Reservoir evaluation using petrophysics informed machine learning:A case study

relationships between logging data and reservoir parameters.We compare our method’s performances using two datasets and evaluate the influences of multi-task learning,model structure,transfer learning,and petrophysics informed machine learning(PIML).Our experiments demonstrate that PIML significantly enhances the performance of formation evaluation,and the structure of residual neural network is optimal for incorporating petrophysical constraints.Moreover,PIML is less sensitive to noise.These findings indicate that it is crucial to integrate data-driven machine learning with petrophysical mechanism for the application of artificial intelligence in oil and gas exploration.

Pore structure effect on reservoir electrical properties and well logging evaluation

The reservoir pore structure controls the reservoir quality and resistivity response of hydrocarbon-bearing zones and thus, critically affects logging interpretation. We use petrophysical data in three types of reservoir with different pore structure characteristics to show that the complexity of pore structure had a significant effect on the effective porosity and permeability regardless of geological factors responsible for the formation of pore structure. Moreover,, the distribution and content of conductive fluids in the reservoir varies dramatically owing to pore structure differences, which also induces resistivity variations in reservoir rocks. Hence, the origin of low-resistivity hydrocarbon-bearing zones, except for those with conductive matrix and mud filtrate invasion, is attributed to the complexity of the pore structures. Consequently, reservoir-specific evaluation models, parameters, and criteria should be chosen for resistivity log interpretation to make a reliable evaluation of reservoir quality and fluids.

Evaluating reservoir suitability for large-scale hydrogen storage:A preliminary assessment considering reservoir properties

With rising demand for clean energy,global focus turns to finding ideal sites for large-scale underground hydrogen storage(UHS)in depleted petroleum reservoirs.A thorough preliminary reservoir evaluation before hydrogen(H_(2))injection is crucial for UHS success and safety.Recent criteria for UHS often emphasize economics and chemistry,neglecting key reservoir attributes.This study introduces a comprehensive framework for the reservoir-scale preliminary assessment,specifically tailored for long-term H_(2) storage within depleted gas reservoirs.The evaluation criteria encompass critical components,including reservoir geometry,petrophysical properties,tectonics,and formation fluids.To illustrate the practical application of this approach,we assess the Barnett shale play reservoir parameters.The assessment unfolds through three key stages:(1)A systematic evaluation of the reservoir's properties against our comprehensive screening criteria determines its suitability for H_(2) storage.(2)Using both homogeneous and multilayered gas reservoir models,we explore the feasibility and efficiency of H_(2) storage.This phase involves an in-depth examination of reservoir behavior during the injection stage.(3)To enhance understanding of UHS performance,sensitivity analyses investigate the impact of varying reservoir dimensions and injection/production pressures.The findings reveal the following:(a)Despite potential challenges associated with reservoir compaction and aquifer support,the reservoir exhibits substantial promise as an H_(2) storage site.(b)Notably,a pronounced increase in reservoir pressure manifests during the injection stage,particularly in homogeneous reservoirs.(c)Furthermore,optimizing injection-extraction cycle efficiency can be achieved by augmenting reservoir dimensions while maintaining a consistent thickness.To ensure a smooth transition to implementation,further comprehensive investigations are advised,including experimental and numerical studies to address injectivity concerns and explore storage site development.This evaluation framework is a valuable tool for assessing the potential of depleted gas reservoirs for large-scale hydrogen storage,advancing global eco-friendly energy systems.

Quantitative evaluation methods for waterflooded layers of conglomerate reservoir based on well logging data

The rapid changing near source, multi-stream depositional environment of conglomerate reservoirs leads to severe heterogeneity, complex lithology and physical properties, and large changes of oil layer resistivity. Quantitative evaluation of water-flooded layers has become an important but difficult focus for secondary development of oilfields. In this paper, based on the analysis of current problems in quantitative evaluation of water-flooded layers, the Kexia Group conglomerate reservoir of the Sixth District in the Karamay Oilfield was studied. Eight types of conglomerate reservoir lithology were identified effectively by a data mining method combined with the data from sealed coring wells, and then a multi-parameter model for quantitative evaluation of the water-flooded layers of the main oil-bearing lithology was developed. Water production rate, oil saturation and oil productivity index were selected as the characteristic parameters for quantitative evaluation of water-flooded layers of conglomerate reservoirs. Finally, quantitative evaluation criteria and identification rules for water-flooded layers of main oil-bearing lithology formed by integration of the three characteristic parameters of water-flooded layer and undisturbed formation resistivity. This method has been used in evaluation of the water-flooded layers of a conglomerate reservoir in the Karamay Oilfield and achieved good results, improving the interpretation accuracy and compliance rate. It will provide technical support for avoiding perforation of high water-bearing layers and for adjustment of developmental programs.

Evaluation, prediction, and protection of water quality in Danjiangkou Reservoir, China

The water quality in the Danjiangkou Reservoir has attracted considerable attention from the Chinese public and government since the announcement of the Middle Route of the South to North Water Diversion Project （SNWDP）, which commenced transferring water in 2014. Integrated research on the evaluation, prediction, and protection of water quality in the Danjiangkou Reservoir was carried out in this study in order to improve environmental management. Based on 120 water samples, wherein 17 water quality indices were measured at 20 monitoring sites, a single factor evaluation method was used to evaluate the current status of water quality. The results show that the main indices influencing the water quality in the Danjiangkou Reservoir are total phosphorus （TP）, permanganate index （CODM,）, dissolved oxygen （DO）, and five-day biochemical oxygen demand （BODs）, and the concentrations of TP, BODs, ammonia nitrogen （NH3--N）, CODM,, DO, and anionic surfactant （Surfa） do not reach the specified standard levels in the tributaries. Seasonal Mann--Kendall tests indicated that the CODMn concentration shows a highly significant increasing trend, and the TP concentration shows a significant increasing trend in the Danjiangkou Reservoir. The distribution of the main water quality indices in the Danjiangkou Reservoir was predicted using a two-dimensional water quality numerical model, and showed that the sphere of influence from the tributaries can spread across half of the Han Reservoir if the pollutants are not controlled. Cluster analysis （CA） results suggest that the Shending River is heavily polluted, that the Jianghe, Sihe, and Jianhe rivers are moderately polluted, and that they should be the focus of environmental remediation.

A new method of formation evaluation for fractured and caved carbonate reservoirs:A case study from the Lundong area,Tarim Basin,China

The carbonate reservoirs in the Tarim Basin are characterized by low matrix-porosity,heterogeneity and anisotropy,which make it difficult to predict and evaluate these reservoirs.The reservoir formations in Lundong area experienced a series of diagenesis and tectonic evolution stages.And secondary storage spaces such as fractures and dissolution caves were developed while nearly all the primary pores have disappeared.Based on a summary of different types of storage spaces and their responses in conventional logs,FMI and full waveform sonic logs which are sensitive to different reservoirs,the comprehensive probability index （CPI） method is applied to evaluating the reservoirs and a standard of reservoir classification is established.By comparing the evaluation results with actual welllogging results,the method has proven to be practical for formation evaluation of carbonate reservoirs,especially for the fractured carbonate reservoirs.In reservoir fluid identification,the multivariate stepwise discriminant analysis （MSDA） method is introduced.Combining the CPI method and MSDA method,comprehensive formation evaluation has been performed for fractured and caved carbonate reservoirs in the Tarim Basin.Additionally,on the basis of secondary pore inversion results,another new method of formation evaluation is also proposed in the discussion part of this paper.Through detailed application result analysis,the method shows a promising capability for formation evaluation of complex carbonate reservoirs dominated by various secondary pores such as holes,caves,and cracks.

Logging Evaluation of the Ordovician Carbonate Reservoir Beds in the Lungudong Region,Tarim Basin

In recent years, great progress has been made constantly in oil and gas exploration in the Lungudong region of the Tarim Basin. However, progress has been slow in the evaluation of its main oil-producing horizons -- the Ordovician carbonate reservoir beds. Based on previous researches and on the various data such as drilling, geology and oil test, in combination with the interpretation of each single-well imaging and conventional logging data, and through analysis and comparison, the identification methods in imaging and conventional logging for four types of carbonate reservoir beds in this region are summarized in this paper. Calculation formulas for four reservoir bed parameters, i. e. shale content, porosity, permeability and oil saturation in this region are proposed; and reservoir beds in this region are divided into three levels （Ⅰ, Ⅱ and Ⅲ） by combining oil test data and logging data, The lower limits of the effective porosity of reservoir beds and the fracture porosity of effective reservoir beds are determined as 1.8% and 0.04%, respectively. The physical property parameters are calculated by conventional logging curves, and the most advantageous areas for reservoir development are predicted comprehensively. On the plane, the high-value zones of reservoir bed parameters are mainly concentrated in the N-S-trending strike-slip fault, the Sangtamu fault horst zone and near the LG38 well area; vertically, the reservoir bed parameters of the Yijianfang Formation are better than those of the Yingshan and Lianglitage formations.

A Comprehensive Evaluation Method for Low-permeability Reservoirs

According to the geological characteristics and their influential factors of the low-permeability reservoirs, a comprehensive method for evaluation of low-permeability reservoirs is put forward. The method takes a matrix system as the basis, a fracture system as the focus and a stress field system as the restricted factor. It can objectively reflect not only the storage capability and seepage capability of low-permeability reservoirs, but also the effect on development as well. At the same time, it can predict the seepage characteristics at different development stages and provide a reasonable geological basis for the development of low-permeability reservoirs.

Discussion on evaluation methodology of hydrothermal geothermal reservoir

Geothermal reservoir are the vehicle of geothermal resources and their occurrence as well as the storage mass. Precise description and evaluation of geothermal reservoir serves to be the cornerstone of geothermal resource exploration and exploitation. Based on the principles and basic train of geothermal reservoir evaluation, in this work, the content of geothermal reservoir evaluation was determined and the value range of geothermal reservoir evaluation parameters was discussed in combination with the actual production data of two types of geothermal reservoir in North China: The Neogene Guantao Formation sandstone pore-type geothermal reservoir, and the CambrianOrdovician and Middle Proterozoic Jixian carbonate karst-fissure-type geothermal reservoir. An evaluation method for the sandstone pore-type and the carbonate karstfissure-type geothermal reservoir is finally established based on the analysis of the production data, i.e. the values of geothermal reservoir temperature, geothermal fluid production, reinjection, physical properties and other parameters are assigned, and the geometric average value of the assigned values for the above-mentioned parameters is taken as the overall evaluation index of geothermal reservoir. From large to small, this index categorizes geothermal reservoir into three grades:Ⅰ, Ⅱ and Ⅲ, which corresponds to advantageous, moderate advantageous and disadvantageous geothermal reservoir respectively. The geothermal reservoir of the same grade are further classified in light of the index value, thus realizing the comprehensive evaluation of geothermal reservoir.

A quantitative model for danger degree evaluation of staged operation of earth dam reservoir in flood season and its application

Based on the natural disaster risk evaluation mode, a quantitative danger degree evaluation model was developed to evaluate the danger degree of earth dam reservoir staged operation in the flood season. A formula for the overtopping risk rate of the earth dam reservoir staged operation was established, with consideration of the joint effect of flood and wind waves in the flood sub-seasons with the Monte Carlo method, and the integrated overtopping risk rate for the whole flood season was obtained via the total probability approach. A composite normalized function was used to transform the dam overtopping risk rate into the danger degree, on a scale of 0-1. Danger degree gradating criteria were divided by four significant characteristic values of the dam overtopping rate, and corresponding guidelines for danger evaluation are explained in detail in this paper. Examples indicated that the dam overtopping danger degree of the Chengbihe Reservoir in China was 0.33-0.57, within the range of moderate danger level, and the flood-limiting water level （FLWL） can be adjusted to 185.00 m for the early and main flood seasons, and 185.00-187.50 m for the late flood season. The proposed quantitative model offers a theoretical basis for determination of the value of the danger degree of an earth dam reservoir under normal operation as well as the optimal scheduling scheme for the reservoir in each stage of the flood season.

A stability evaluation method for deep-seated toppling in the upper Lancang river,Southwestern China

Deep-seated toppling in the upper reaches of the Lancang River,southwest China involves deformations exceeding 100 m in depth.The slope deformation is initiated by river downcutting and evolves distinctive characteristics with a depth of river incision.In this study,we propose a system for evaluating the stability of deep-seated toppled slopes in different evolutionary stages.This system contains identification criteria for each evolutionary stage and provides the corresponding stability evaluation methods.Based on the mechanical and kinematic analysis of slope blocks,the specific stage of slope movement can be identified in the field through outcrop mapping,in situ tests,surface displacement monitoring,and adit and borehole explorations.The stability evaluation methods are established based on the limiting equilibrium theory and the strain compatibility between the undisturbed zone and the toppled zone.Finally,several sample slopes in different evolution stages have been investigated to verify the applicability and accuracy of the proposed stability evaluation system.The results indicate that intense tectonic activity and rapid river incision lead to a maximum principal stress ratio exceeding 10 near the slope surface,thus triggering widespread toppling deformations along the river valley.When considering the losses of joint cohesion during the further rotation process,the safety factor of the slope drops by 7%e28%.The self-stabilization of toppling deformation can be recognized by the layer symmetry configuration after the free rotation of the deflected layers.Intensely toppled rock blocks mainly suffer sliding failures beyond the layer symmetry condition.The factor of safety of the K73 rockslide decreased from 1.17 to 0.87 by considering the development of the potential sliding surface and the toesaturated zone.

Logging evaluation of deep multi-type unconventional gas reservoirs in the Songliao basin,northeast China:Implications from continental scientific drilling

Multi-type unconventional gas-bearing reservoirs with different lithologies and gas accumulation potential occur in the deep part of the Songliao basin.However,the reservoirs are non-homogeneous,the gas components differ substantially,and not all types of gas-bearing reservoirs have been identified or evaluated.The International Continental Scientific Drilling Program(ICDP)is used as an example to conduct qualitative and quantitative evaluations of deep multi-type unconventional gas-bearing reservoirs using conventional and specialized logging data.The core test data are used to determine the physical properties.The porosity and permeability are compared and analyzed using different methods and models.The results show that the reservoirs have low to ultra-low porosity and ultra-low permeability.Based on the comparison of the rock mechanical parameters and mineral composition,brittleness evaluation parameters are proposed for different types of deep reservoirs in the study region.The mineral brittleness index is highly consistent with the brittleness index based on rock mechanics.An identification method for deep multi-type gas-bearing reservoir and a classification approach for different gas properties are established based on the logging response and parameter interpretation.The methane gas reservoirs have low density(DEN)and low compensated neutron logging(CNL)values and high acoustic(AC)time difference and high resistivity(RT)values.The CO_(2)gas reservoirs have lower RT values and higher CNL values than the hydrocarbon gas reservoirs.The comprehensive analysis of deep gas source rock conditions and of the source-reservoir relationship provides insights for the evaluation of deep multi-type unconventional gas reservoirs.The discovery of high hydrogen content is of significant importance for developing new areas for deep natural gas exploration.

The productivity evaluation model and its application for finite conductivity horizontal wells in fault block reservoirs

It is very difficult to evaluate the productivity of horizontal wells in fault block reservoirs due to the influence of fault sealing.On the basis of the method of images and source-sink theory,a semianalytical model coupling reservoir and finite conductivity horizontal wellbore flow dynamics was built,in which the influence of fault sealing was taken into account.The distribution of wellbore flow and radial inflow profiles along the horizontal interval were also obtained.The impact of the distance between the horizontal well and the fault on the well productivity was quantitatively analyzed.Based on this analysis,the optimal distance between the horizontal well and the fault in banded fault block reservoirs could be determined.According to the field application,the relative error calculated by the model proposed in this paper is within ±15%.It is an effective evaluation method for the productivity of horizontal wells in fault block reservoirs.The productivity of the horizontal well increases logarithmically as the distance between the horizontal well and the fault increases.The optimal distance between the horizontal well and the fault is 0.25-0.3 times the horizontal well length.

Comprehensive Evaluation Model of Reservoir Operation Based on Improved Set Pair Analysis

A comprehensive evaluation model based on improved set pair analysis is established. Considering the complexity in decision-making process, the model combines the certainties and uncertainties in the schemes, i.e., identical degree, different degree and opposite degree. The relations among different schemes are studied, and the traditional way of solving uncertainty problem is improved. By using the gray correlation to determine the difference degree, the problem of less evaluation indexes and inapparent linear relationship is solved. The difference between the evaluation parameters is smaller in both the fuzzy comprehensive evaluation model and fuzzy matter-element method, and the dipartite degree of the evaluation result is unobvious. However, the difference between each integrated connection degree is distinct in the improved set pair analysis. Results show that the proposed method is feasible and it obtains better effects than the fuzzy comprehensive evaluation method and fuzzy matter-element method.

Evaluation of hydraulic fracturing of horizontal wells in tight reservoirs based on the deep neural network with physical constraints

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.

Classification of microscopic pore-throats and the grading evaluation on shale oil reservoirs

On the basis of the characterization of microscopic pore-throats in shale oil reservoirs by high-pressure mercury intrusion technique, a grading evaluation standard of shale oil reservoirs and a lower limit for reservoir formation were established. Simultaneously, a new method for the classification of shale oil flow units based on logging data was established. A new classification scheme for shale oil reservoirs was proposed according to the inflection points and fractal features of mercury injection curves: microscopic pore-throats(less than 25 nm), small pore-throats(25-100 nm), medium pore-throats(100-1 000 nm) and big pore-throats(greater than 1 000 nm). Correspondingly, the shale reservoirs are divided into four classes, I, II, III and IV according to the number of microscopic pores they contain, and the average pore-throat radii corresponding to the dividing points are 150 nm, 70 nm and 10 nm respectively. By using the correlation between permeability and pore-throat radius, the permeability thresholds for the reservoir classification are determined at 1.00× 10^(-3) μm^2, 0.40×10^(-3) μm^2 and 0.05×10^(-3) μm^2 respectively. By using the exponential relationship between porosity and permeability of the same hydrodynamic flow unit, a new method was set up to evaluate the reservoir flow belt index and to identify shale oil flow units with logging data. The application in the Dongying sag shows that the standard proposed is suitable for grading evaluation of shale oil reservoirs.

Study and application on the evaluation method of porous formation for long-term waterflooding sand reservoir

Nine targets which stand both for the static characteristic of produced formations and the dynamic parameter of wells including the average permeability,variation coefficient of permeability,moving capability,remaining recoverable reserves,coefficient of flooding,daily oil production,increasing rate of water cut,cumulative liquid production per unit meter and efficiency index of oil production are selected as the evaluation indexes,a novel model to evaluate the porous formations in long-term waterflooding sand reservoir was established by using the support vector machine and clustering analysis. Data of 57 wells from Shentuo 21 block Shengli oilfield was analyzed by using the model. Four kinds of formation groups were gained. According to the analysis result,different adjustment solutions were put forward to develop the relevant formations. The Monthly oil production increased 7.6 % and the water cut decreased 8.9 % after the adjusted solutions. Good results indicate that the learning from this method gained will be valuable adding to other long-term waterflooding sand reservoirs in Shengli oilfield and other similar reservoirs worldwide.

A quantitative evaluation for well pattern adaptability in ultra-low permeability oil reservoirs:A case study of Triassic Chang 6 and Chang 8 reservoirs in Ordos Basin

Based on the previous studies and development practice in recent 10 years, a quantitative evaluation method for the adaptability of well patterns to ultra-low permeability reservoirs was established using cluster analysis and gray correlation method, and it includes 10 evaluation parameters in the four aspects of optimal evaluation parameters, determination of weights for evaluation parameters, development stage division, and determination of classification coefficients. This evaluation method was used to evaluate the well pattern adaptability of 13 main ultra-low permeability reservoirs in Triassic Chang 6 and Chang 8 of Ordos Basin. Three basic understandings were obtained: Firstly, the well pattern for ultra-low permeability type-I reservoirs has generally good adaptability, with proper well pattern forms and well pattern parameters. Secondly, square inverted nine-spot well pattern is suitable for reservoirs with no fractures; rhombic inverted nine-spot injection pattern is suitable for reservoirs with some fractures; and rectangular well pattern is suitable for reservoirs with rich fractures. Thirdly, for the ultra-low permeability type-Ⅱ and type-Ⅲ reservoirs, with the principles of well pattern form determination, the row spacing needs to be optimized further to improve the level of development of such reservoirs.

Multi-hierarchical fuzzy judgment and nested dominance relation of rough set theory-based environmental risk evaluation for tailings reservoirs

Environmental risk assessment of tailings reservoir assessment system is complex and has many index factors.In order to accurately judge surrounding environmental risks of tailings reservoirs and determinate the corresponding prevention and control work,multi-hierarchical fuzzy judgment and nested dominance relation of rough set theory are implemented to evaluate them and find out the rules of this evaluation system with 14 representative cases.The methods of multi-hierarchical fuzzy evaluation can overall consider each influence factor of risk assessment system and their mutual impact,and the index weight based on the analytic hierarchy process is relatively reasonable.Rough set theory based on dominance relation reduces each index attribute from the top down,largely simplifies the complexity of the original evaluation system,and considers the preferential information in each index.Furthermore,grey correlation theory is applied to analysis of importance of each reducted condition attribute.The results demonstrate the feasibility of the proposed safety evaluation system and the application potential.

Grading evaluation and prediction of fracture-cavity reservoirs in Cambrian Longwangmiao Formation of Moxi area,Sichuan Basin,SW China

By using core, thin section, well logging, seismic, well testing and other data, the reservoir grading evaluation parameters were selected, the classification criterion considering multiple factors for carbonate reservoirs in this area were established, and the main factors affecting the development of high quality reservoir were determined. By employing Formation MicroScanner Image(FMI) logging fracture-cavity recognition technology and reservoir seismic waveform classification technology, the spatial distribution of reservoirs of all grades were predicted. On the basis of identifying four types of reservoir space developed in the study area by mercury injection experiment, a classification criterion was established using four reservoir grading evaluation parameters, median throat radius, effective porosity and effective permeability of fracture-cavity development zone, relationship between fracture and dissolution pore development and assemblage, and the reservoirs in the study area were classified into grade I high quality reservoir of fracture and cavity type, grade II average reservoir of fracture and porosity type, grade Ⅲ poor reservoir of intergranular pore type. Based on the three main factors controlling the development of high quality reservoir, structural location, sedimentary facies and epigenesis, the distribution of the 3 grades reservoirs in each well area and formation were predicted using geophysical response and percolation characteristics. Follow-up drilling has confirmed that the classification evaluation standard and prediction methods established are effective.