blogger counters

Sunday, January 27, 2019

Risk Mgmt Unit 4: Using Blockchain to Eliminate Counterfeit Electronics: Scenarios and Simulations

Learn how to develop probabilistic models using machine learning and other analytic tools to identify and quantify risk. Identify effective ways to use scenarios and simulations, especially in a collaborative environment or context, to identify risks and manage them by using all available combinations of resources. Describe how blockchain is revolutionizing the supply chain.

Unit Presentation:


PDF (contains links to readings, etc.)
Scenario 4:  Using Blockchain to Eliminate Counterfeit Electronics: Scenarios and Simulations

Emily and Charles are worried. They’ve agreed to put sensors on all the pumps, gas gathering systems, in pipelines, injection wells, and disposal wells.

They hope to eliminate the need for field techs to have to check installations every day, and they want to be able to predict maintenance schedules, as well as where / when to maintain corrosion control, and when to replace equipment. They want to move away from a rigid schedule of maintenance and move to a more “reality based” maintenance and replacement.

However, they are worried. Their entire model depends on high-quality sensors and electronic components that do the job they’re supposed to do.

They’ve come to find out that an alarming percentage of electronic components are counterfeit, which means that they do not do what they’re supposed to do. That’s a terrifying thought when one considers that all the decisions are made based on the readings that the sensors and components deliver via the Industrial Internet of Things (IIoT).

Your Task: Help Emily and Charles come up with a plan to make sure that all that the components they have are authentic.

• Develop a plan for Emily and Charles to work with their suppliers to use Blockchain technology to assure authenticity.

• Also, help Emily and Charles develop a plan to use the information from the IIoT to determine when and how to maintain and replace equipment.

• Explain to Emily and Charles how to brainstorm using mind-mapping and role-playing with other team members.

• Develop recommendations for both supply chain integrity (using blockchain) and maintenance / replacement protocols and best practices for the company.


Thinking about Scenarios:

 How to do them
 Define the elements
  What can happen?
  Who is impacted?
  Who can do anything?

 Mind maps


 Group activity (collaborative online and face to face)
 What is the information that you need?
 What is the situation?
 What are the variables?
 What can be controlled?
 What is the flow? (mapping / workflow)
 How to get started:  software
 Dealing with complexity
 Possible outcomes: listing / prioritizing
 Quantifying possible consequences


Future directions:

What is Blockchain Technology?  A Step-by-Step Guide for Beginners

Blockchain Fundamentals:

“Every time a product changes hands, the transaction could be documented, creating a permanent history of a product, from manufacture to sale”

Vorabutra, Jon-Amerin, (2016) Why Blockchain is a Game-changer in Supply  Chain Management Transparency.

TAMUT  MBA in Energy Leadership: Click link to apply - more information

For more information about the courses (and this full course), please contact me.

Risk Mgmt Unit 3: Predicting Risk: Approaches using Artificial Intelligence and Machine Learning

Upon successful completion of this unit, learners will be able to identify how to use artificial intelligence and machine learning to predict levels and types of risk, both known and unknown.  Links to open source platforms, languages, and computing environments are provided.  It is not necessary to learn the computing languages or to develop new code or programs; the goal of this unit is to familiarize learners in order to work effectively in teams with data scientists, domain experts, and financial decision-makers.

Unit Presentation:


PDF (contains links to readings, etc.)  

Scenario 3:  Predicting Risk: Approaches using Artificial Intelligence and Machine Learning

Julia, Patricio, and Reyna are part of a team that is tasked with classifying old shallow-water offshore wells in the Gulf of Mexico in new ways that will help them develop a plan to boost production. 

They feel very fortunate in that around a million geological and production records have been scanned, and they cover the 150 or so wells in the field.  It’s a treasure trove of data, and they want to incorporate it with the new data in order to develop a profile of the best wells, as well as the good, mediocre, and underperforming wells.

Your Task: Help Julia, Patricio, and Reyna develop a plan to analyze the data, and then help them determine where, when, and how they can use artificial intelligence and machine learning to create profiles.

Here are a few things to consider:
 How will you select the data to use?
 How will you organize it?

What does it mean for a well to be:

What are the attributes or clusters of characteristics you’ll use?
 What approach will you use to select data?
  To clean the data?
  To analyze the data?
 What kind of AI / ML approach will you use?
 How will you use the results?


Overview thoughts / concepts

Lists of uses of AI / Machine Learning the energy industry
  Classify wells using your own unique set of criteria
  Identify high-value (or potential high-value) blocks
  Classify infrastructure (pipelines, etc) with your own criteria
  Predict overall performance and the location of bottlenecks
  Retail / distribution
 Wind energy  Identify high-value, high-return new locations
  Identify small businesses that would benefit from local energy
 Solar energy
Workflow for machine learning (in general)

● Pinpoint the problem you want to solve.
● Identify the data you’ll need to use
● Collect the data
● Clean the data
● Organize your data (put into a model - if structured, may use Open Source models such as those from Apache HaDoop)
● Find a model
● Develop algorithms (May use repositories and also cloud-based interfaces)
● Train the model
● Test with data sets
● Reality check
● Decision points

How do I clean data?
 What is “dirty” data? 
  Does not make sense
  Bad labels
  Incorrect formatting
  Too many “nulls”
  Part of the data in a different order or different columns

Brendon Bailey’s Guide:  Use Excel or Python to Clean Data?

Use Excel if: You have fewer than 1 million records
You need to do the job quick and easy
There is a logical pattern to cleaning the data and it’s easy enough to clean using Excel functions
The logical pattern to cleaning the data is hard to define, and you need to clean the data manually

When you might use Python or another scripting language:

Use Python if: You need to document your process
You plan on doing the job on a repeat basis
There is a logical pattern to cleaning the data, but it is hard to implement with Excel functions

Brendon Bailey. “Data Cleaning 101”

Where do you keep the data?
 cloud solutions (Google, Amazon Web Services (AWS))

Software for risk analytics (free / open source):

Spotfire ( (free Spotfire alternative,
Jupyter Notebook

A Gallery of interesting Jupyter Notebooks (ready to share)

How do we predict where and when high-risk situations may take place?
 Analyze data
 Probabilistic analysis (Spotfire, etc.)
 Using geospatial elements

What is the ideal combination of variable or factors to tell us when / where / how conditions are ideal for a) optimization; b) an accident or problem ?
 Use multivariate analysis
 Bring together all risk factors: geological, logistical, political, economic, legal, environmental, etc.
 Weight them by importance (assign a percentage)

Learn and Use Machine Learning


Tensorflow Machine Learning Cookbook:

AI and Probabilistic Models

Part I

Part II

Bougher, Benjamin Bryan. (2016)  Machine Learning Applications to Geophysical Data Analysis. Open Collections. University of British Columbia.

Bougher, Ben B. (2016) Using the scattering transform to predict stratigraphic units from well logs. Seismic Laboratory for Imaging and Modeling (SLIM), The University of British Columbia, Vancouver

Data:  Trenton Black River gamma ray logs

Methodology:  supervised learning ("uses labelled datasets to train a classifier to make predictions about future data" (Bougher, 2016))

Methodology - what's the algorithm?  Bougher uses a scattering transform - and then it fieeds a K-Nearest Neighbours (KNN) classifier).

How can I do this?

Using convolutional neural networks to solve a mineral prospectivity mapping problem
Framing the exploration task as a supervised learning problem, the geological, geochemical and geophysical information can be used as training data, and known mineral occurrences can be used as training labels. The goal is to parameterize the complex relationships between the data and the labels such that mineral potential can be estimated in under-explored regions using available geoscience data.

Granek, Justin. (2016). Application of Machine Learning Algorithms to Mineral Prospectivity Mapping. Open Collections. University of British Columbia.

TAMUT  MBA in Energy Leadership: Click link to apply - more information

For more information about the courses (and this full course), please contact me. 

Risk Mgmt Unit 2: Cascading Risks: Workflows for Risks

Learn to identify and evaluate cascading risks and causal chains is the goal of this unit, with easy-to-use tools for creating flow charts and maps for analysis and decision-making.
• Determine the data you need to understand systemic risks
• Identify the relationships that lead to cascading risks
• Discuss ways do develop workflows of flows of risks
• Identify the locations most likely to trigger cascading failures
• Identify the types of risks associated with the failures
• Describe methods of analyzing cascading risks using several analytical techniques
• Explain how a Bayesian analysis can be effective for identifying relationships

Unit Presentation:

PDF (contains links to readings, etc.)

Scenario 2:  Cascading Risks:  Workflows for Risks
Joseph works for Wolf Midstream, which recently diversified into solar and wind energy to generate electricity for the grid in northeastern Texas and southwest Arkansas. 

Things have been going well.  However, the weather forecast says there is a high likelihood of a tornado outbreak near their solar panel farm and also near the Wolf wind farm. Wolf Midstream is connected with Lone Wolf Electric, which owns transmission lines into the small towns and rural homes.

The leadership of Wolf wants a report that provides 3 different scenarios for different levels of storms.  They want to know what all the potential impacts will be, and how they will affect each other.

Your Task: Help Joseph develop a map that shows how damage in one place will affect other places, resulting in causal chains, and cascading failures.

What will Joseph need?
 Which data does she need to collect?
 What kind of maps should she build?
 Use a diagram to show with arrows the cascading failures.
 Then, mark on a map where the problems will occur (after you’ve completed the diagrams).

You may wish to create 4 different maps:
 Stage 1: Initial impact
 Stage 2:  Secondary impact
 Stage 3:  What happens after Stage 2 failures occur
 Stage 4:  Final level of outcomes (long-term consequences).


“Risk relationships and cascading relationships in critical infrastructures”,%202014.pdf

Destruction of infrastructure => disruption of supply chain => disruptions in global / local manufacturing (or mining, etc.)

Bottlenecks (constraints)
Strategic Supply Chain Mapping Approaches

Mapping Supply Chain Constraints in LPG
Analysis of Liquified Petroleum Gas (LPG) Shortage in Ghana: Case of the Ashanti Region

Bayesian networks:
Bayesian Network Tools in Java:

Getting started:

Texas AM Texarkana TAMUT MBA in Energy Leadership: Click link to apply - more information

For more information about the courses (and this full course), please contact me. 

Risk Mgmt Unit 1: Identifying and Quantifying Risks in the Energy Industry Using Heat Maps

Upon successful completion of this unit, learners will be able to identify and define risks in the energy industry (petroleum, natural gas, alternative), and construct risk heat maps for analysis, strategic planning and decision-making.

Unit Presentation: 
Pdf:  (contains links to readings):


Scenario 1:  The Real Risks:  Identifying and Quantifying Using Heat Maps

Mark, Tamara, and Talib have put together a small company, Invictus Energy, with the goal of buying two or three small mature fields that also has a pipeline and gas gathering system. 

 Their goal is to revitalize the fields, renegotiate contracts, and then sell the fields and the gas gathering system and pipelines. They have obtained private equity financing, but are a bit alarmed at how much personal "skin in the game" they have to put up.

They are required to put in their own savings and assets, which makes them very nervous. But, they believe they can boost the production and recoverable reserves by 50%.  They are worried because the pumps are old, and the pipeline and gas gathering systems have not had any corrosion control or maintenance in many years.

Your Task:  Help Mark, Tamara, and Talib identify and rank the risks. Then, help them create a heat map so they can make sound financial decisions.

 --What are the kinds of risks that Invictus Energy will face?
 --What is the probability and potential impact of each?
 --What does a risk heat map look like for Invictus?
 --What are 3 or 4 decisions that the heat map can help with?


Unit Presentation:

Heat Maps – where how to build them 

Example: Upstream oil and gas exploration and development
 Geological Risk (model, quality of information, imaging)
 Legal risk (title, etc.)
 Analytics risk (model, organization of information)
 Data Acquisition Risk
 Safety risk
 Drilling Risk (out of zone)
 Hydraulic fracturing risk
 Completion Risk 

Other examples:  Solar and wind energy generation and distribution.

Texas A&M Texarkana MBA in Energy Leadership: Click link to apply - more information

For more information about the courses (and this full course), please contact me. 

Blog Archive