22
Copyright 2016 Southwestern Energy Company. All rights reserved. Production Nuance Analysis Effective Not Just Efficient Mark Reynolds, June 7, 2016

2016 06-07 data driven production

Embed Size (px)

Citation preview

Page 1: 2016 06-07 data driven production

Copyright 2016 Southwestern Energy Company. All rights reserved.

Production Nuance AnalysisEffective Not Just Efficient

Mark Reynolds, June 7, 2016

Page 2: 2016 06-07 data driven production

2 Copyright 2016 Southwestern Energy Company. All rights reserved.

Introduction to Southwestern Energy

Southwestern Energy Company (NYSE: SWN) is a leading natural gas and oil company with operations predominantly in the United States, engaged in exploration, development and production activities, including related natural gas gathering and marketing.

Source: http://www.swn.com/

Page 3: 2016 06-07 data driven production

3 Copyright 2016 Southwestern Energy Company. All rights reserved.

Production Nuance Analysis

Production Nuance Analysis-Effective Not Just Efficient

• Efficient O&G does not suffice in an industry downturn – effective investment in time and effort is required to rise above the pack

• Production analysis need not be mystical; it should not be rote• Nuance and subtle variations provide leading indicators into impending

production issues• Decline curves, certainly crucial, must be analyzed in context• Case-based, topological analysis, rule inference, curve plotting solutions

are common solutions, but fall short• Application of nuance analysis within environment of Data-Intensive

Scientific Discovery

Page 4: 2016 06-07 data driven production

4 Copyright 2016 Southwestern Energy Company. All rights reserved.

Efficient• ROP• $ / ft• Daily Volume

Effective• Placement• PVI• EUR

Efficiencies vs Effectiveness in Upstream

Source: Mark Reynolds, compilation

Page 5: 2016 06-07 data driven production

5 Copyright 2016 Southwestern Energy Company. All rights reserved.

Efficient vs Effective

“The difference between efficiency and effectiveness—that which differentiates wisdom from understanding, knowledge, information, and data—is reflected in the difference between development and growth.”

- Russell Ackoff

Source: Ackoff, R. L. (1999) Ackoff’s Best. New York: John Wiley & Sons, pp 170 – 172

Survive Thrive

Die Slowly Die QuicklyEffec

tiven

ess

Efficiency

Page 6: 2016 06-07 data driven production

6 Copyright 2016 Southwestern Energy Company. All rights reserved.

Evolution of Production Analysis

Source: Mark Reynolds, compilation

Page 7: 2016 06-07 data driven production

7 Copyright 2016 Southwestern Energy Company. All rights reserved.

The Catalyst• Data captured

by instruments• Data generated

by simulations• Data acquired

by sensor networks

The Destination• Solutions from

– data analysis– data mining– visualization– drill down

• Solutions for the bottom line

• Solutions using eScience

4th Paradigm – Data Intensive Solutions

Source: eScience and the Fourth Paradigm: Data-Intensive Scientific Discovery and Digital Preservation, Tony Hey, Microsoft Research http://www.alliancepermanentaccess.org/wp-content/uploads/2011/12/apa2011/15_%28Nov11%29TonyHey-APA%20Meeting.pdf

“eScience is the set of tools and technologies to support data federation and collaboration.”

- Jim Grey

Page 8: 2016 06-07 data driven production

8 Copyright 2016 Southwestern Energy Company. All rights reserved.

What to expect in the 4th Paradigm

Acquire Analyze Annunciate Archive Analyze Anticipate Apply

Data InformationVisualization

KnowledgeForensics

UnderstandingAnalysis &

Mining

WisdomAnticipating Application

Creating Informational Accessibility and Transparency Discovering Experiential Performance Improvements Segmenting Processes and Process Results Automating Decisions and Processes Innovating New Models, Products, Services

Source: Mark Reynolds, compilation

Quantum Shift in Methodical Processes

Real-Time & 24/7 Data-Intensive Scientific Discovery --- the 4th Paradigm

Creating Discovering Segmenting Automating Innovating

Page 9: 2016 06-07 data driven production

9 Copyright 2016 Southwestern Energy Company. All rights reserved.

Data InformationVisualization

KnowledgeForensics

UnderstandingAnalysis &

Mining

WisdomAnticipating Application

Toward Data-Intensive Scientific Discovery

Seismic

Drilling

Completions

Production

RT Frac

Daily Rpts

Well Plan RT

Drill

Geo-steer

AFE

RT Prod

Source: Mark Reynolds, compilation

Real-Time & 24/7 Data-Intensive Scientific Discovery --- the 4th Paradigm

Page 10: 2016 06-07 data driven production

10 Copyright 2016 Southwestern Energy Company. All rights reserved.

Moving into the 4th Paradigm

3rd ParadigmComputational

Transitional 3rd Paradigm

4th ParadigmData Exploration

• Models• Exceptions• Alerts• Real-Time• Charts• Workbooks

• Cross – Silo Blending

• Complex Event Analysis

• Fast Data• IIoT

• Content Representation

• Spatial – Temporal• Tightly and

Loosely Coupled

Not so long ago Passing though the[Gartner] Hype

The near future

Source: Mark Reynolds, compilation

Page 11: 2016 06-07 data driven production

11 Copyright 2016 Southwestern Energy Company. All rights reserved.

Machine Learning on the Hype Curve

Page 12: 2016 06-07 data driven production

12 Copyright 2016 Southwestern Energy Company. All rights reserved.

System Architectures for Personalization …

• Online Computation– Recent events– User interaction

• Offline Computation– Less data limits– Relaxed timing rqmts– Grows stale

• Nearline Computation– Online-like computations– Not served in realtime

• Model Training– Creates model offline– Later used in realtime

Source: NetFlix Tech Blog, Xavier Amatriain and Justin Basilico, March 27, 2013http://techblog.netflix.com/2013/03/system-architectures-for.html

Page 13: 2016 06-07 data driven production

13 Copyright 2016 Southwestern Energy Company. All rights reserved.

Theoretical Evolution Into Advanced Control

External ProcessSet

Point

e

feedback

HistAnalytics

& ML

Enhanced Feedback

Page 14: 2016 06-07 data driven production

14 Copyright 2016 Southwestern Energy Company. All rights reserved.

Data-Intensive Scientific Discovery

Data

Information

Knowledge

Understanding

Wisdom

Application

The question is NOT“how can we … ?”

But instead“what is the objective?”

( or “Why?” )

Source: Mark Reynolds, compilation

Page 15: 2016 06-07 data driven production

15 Copyright 2016 Southwestern Energy Company. All rights reserved.

Questions Which Must be Addressed

• Which model (and coefficients) effectively describe well behavior?

• What constitutes an effective intervention?(or even a second look?)

• How have interventions been effective in a scenario?• How can intervention teams be effectively deployed?

Page 16: 2016 06-07 data driven production

16 Copyright 2016 Southwestern Energy Company. All rights reserved.

Algorithmic Approaches

• Decision Tree Learning– Maps observation to conclusions

• Association Rule Learning– Discovering interesting relations

• Artificial Neural Networks– Incremental function modules

• Inductive Logic Programming– Rule based representations for

input --> output

• Support Vector Machines– Classification and regression

• Clustering– Assignment of observations to

clusters

• Bayesian Networks– Probabilistic models correlating

variables

• Reinforcement Learning– Finds policy to map states to

desired outcome

• Representation Learning– Principal component analysis

• Similarity & Metric Learning– Pairs of examples train others

• Sparse Dictionary Learning– Datum as linear combinations

• Genetic Algorithms– Mimics natural heuristics

Source: Mark Reynolds, compilation

Page 17: 2016 06-07 data driven production

17 Copyright 2016 Southwestern Energy Company. All rights reserved.

Leveraging Data-Intensive Value

• Creating Informational Accessibility and Transparency

• Discovering Experiential Performance Improvements

• Segmenting Processes and Process Results

• Replacing Human Decision w/ Automated Algorithms

• Innovating New Models, Products, Services

Source: McKinsey Global Institute, 2011, Big Data: The next frontier for innovation, competition, and productivity

Page 18: 2016 06-07 data driven production

18 Copyright 2016 Southwestern Energy Company. All rights reserved.

Data

Qua

lity

Data

Integrity

Data

Validation

DataModeling DataSecurity

Data Mining

Data

AnalyticsData Life Cycle on a Daily Basis

Proactive & Closed-Loop

Systems

Mining and AnalyticsForensics

Control Visualization

and Observation

Source Capture and

Utilization

• Intelligence during operations (Observation and Anticipation)• Intelligence reviewing operations (Forensic)• Intelligence planning operations (Historical and Analytical)• Intelligence driving operations (Machine Learning)

Well Plan RT

Prod

RT Drill

Geo-steer

RT Frac

Daily RptsAFE

Source: Mark Reynolds, compilation

Page 19: 2016 06-07 data driven production

19 Copyright 2016 Southwestern Energy Company. All rights reserved.

What to expect in the 4th Paradigm

Upstream Systems & Knowledge Engineer

O&G Systems

Control Systems

Remote Systems

Information Systems

Embedded Systems

Robotic Systems

Data Fusion

Real-Time Systems

Look-Back Analysis

Look-Ahead

SystemsLand and Regulatory

Geology Geophysics

Drilling Engineering

Completion Engineering

Production Engineering

Reservoir Engineering

Systems Engineering

Source: Mark Reynolds, compilation

Upstream Systems & Knowledge Engineer

Page 20: 2016 06-07 data driven production

20 Copyright 2016 Southwestern Energy Company. All rights reserved.

Worst Practices• ROP-centric evaluations• Spreadsheet proliferation• Ad-hoc forensics• Compartmentalization• Long-lead topical analysis

Best Practices• Value propositions• Systems engineering• Spatial-temporal analytics• Intelligent Mining• Cross-Relationships

The Best Practices, Tomorrow

Source: Mark Reynolds, compilation

“Foster Tools and Foster Tool Support” - Jim Grey

Page 21: 2016 06-07 data driven production

21 Copyright 2016 Southwestern Energy Company. All rights reserved.

And – Keep Your Eye on the Machine

Page 22: 2016 06-07 data driven production

22 Copyright 2016 Southwestern Energy Company. All rights reserved.

Mark Reynolds

Mark Reynolds Vitae• Southwestern Energy• Lone Star College• Intent Driven Designs• Scan Systems• Sikorsky Aircraft• General Dynamics

SWN Email: [email protected]