**Peer Reviewed**

**Source**

**Journal**

**Conference**

- 1999 SEG Annual Meeting (1)
- 2012 SEG Annual Meeting (2)
- 2013 SEG Annual Meeting (2)
- 2014 SEG Annual Meeting (7)
- 2015 SEG Annual Meeting (6)
- 2016 SEG International Exposition and Annual Meeting (6)
- 2017 SEG International Exposition and Annual Meeting (4)
- 43rd U.S. Rock Mechanics Symposium & 4th U.S. - Canada Rock Mechanics Symposium (1)
- 45th U.S. Rock Mechanics / Geomechanics Symposium (1)
- ISRM International Symposium on Rock Mechanics - SINOROCK 2009 (2)
- SEG International Exposition and Annual Meeting (1)
- SPE European Formation Damage Conference and Exhibition (1)
- SPE International Symposium and Exhibition on Formation Damage Control (2)
- SPE International Symposium and Exhibiton on Formation Damage Control (1)
- SPE International Symposium on Oilfield Chemistry (1)
- SPE Middle East Oil & Gas Show and Conference (2)
- SPE Reservoir Simulation Symposium (4)
- SPE/AAPG/SEG Unconventional Resources Technology Conference (1)
- SPE/IADC Drilling Conference and Exhibition (2)
- The Twentieth International Offshore and Polar Engineering Conference (2)

**Publisher**

**Theme**

**Author**

- Cao, Mingqiang (1)
- Champagne, Lakia M. (1)
- Chen, Bingrui (1)
- Chen, Guang (2)
- Chen, Hanming (11)
- Chen, Haolin (1)
- Chen, Hong (2)
- Chen, Xinyu (1)
- Chen, Yangkang (5)
- Chen, Yuhua (2)
- Davis, Chesnee L. (2)
- Deville, Jay P. (5)
- Dismuke, Keith I. (1)
- Dou, Yuzhao (1)
- Ellena, Linda (1)
- Fang, Jinwei (1)
- Feng, Xia- Ting (1)
- Feng, Xia-Ting (2)
- Galindo, Kay (1)
- Galindo, Kay A. (3)
- Gan, Shuwei (1)
- Guan, Shoujun (2)
- Guo, Jia (1)
- Hu, Zongwen (1)
- Hudson, J.A. (1)
- Lascaud, Benjamin (1)
- Lee, Seong H. (1)
- Lee, Seong Hee (2)
- Lett, Nathan L. (2)
- Li, Qingqing (4)
- Li, Shaojun (1)
- Li, Yanqi (2)
- Li, Zhenchun (1)
- Lin, He (1)
- Liu, Chongnag (1)
- Liu, Mingdi (2)
- Liu, Wenling (1)
- Liu, Ying (1)
- Long, Teng (1)
- Pan, Peng-Zhi (2)
- Pan, Xiao (1)
- Penny, Glenn S. (2)
- Qin, Mo (1)
- Qu, Shan (6)
- Sato, Motoyuki (1)
- Shen, Lin-Fang (1)
- Shi, Yongjiu (2)
- Shuwei, Gan (1)
- Tang, Yanchun (1)
- Tao, Yonghui (2)
- Tchelepi, Hamdi A. (7)
- Tian, Yukun (1)
- Wang, Haiyang (1)
- Wang, Jie (2)
- Wang, Lingqian (2)
- Wang, Minglu (1)
- Wang, Ning (2)
- Wang, Shangxu (1)
- Wang, Shucheng (2)
- Wang, Xiaochen (1)
- Wang, Yuanqing (2)
- Wang, Yufeng (2)
- Xia, Muming (4)
- Xie, Chunlin (3)
- Yang, Yahui (2)
- Yu, Bo (3)
- Yuan, Jiang (2)
- Zelenev, Andrei S. (2)
- Zha, Weibin (4)
- Zhang, Chuanqing (1)
- Zhang, Dong (1)
- Zhang, Guangchao (1)
- Zhang, Hongjing (2)
- Zhang, Qi (1)
- Zhang, Qingchen (3)
- Zhao, Xuebin (1)
- Zhi, Ling (1)
**Zhou, Hui (52)**- Zou, Xiaofeng (3)
- Zou, Yaming (2)
- Zu, Shaohuan (6)
- Zuo, Anxin (2)

**Concept Tag**

- accuracy (2)
- acquisition (4)
- algorithm (4)
- amplitude (3)
- annual meeting (7)
- application (3)
- Artificial Intelligence (21)
- AWWE (2)
- base metal (2)
- BILU (2)
- Biopolymer (3)
- boundary (2)
- Brine (4)
- brine-based drill-in fluid (2)
- cell (3)
- Chen (3)
- coefficient (2)
- conservation (2)
- constraint (3)
- construction (3)
- convergence (3)
- convolutional (2)
- curve (2)
- data quality (4)
- dispersion (2)
- drill-in fluid (4)
- drill-in fluid sample (2)
- drilling fluid chemistry (6)
- drilling fluid formulation (6)
- drilling fluid property (6)
- drilling fluid selection and formulation (6)
- drilling fluids and materials (6)
- effect (2)
- elastic impedance (4)
- elastic impedance inversion (2)
- Engineering (2)
- equation (17)
- estimation (2)
- experiment (3)
- failure (2)
- filtration control (2)
- finite-difference method (2)
- flow in porous media (4)
- Fluid Dynamics (4)
- fluid loss (5)
- fluid recovery (2)
- formation damage (4)
- formulation (5)
- fracture (3)
- frequency (8)
- geophysics (5)
- high temperature (3)
- Hp Wbm (2)
- Ht Hp Wbm (2)
- HT polymer (2)
- hydraulic fracturing (6)
- impedance (4)
- information (3)
- international exposition (3)
- inversion (15)
- inversion result (7)
- iteration (5)
- LBM (3)
- loading (3)
- machine learning (6)
- migration (3)
- Modeling & Simulation (3)
- Multiscale (3)
- noise (3)
- OMP algorithm (2)
- operator (6)
- p-wave velocity (3)
- permeability (11)
- polymer (5)
- prolongation operator (3)
- reflection (4)
- reflection coefficient (4)
- Reservoir Characterization (33)
- reservoir description and dynamics (11)
- reservoir geomechanics (3)
- reservoir simulation (7)
- rock (4)
- s-wave velocity (3)
- scaling method (7)
- seg denver 2014 (3)
- seismic data (4)
- Simulation (3)
- stability (4)
- static aging (5)
- TAM (2)
- Tchelepi (2)
- Thickness (2)
- Upstream Oil & Gas (51)
- Vibroseis (2)
- Vibroseis data (2)
- viscoacoustic wave equation (4)
- viscosity (5)
- Wave Equation (7)
- wavefield (5)
- well completion (5)

**File Type**

**Abstract**

With hundreds of rigs running and thousands of wells producing in unconventional plays, more and more data becomes available every day and it is ever more tempting to apply machine learning techniques for unconventional development, be it to identify geology sweet spot, understand performance drivers and optimize development strategies such as well spacing, completion and production designs etc. However, most of the previous applications of machine learning are limited to either certain types of data or small areas of interest. Consequently, the results often lack the predictability or generalizability necessary to impact important development decisions. We developed a flexible, scalable and integrated machine learning framework to leverage all sources of data for the goal of optimizing unconventional resources development.

The framework is built on a big data warehouse and on-demand capability to efficiently visualize and analyze large volumes of heterogeneous data. The most important pillar of the framework is the ability to transform all different types of data with fit-for-purpose methodologies to be closely related to the evaluation and prediction of well performance. This is enabled mechanistically by an interface to scripting languages such as R or Python for interactive data processing, validation and visualization. We also developed several innovative methodologies to overcome some common challenges in characterizing well performance and analyzing well spatial and temporal relationships in terms of well spacing, stacking and infill timing. Ultimately, all the data is regularized to be ready for machine learning. The framework enables a rich set of state-of-the-art machine learning techniques. More importantly, the integration of machine learning with geology, reservoir and development data in a visual environment enables very intuitive and interactive testing, validation and interpretation, which provides valuable insight and confidence for development decision making.

The framework has been extensively employed in Permian Basin for important technical studies such as evaluation of new formation, optimization of well completion and spacing, and even PUD reserve booking compatible with SPEE recommended reliable technology. Field case studies clearly demonstrate the applicability and efficiency of the framework as well as the predictability and insights the machine learning techniques offer.

application, Artificial Intelligence, big data, completion, data infrastructure, data transformer, forecast, geology, Hadoop, information, machine learning, production data, proppant, reservoir, unconventional reservoir, unconventional resource, unconventional resource development, Upstream Oil & Gas, urtec 319, well performance

Oilfield Places:

- North America > United States > West Virginia > Appalachian Basin > Marcellus Shale (0.99)
- North America > United States > Virginia > Appalachian Basin > Marcellus Shale (0.99)
- North America > United States > Texas > Permian Basin > Delaware Basin (0.99)
- (5 more...)

SPE Disciplines:

Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)

Wang, Lingqian (State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum–Beijing) | Zhou, Hui (State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum–Beijing) | Wang, Yufeng (State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum–Beijing) | Yu, Bo (State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum–Beijing) | Long, Teng (State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum–Beijing)

It is necessary to estimate the elastic impedance accurately for three-parameter inversion. However, the elastic impedance can be calculated from the reflectivity with the recursive inversion and the generalized linear inversion (GLI) separately. It has been demonstrated that GLI can improve the shortcomings of recursive inversion with respect to relative and absolute scale of the impedance results. But both of them depend on the accuracy of the reflectivity, so it is necessary to get the reflectivity accurately. Here we use alternating direction method of multipliers (ADMM) and difference of convex algorithm (DCA) to solve the _{1-2} minimization problem to obtain a more accurate reflectivity series. Examples have shown the superior performance of the ADMM-_{1-2} inversion result over the solution of OMP algorithm.

Presentation Date: Monday, October 15, 2018

Start Time: 1:50:00 PM

Location: Poster Station 11

Presentation Type: Poster

ADMM, algorithm, annual meeting 10, Artificial Intelligence, elastic impedance, elastic impedance inversion, equation, generalized linear inversion, impedance, impedance inversion, international exposition, inversion, inversion result, minimization, omp, OMP algorithm, recursive inversion, reflection, reflectivity, Reservoir Characterization, subproblem, Upstream Oil & Gas

SPE Disciplines: Reservoir Description and Dynamics > Reservoir Characterization > Seismic processing and interpretation (1.00)

We propose to estimate velocity and seismic quality factor (

Presentation Date: Wednesday, September 27, 2017

Start Time: 9:45 AM

Location: Exhibit Hall C/D

Presentation Type: POSTER

SPE Disciplines: Reservoir Description and Dynamics > Reservoir Characterization > Seismic processing and interpretation (1.00)

Wang, Shucheng (China University of Petroleum–Beijing) | Xia, Muming (China University of Petroleum–Beijing) | Zhou, Hui (China University of Petroleum–Beijing) | Wang, Ning (China University of Petroleum–Beijing) | Fang, Jinwei (China University of Petroleum–Beijing)

In this paper, lattice Boltzmann method (LBM) is employed in forward modeling of seismic P-wave propagation. By choosing different relaxation factors in numerical experiments and using spectrum ratio method, the relationship between the quality factor

Presentation Date: Wednesday, September 27, 2017

Start Time: 4:45 PM

Location: 381A

Presentation Type: ORAL

SPE Disciplines: Reservoir Description and Dynamics > Reservoir Characterization > Seismic processing and interpretation (1.00)

Prediction of shear-wave velocity plays an important role in some seismic applications, such as amplitude variation with offset (AVO) analysis, and the construction of lithofacies recognition library. This paper presents a method for predicting S-wave velocity based on three logging curves: interval transit time, density and gamma. There are two main problems: accurate establishment of reasonable rock physical models and efficient solution of an objective function. Three logging curves can be used to calculate porosity, shale volume and to determine the lithology. We can get the compaction constant through solving the P-wave objective function. An advantage of this method is that there are few empirical parameters, such as clay content, mineral modulus and pore aspect ratio, to be chosen. On the other hand, it can accurately predict S-wave velocity by building a reasonable rock physical models with practical well logs rather than petrophysical experiment in the laboratory.

Presentation Date: Tuesday, September 26, 2017

Start Time: 3:30 PM

Location: Exhibit Hall C/D

Presentation Type: POSTER

Li, Qingqing (China University of Petroleum–East China) | Li, Zhenchun (China University of Petroleum–East China) | Zhou, Hui (China University of Petroleum–Beijing) | Zhao, Xuebin (China University of Petroleum–Beijing) | Zu, Shaohuan (China University of Petroleum–Beijing)

The stability and efficiency, especially the stability, are generally concerned issues in

Presentation Date: Wednesday, September 27, 2017

Start Time: 1:50 PM

Location: 371A

Presentation Type: ORAL

This paper discusses two high-temperature-resistant polymers (Polymers A and B) that have been developed as thermally stable, dual-functional viscosifiers and fluid-loss additives. Polymer A was designed for monovalent brines, while Polymer B works for divalent brines. These polymers enable the formulation of brine-based drill-in fluids that are stable at high to ultra-high temperatures, which is a significant improvement when compared to conventional biopolymer-based drill-in fluids. When combined, the two polymers work synergistically to further reduce fluid loss in monovalent brines.

The two thermally stable polymers were readily incorporated into various drill-in fluid formulations containing either monovalent or divalent brines over a broad range of densities. These drill-in fluids exhibited exceptional thermal stability and showed no stratification after static aging at 400°F for three days or at 375°F for seven days. A minimal change in fluid behavior was observed when comparing the rheological properties of the un-aged and aged samples. The samples provided excellent fluid-loss control, even after aging. A synergistic effect was observed between Polymers A and B when used in monovalent brines to further reduce the HPHT fluid loss with no negative impact on fluid rheology. Core flow tests showed that both fluids were non-damaging after acid-breaker treatment. It is anticipated that these polymers will extend the envelope to which water-based drill-in fluids can be successfully used to drill high- and ultra-high-temperature reservoirs. Recent successful field trial of the divalent brine-based fluid as a testing fluid further proved the robustness of these fluids for these reservoirs.

acid treatment, Biopolymer, Brine, brine-based drill-in fluid, drill-in fluid, drill-in fluid formulation, drilling fluid chemistry, drilling fluid formulation, drilling fluid property, drilling fluid selection and formulation, drilling fluids and materials, fluid loss, hpht fluid, LBM, monovalent brine, permeability, polymer, static aging, synergistic effect, thermally stable, Upstream Oil & Gas, viscosity

SPE Disciplines: Well Drilling > Drilling Fluids and Materials > Drilling fluid selection and formulation (chemistry, properties) (1.00)

Recently, a decoupled fractional Laplacian viscoacoustic wave equation has been developed based on the constant-

Presentation Date: Thursday, October 20, 2016

Start Time: 8:30:00 AM

Location: 148

Presentation Type: ORAL

accuracy, constant fractional-order laplacian viscoacoustic, constant fractional-order laplacian wave equation, data quality, equation, equation 11, fractional laplacian, fractional-order laplacian, fractional-order laplacian wave, fractional-order laplacian wave equation, Laplacian, Laplacian wave equation, numerical solution, Reservoir Characterization, Upstream Oil & Gas, variable fractional-order laplacian, viscoacoustic wave equation, Wave Equation

Chen, Guang (China University of Petroleum–Beijing) | Zhou, Hui (China University of Petroleum–Beijing) | Liu, Mingdi (China University of Petroleum–Beijing) | Tao, Yonghui (China University of Petroleum–Beijing) | Wang, Haiyang (China University of Petroleum–Beijing)

Elastic impedance inversion is an important prestack inversion method in reservoir prediction and fluid identification. Constrained sparse spike inversion (CSSI) used to be the most widely used method in poststack seismic inversion. Because of the relationship between the elastic impedance and the wave impedance, the CSSI can be directly applied to the prestack elastic impedance inversion. However, CSSI usually suffers from strongly ill-posed problem when using some local optimization algorithm, such as conjugate gradient (CG) method, and has a strong dependence on the initial model of reflection coefficient. Besides, conventional CSSI separately inverts the time locations and amplitudes of sparse-spikes, which increases the computational complexity. In this paper, we improve CSSI theory with a linear wave impedance constraint, which is named as LCSSI. We apply orthogonal matching pursuit (OMP) non-linear algorithm to linear constrained sparse spike prestack elastic impedance inversion. We derive a linear matrix equation from the cost function and use OMP algorithm to invert the sparse-spikes' time locations and amplitudes simultaneously. Due to OMP, this method can reduce dependence on initial model and obtain the inversion results precisely and quickly. Numerical examples indicate that our method can achieve a good performance even for noisy data, while the CG algorithm fails to get a desirable inversion result.

Presentation Date: Wednesday, October 19, 2016

Start Time: 8:00:00 AM

Location: 155

Presentation Type: ORAL

algorithm, application, Artificial Intelligence, elastic impedance, elastic impedance inversion, impedance, impedance constraint, inversion, inversion result, LCSSI method, objective function, OMP algorithm, optimization problem, reflection coefficient, Reservoir Characterization, sparse, Upstream Oil & Gas, Wave Impedance

Oilfield Places:

- Europe > Norway > Norwegian Sea > Halten Bank Area > Vøring Basin > Block 6506/11 > Kristin Field > Tofte Formation (0.99)
- Europe > Norway > Norwegian Sea > Halten Bank Area > Vøring Basin > Block 6506/11 > Kristin Field > Ile Formation (0.99)
- Europe > Norway > Norwegian Sea > Halten Bank Area > Vøring Basin > Block 6506/11 > Kristin Field > Garn Formation (0.99)
- (3 more...)

Technology: Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (0.92)

Yu, Bo (China University of Petroleum–Beijing) | Zhou, Hui (China University of Petroleum–Beijing) | Zou, Xiaofeng (China University of Petroleum–Beijing) | Zu, Shaohuan (China University of Petroleum–Beijing) | Wang, Ning (China University of Petroleum–Beijing) | Wang, Shucheng (China University of Petroleum–Beijing)

Prestack multiwave joint inversion for Young's modulus and Poisson ratio based on stochastic kriging interpolation Summary The product of Young's modulus and density can highlight abnormal characteristic of shale gas reservoirs, Poisson ratio can indicate fluid property. In this paper, the joint PP and PS AVO inversion based on Bayes theorem is used to obtain Young's modulus and Poisson's ratio. This method can achieve more accurate elastic parameters for fluid prediction and shale gas reservoir identification. We get the PP and PS wave approximate reflection coefficient by the approximate equation of Aki-Richards. We obtain the object function by Bayes theorem, and we suppose the parameter sequence is subject to the Cauchy distribution.

Artificial Intelligence, AVO inversion, bayes theorem, Bayesian Inference, equation, fractal, information, interpolation, inversion, inversion result, joint inversion, machine learning, Poisson ratio, prestack multiwave joint, reflection coefficient, Reservoir Characterization, shale gas reservoir, Upstream Oil & Gas

Thank you!