluation is the basis of tight sandstone oil development. A comprehensive evaluation approach based on the gray correlation algorithm is established to effectively assess tight sandstone reservoir quality. Seven tight sandstone samples from the Chang 6 reservoir in the W area of the AS oilfield in the Ordos Basin are employed. First, the petrological and physical characteristics of the study area reservoir are briefly discussed through thin section observations, electron microscopy analysis, core physical property tests, and whole-rock and clay mineral content experiments. Second, the pore type, throat type and pore and throat combination characteristics are described from casting thin sections and scanning electron microscopy. Third, high-pressure mercury injection and nitrogen adsorption experiments are optimized to evaluate the characteristic parameters of pore throat distribution, micro- and nanopore throat frequency, permeability contribution and volume continuous distribution characteristics to quantitatively characterize the reservoir micro- and nanopores and throats. Then, the effective pore throat frequency specific gravity parameter of movable oil and the irreducible oil pore throat volume specific gravity parameter are introduced and combined with the reservoir physical properties, multipoint Brunauer-Emmett-Teller (BET) specific surface area, displacement pressure, maximum mercury saturation and mercury withdrawal efficiency parameters as the basic parameters for evaluation of tight sandstone reservoir quality. Finally, the weight coefficient of each parameter is calculated by the gray correlation method, and a reservoir comprehensive evaluation indicator (RCEI) is designed. The results show that the study area is dominated by types II and III tight sandstone reservoirs. In addition, the research method in this paper can be further extended to the evaluation of shale gas and other unconventional reservoirs after appropriate modification.

Sign in / Sign up

Export Citation Format

Share Document