Categories
Updates

Looking Back on Hacking for Houston 2020

Bringing together O&G technical experts and public health professionals

Earlier this year, before the era of social distancing and remote work, Petro.ai dedicated time and effort to give back to the community with data science. We created the “Hacking for Houston” event to give the Petro.ai user base a voice for good in the communities in which we live and work and partnered with Harris County Public Health (HCPH).

Watch now.

Uche Arizor, Team Lead at PHI Lab, the innovation arm of HCPH commented that, “Our mission is to facilitate cross-sector collaboration, creativity, and innovation in public health practice. Partnering with Petro.ai for Hacking for Houston 2020 was a great opportunity to bring people together from the sectors of oil & gas, data science, and public health to work on real issues that HCPH would like to address.” 

All of us were surprised when the night before the hackathon, a water main burst in downtown Houston (remember this?). After all the hard work put into organizing the event with our partner, the Public Health Innovations Lab (PHI Lab) at Harris County Public Health, we decided to press on with the event. We are so glad that we did!  Little did we know, this was our last opportunity to interact with a large group of people in our office space. More importantly, participants were able to deliver actionable insights!

We encouraged anyone with a passion for data science to attend, especially our clients and partners, as well as university students in data science and public health. We were unsure if attendees would still be able to join us in light of the water main break—but even the turnout for the optional two-hour morning workshop was fantastic. Shota Ota and other members of the Petro.ai support team covered tools and topics useful for the Hackathon. 

After lunch, the hackathon began with a high-intensity couple of hours where participants worked in teams of 1-3 people to build and code projects. Teams were not restricted to any particular software or tools to implement their solutions and people deployed a variety of tools including Power BI, Spotfire, R, python, ArcGIS, Excel, Jupyter notebooks, and even open-sourced 3D visualization software. 

Three Challenges were laid out to participants, each with actual data provided by HCPH. Teams then chose one of the available challenges to work on during the event. 

Go Upstream for Downstream Costs

Objectives:   

  • Identify the rates of preventable hospitalization types and charges from zip codes with the highest rates of preventable visits.  
  • Create profiles of select zip codes that explore trends in socio-demographics, health outcomes, and issues in health care access.   

Increase Government Efficiency

Objectives:   

  • Model the overlap and gap of services provided by current facility locations based on community need (population density, poor health outcomes, etc.) 
  • Identify pilot sites for the co-location of public health, clinical health, and mental health services, while justifying community needs around the site. 
  • Explore the impact of other public and private facilities that may offer similar services in affected communities.   

Reducing West Nile virus (WNV) Disease Risk

Objectives:   

  • Use disease, mosquito, environmental and population data from the past 4 years, to develop a model that predicts areas in Harris County at higher risk for WNV disease transmission compared to others.   
  • Identify the key factors that influence WNV disease risk in Harris County as a whole or in different clustered communities. 

At 5 pm, each team gave a 5-minute presentation or “pitch” to the panel of judges and other participants. Their projects were judged according to four categories: communication, technical achievement, creativity, and aesthetic. Our 2020 judges included Dr. Dana Beckham, Director of the Office of Science, Surveillance, and Technology, HCPH; Dr. Lance Black, Associate Director, TMCx; and Dr. Troy Ruths, Founder and CEO, Petro.ai.

The judges were impressed by all the teams and how much they were able to accomplish in just four hours. Each team presented their findings and their recommendations for HCPH. The winning team consisted of Callie Hall from the Houston Health Department, Elena Feofanova, a PhD candidate at UT Health, and Alex Lach, a reservoir engineer at Oxy. Their team chose Challenge 2, Increase Government Efficiency, and combined outstanding data analysis with a great pitch.  

Dr. Beckham, Director of the Office of Science, Surveillance, and Technology at HCPH, said, “The hackathon was a great way to network with future leaders and address public health issues in a creative and innovative way. Information taken back will be implemented to assist with making better business decisions to provide services to Harris County residents. It was a great opportunity for government (HCPH) and private industry (Petro.ai) to work together for equity and better health outcomes for the community.” 

The success of Hacking for Houston 2020 made it an easy decision for us to bring it back in the future. If you missed the event, joined the Petro.ai Community to stay up to date and hear about our next hackathon. 

Categories
Business Intelligence Tools Data Science & Analytics Updates

Hacking for Houston 2020: Improving Care in Our Community

As a proud member of the community, Petro.ai wanted to give back. We created the “Hacking for Houston” event to give the Petro.ai user base a voice for good in the communities in which we live and work. 

Bringing together O&G technical experts and public health professionals

Uche Arizor, Team Lead at PHI Lab commented that, “Our mission is to facilitate cross-sector collaboration, creativity, and innovation in public health practice. Partnering with Petro.ai for Hacking for Houston 2020 was a great opportunity to bring people together from the sectors of oil & gas, data science, and public health to work on real issues that HCPH would like to address.” 

All of us were surprised when the night before the hackathon, a water main burst in downtown Houston. The 610 East Loop was closed for several hours due to flooding. Our team exchanged e-mails to decide if we needed to cancel the hackathon, but felt reluctant to do so, after all the hard work put into organizing the event with our partner, the Public Health Innovations Lab (PHI Lab) at Harris County Public Health. Employees arrived early and decided to press on with the Hackathon; we are so glad that we did!  

We encouraged anyone with a passion for data science to attend, especially our clients and partners, as well as university students in data science and public health. We were unsure if attendees would still be able to join us in light of the water main break—but even the turnout for the optional two-hour morning workshop was fantastic. Shota Ota, Support Engineer, and Jason May, Data Scientist at Petro.ai covered tools and topics useful for the Hackathon. 

After lunch, the hackathon began with a high-intensity couple of hours where participants worked in teams of 1-3 people to build and code projects. Teams were not restricted to any particular software or tools to implement their solutions and people deployed a variety of tools including Power BI, Spotfire, R, python, ArcGIS, Excel, Jupyter notebooks, and even open-sourced 3D visualization software. 

Three Challenges were laid out to participants, each with actual data provided by HCPH. Teams then chose one of the available challenges to work on during the event. 

Go Upstream for Downstream Costs

Objectives:   

  • Identify the rates of preventable hospitalization types and charges from zip codes with the highest rates of preventable visits.  
  • Create profiles of select zip codes that explore trends in socio-demographics, health outcomes, and issues in health care access.   

Increase Government Efficiency

Objectives:   

  • Model the overlap and gap of services provided by current facility locations based on community need (population density, poor health outcomes, etc.) 
  • Identify pilot sites for the co-location of public health, clinical health, and mental health services, while justifying community needs around the site. 
  • Explore the impact of other public and private facilities that may offer similar services in affected communities.   

Reducing West Nile virus (WNV) Disease Risk

 Objectives:   

  • Use disease, mosquito, environmental and population data from the past 4 years, to develop a model that predicts areas in Harris County at higher risk for WNV disease transmission compared to others.   
  • Identify the key factors that influence WNV disease risk in Harris County as a whole or in different clustered communities. 

At 5 pm, each team gave a 5-minute presentation or “pitch” to the panel of judges and other participants. Their projects were judged according to four categories: communication, technical achievement, creativity, and aesthetic. Our 2020 judges included: 

The judges were impressed by all the teams and how much they were able to accomplish in just four hours. Each team presented their findings and their recommendations for HCPH. The winning team consisted of Callie Hall from the Houston Health Department, Elena Feofanova, a PhD candidate at UT Health, and Alex Lach, a reservoir engineer at Oxy. Their team chose Challenge 2, Increase Government Efficiency, and combined outstanding data analysis with a great pitch.  

Dr. Beckham, Director of the Office of Science, Surveillance, and Technology at HCPH, said, “The hackathon was a great way to network with future leaders and address public health issues in a creative and innovative way. Information taken back will be implemented to assist with making better business decisions to provide services to Harris County residents. It was a great opportunity for government (HCPH) and private industry (Petro.ai) to work together for equity and better health outcomes for the community.” 

The success of Hacking for Houston 2020 made it an easy decision for us to bring it back in the future. If you missed the event, joined the Petro.ai Community to stay up to date and hear about our next hackathon. 

Categories
Data Science & Analytics Transfer

The Future of AI in O&G

On November 25th, Petro.ai Founder and CEO, Dr. Troy Ruths, was a guest on the Invest with James West podcast series hosted by James West, Senior Managing Director & Partner at Evercore ISI. During the 30-minute podcast, James and Troy discuss trends of artificial intelligence and machine learning in the oil and gas industry and how Petro.ai is changing the way E&P companies plan, develop, and operate their assets.

The Role or AI

The creation and application of artificial intelligence requires a lot of data. Oil and gas operators have always generated large quantities of data, but the massive increase in activity the industry has seen as a result of unconventionals created an ideal environment for AI. Each well, and even each stage, can be seen as a unique data point where operators are constantly changing and experimenting. The real power of AI is in unlocking all this data.

People think of AI at the top of the pyramid,” says Troy. “But the future is with AI at the bottom of the pyramid—the new backbone that serves information up to the enterprise, and humans are going to remain at the top of the pyramid.” This view represents a departure from how many individuals see AI but promises a much greater impact to operators. Engineers today think about their data in terms of spreadsheets or databases. The data layer of the future provides significantly more context while being much more intuitive. This is the role played by Petro.ai, intelligently storing, integrating, and activating more than 60 types of oil and gas specific data, as well as associated metadata. Many of these data types that are ingested by Petro.ai, like microseismic events, fiber, or electromagnetic imaging data don’t have a standard home today.

Challenges to AI Adoption and Change

 “I would negatively correlate ability to adopt new technology to oil price. The better the oil price is, the harder it is to get technology adoption,” remarked Troy. The current price environment is ideal for technology adoption, especially when it comes to AI. Operators are at a point now where they need digital tools to help them do more with less. The other impediment to AI adoption revolves around education. AI can mean a lot of different things to different people and there is a level of education that still needs to take place to inform the industry on how AI can best fit into their organizations.

Troy goes on to explain another challenge, “AI can only extrapolate from what it’s seen, and that can be a problem in a world where the solution may be outside of what we’ve actually tried in the past.” Petro.ai incorporates principles of geomechanics into our workflows, bridging the gap between what we know from physics with machine learning.

AI in Upstream O&G

When prompted by James on the differentiated approach upstream analytics, Troy noted that “A lot of the new software that has entered the space is focused on operational efficiency and labor.…but honesty, those aren’t going to be needle moving enough for the industry. We’re focused on the needle moving problem, which is how can we reengineer.  We need to reengineer how we approach these unconventional assets.” Good engineering done in the office is going to drive real improvements.

With recovery factors, well spacing, or frac hits, operators really need to focus on the productivity drivers for a resource unit. These questions cannot be investigated in isolation and some of the best practices we have seen come from bundling disparate workflows together. For example, a completions engineer may want to look at several different data types simultaneously. They may want to look at and ask questions about geology, drilling or surface constraints. This example goes back to humans being on top of the pyramid. The engineer needs to be fed with the relevant information, which is where AI can really help. Petro.ai not only serves up this data, but also uses a complex system model built using geomechanics and machine learning that takes engineers through an 8-step workflow to understand the key productivity drivers for a resource unit.

2020 Outlook

The industry has clearly learned that unconventionals are extremely difficult to develop profitably – even in the Permian. These are very complex systems with stacked pay that will require good engineering to be properly developed. This is good news for digital companies in 2020. In a broader sense, Troy sees operators evolving “towards surgical development, we’re going to go away from factory drilling and go more towards surgical.” However, some operators are clearing embracing digital more than others and so we expect a clear bifurcation in operator performance.

Listen to the podcast for the full discussion on AI and machine learning in oil and gas and the future for data in the energy sector.

Categories
Reservoir Engineering Transfer

A Whole New Look to Production Forecasting

Petro.ai 4 is here and it’s a big one! Major updates have been added throughout, including an all new web application supporting decline curve analysis as well as machine learning. Users familiar with our previous decline curve tools will recognize some of the intuitive features but now you can batch decline wells and create type curves all in the web. Decline models can be easily moved between ARIES, Spotfire, Excel, and Petro.ai; allowing users to easily compliment existing workflows.

In your browser you can view your wells and filter by any number of parameters to quickly navigate to wells of interest.

Figure 1: Load in public and/or private data, view your wells on an interactive map and easily filter down to your wells of interest.

Type curves are easier than ever! You can dynamically select wells and update oil, gas, and water type curves. These type curves can be saved back to Petro.ai for the same sort of manual tweaking as a single well decline. They are also version controlled and can be recalled and overlaid on new models.

Figure 2: Dynamically generate probabilistic type curves directly from your selection.

Like our previous forecasting tools, you can configure your default decline parameters. Now you can save your defaults or have different set of default parameters for different basins or situations that can be quickly recalled. Flags can be configured to give a quick overview of the quality of fit to enable management by exception.

Figure 3: Configure your decline model and parameters; as well as setup flags for management by exception.

The intuitive user interface puts control at your fingertips – switch to a rate-cum view or toggle on/off individual fluid streams.

Figure 4: Easily switch how you view the declines.

This release of Petro.ai introduces a new social collaboration framework; a first for our industry. You can comment on any data point or model. These comments facilitate collaboration and capture key insights right next to the relevant data. You can also send notifications using @ or create searchable keywords with #.

Figure 5: Comment on any data point, use @notifications and #keywords.

It’s now easier than ever to see how changes to a single decline parameter effect a wells productivity.

Figure 6: Update the auto-forecast and instantly see how the changes effect remaining reserves and EUR.

The production forecasting app is great for asset teams, A&D teams, and even reserves teams. With full audit traceability and a built in approvals workflow, decline models are version controlled and can be rigorously managed.

Figure 7: Decline models are automatically version controlled and tracked for auditability. Petro.ai also supports approval workflows.

Categories
Database, Cloud, & IT Transfer

Petro.ai Joins OSDU

Petro.ai is proud to announce that it joins industry leaders Schlumberger, Chevron, Microsoft, Shell, and others in membership in the Open Subsurface Data Universe™ Forum.  The OSDU is developing a cloud-native data platform for the oil and gas industry, which will reduce silos and put data at the center of the subsurface community.

Membership in the OSDU Forum gives Petro.ai a seat at the table in developing the latest standards in petrotechnical data access and integration. Leveraging the OSDU data platform, Petro.ai accelerates the oil and gas digital transformation: empowering asset teams to organize, share, and interact with data like never before.

Learn more about the OSDU here.

Categories
Drilling & Completions Transfer

Rig Count and Operator Size: Recent Trends

Like many in our industry, the team here at Petro.ai keeps a close eye on oil prices, rig count, and analyst reports to stay in tune with what’s happening. Richard Gaut, our CFO, and I were discussing the recent trends in the rig count which led us to dive into the data. Essentially, we were curious as to how different types of E&P’s are adjusting their activity in the current market. There’s been a lot of news recently on how the super-majors are now finally up to speed in unconventionals and that smaller operators won’t be able to compete.

Figure 1: North American Rig Count (from BakerHughes)

The figure above shows the North American rig count from BakerHuges and we can see the steady recovery from mid-2016 through 2018, followed by another decline in 2019. But has this drop been evenly distributed among operators? TPH provides a more detailed breakdown of the rig count, segmenting the rigs by operator. I put the operators into one of three buckets:

  • Large-cap and integrated E&P’s
  • Mid-cap and small-cap publicly traded E&P’s
  • Privately held E&P’s

The figure below shows the breakdown between these three groups overlaid with the total rig count. You can see the mid and small caps in yellow are a shrinking segment. Figure 3 shows these groups as percentages and makes the divergence between the groups extremely visible.

Figure 2: Rig count segmented by operator type

Figure 3: Percentage breakdown of rigs by operator type

Since the recovery in 2016, privately held companies have taken on a larger share of the rigs and that trend continues through the recent downturn in 2019. This is likely because they are tasked by their financial backers to deploy capital and have no choice but to keep drilling. The large-caps and integrated oil companies have been staying constant or growing slightly since mid-2016 as has been reported. These operators have deep pockets and can offset losses in unconventionals with profits made elsewhere – at least until they become profitable. The story is very different for the small and mid-caps. These operators have experienced the sharpest drop in activity as they are forced by investors to live with in their cash flows.

The data used in this analysis were pulled at the end of September. We typically see a slowdown in activity in Q4 and recent news shows that this slowdown might be worse than normal. It’s likely the divergence we see will only continue through the end of the year.

Next, I split out the rig count by basin and found some interesting trends there which I’ll elaborate on in a second blog post.

Categories
Business Intelligence Tools Geology & Geoscience Reservoir Engineering Transfer

View Well Logs in Spotfire with Petro.ai

https://www.youtube.com/watch?v=NLbAUo38szs

Well logs are a critical input into many engineering and geoscience workflows. However, integrating well logs can be a challenge as many workflows move to tools like TIBCO Spotfire which cannot natively load LAS files or view logs on a vertical plot. This is especially true in unconventionals where engineers typically use a combination of Spotfire and/or Excel rather than more specialized tools like Petrel to design wells.

Petro.ai lets you:

  • Organize LAS files in once place
  • Dynamically load well logs into Spotfire
  • Use Spotfire to view and interact with well logs
  • Access well logs through a REST API
Categories
Data Science & Analytics Drilling & Completions Transfer

Demystifying Completions Data: Collecting and Organizing Data for Analytics (Part 3)

As mentioned in my previous post, in order to really be of value, we need to extend this analysis to future wells where we won’t have such a complete data set. We need to build multi-variate models using common, “always” data – like pump curves, geologic maps, or bulk data. Our approach has been for engineers to build these models directly in Spotfire through a side panel we’ve added but save these models back to a central location so that they can be version controlled and accessed by anyone in the organization. They can quickly iterate through a variety of models trained on our data set to review the model performance and sensitivity.

If we have access to historical information from previous wells, we can run our model on a variety of data sets to confirm its performance. This could be past wells that had micro seismic or where we knew there were issues with containment. Based on these diagnostics we can select a model to be applied by engineers on future developments. In order to make sure the model is used correctly we can set fences on the variables based on our training set to ensure the models are used appropriately. Because the models are built by your team – not a third-party vendor – they know exactly what assumptions and uncertainties went into the model. This approach empowers them to explore their data and answer questions without the stigma of a black-box recommendation.

Figure 1: Your team builds the models in Petro. ai – not a third-party vendor – so you know exactly what assumptions and uncertainties went into it. This approach empowers you to explore your data in new ways and answer questions without the limitations of black-box recommendations.

However, in addition to fences, we need to make sure engineers understand how and when to apply the models correctly. I won’t go into this topic much but will just say that the direction our industry is moving requires a basic level of statistics and data science understanding by all engineers and geologists, because of this Ruths.ai has incorporated training into our standard engagements.

Slightly different hypothesis

This example used a variety of data, but it only answers one question. It’s important to note that even slight variations in the question we ask can alter what data is needed. In our example, instead of asking if a specific frac design would stay within our selected interval, we wanted to know if the vertical fracture length changed over time, we would need a different data set. Since micro seismic is a snapshot in time we wouldn’t know if the vertical frac stays open. A different data type would be needed to show these transient effects.

Data integration is often the biggest hurdle to analytics

We can start creating a map to tie back the required data needed for the questions we are interested in answering. The point of this diagram shown here is not to demonstrate the exact mapping of questions to data types, but rather, to illustrate how data integration quickly becomes a critical part of this story. This chart shows only a couple questions we may want to ask, and you can see how complicated the integration becomes. Not only are there additional questions, but new data types are constantly being added; none of which add value in isolation – there is no silver bullet, no one data type that will answer all our questions.

Figure 2: Data integration quickly becomes complicated based on the data types needed to build a robust model. There is no silver bullet. No single data type can answer all your questions.

With the pace of unconventional development, you probably don’t have time to build dedicated applications and processes for each question. You need a flexible framework to approach this analysis. Getting to an answer cannot take 6 or 12 months, by then the questions have changed and the answers are no longer relevant.

Wrap up

Bringing these data types together and analyzing them to gain cross-silo insights is critical in moving from science to scale. This is where we will find step changes in completions design and asset development that will lead to improving the capital efficiency of unconventionals. I focused on completions today, but the same story applies across the well lifecycle. Understanding what’s happening in artificial lift requires inputs from geology, drilling and completions. Petro.ai empowers asset teams to operationalize their data and start using it for analytics.


Three key take ways:

  • Specific questions should dictate data collection requirements.
  • Data integration is key to extracting meaningful answers.
  • We need flexible tools that can operate at the speed of unconventionals.

I’m excited about the progress we’ve already made and the direction we’re going.

Categories
Data Science & Analytics Drilling & Completions Transfer

Demystifying Completions Data: Collecting and Organizing Data for Analytics (Part 2)

As promised, let’s now walk through a specific example to illustrate an approach to analytics that we’ve seen be very effective.

I’m going to focus more on the methodology and the tools used rather than the actual analysis. The development of stacked pay is critical to the Permian as well as other plays. Containment and understanding vertical frac propagation is key to developing these resources economically. We might want to ask if a given pumping design (pump rate, intensity, landing) will stay in the target interval or break into other, less desirable rock. There are some fundamental tradeoffs that we might want to explore. For example, we may break out of zone if we pump above a given rate. If we lower the pump rate and increase the duration of the job, we need to have some confidence that the increase in day rates will yield better returns.

We can first build simulations for the frac and look at the effects of different completions designs. We can look at offset wells and historical data – though that could be challenging to piece together. We may ultimately want to validate the simulation and test different frac designs. We could do this changing the pumping schedule at different stages along the lateral of multiple wells.


Data collection

With this specific question in mind, we need to determine what data to collect. The directional survey, the formation tops (from reference well logs) and the frac van data will all be needed. However, we will also want micro seismic to see where the frac goes. Since we want to understand why the frac is either contained or not we will also need the stress profile across the intervals of interest. These could be derived from logs but ideally measured from DFITs. We may also want to collect other data types that we think could be proxies to relate back to the stress profile, like bulk seismic or interpreted geologic maps.

These data types will be collected by different vendors, at different times, and delivered to the operator in a variety of formats. We have bulk data, time series data, data processed by vendors, data interpreted by engineers and geologists. Meaningful conclusions cannot be derived from any one data type, only by integrating them can we start to see a mosaic.

Integration

Integrating the data means overcoming a series of challenges. We first need to decide where this data will live. Outlook does not make a good or sustainable data depository. Putting it all on a shared drive is not ideal as it’s difficult to relate. We could stand up a SQL database or bring all the data into an application and let it live there but both have drawbacks. Our approach leverages Petro.ai which uses a NoSQL back end. This provides a highly scalable and performant environment for the variety of data we will need. Also, by not trapping the data in an application (in some proprietary format) it can easily be reused to answer other questions or by other people in the future.



Getting the data co-located is a start but there’s more work to be done before we can run analytics. Throwing everything into a data lake doesn’t get us to an answer and it’s why we now have the term “data swamp”. A critical step is relating the data to each other. Petro.ai takes this raw data and transforms it using a standard, open data model and robust well alias system; all built from the ground up for O&G. For example, different pressure pumping vendors will have different names for common variables (maybe even different well names) that we need to reconcile. We use a well-centric data model that currently supports over 60 data types and exposes the data through an open API.



Petro.ai also accounts for things like coordinate reference systems, time zones, and units. These are critical corrections to make since we want to be able to reuse as much of our work as possible in future analysis. Contrast this approach with the one dataset – one use case approach where you essentially rebuild the data source for every question you want to ask. We’ve seen the pitfalls of that approach as you quickly run into sustainability challenges around supporting these separate instances. At this point we have an analytics staging ground that we can actually use.

Interacting with and analyzing data

With the data integrated we need to decide how users are going to interact with the data. That could be through Matlab, Spotfire, python, excel, or PowerBI. Obviously, there are trade-offs here as well. Python and Matlab are very flexible but require a lot of user expertise. We need to consider not only the skill set of the people doing the analysis, but the skill set of the those who may ultimately leverage the insights and workflows. Do only a small group of power users need to run this analysis, or do we want every completions engineer to be able to take these results and apply them to their wells? We see a big push for the latter and so our approach has been to use a combination of custom web apps we’ve created along with O&G specific Spotfire integrations. Spotfire is widespread in O&G and it’s great for workflows. We’ve added custom visualizations and calculations to Spotfire to aid in the analysis. For example, we can bring in the directional surveys, grids, and micro seismic points to see them in 3D.


Figure 4: Petro.ai enables a user friendly interface, meeting engineers where they are already working with integrations to Spotfire and web apps.

We now have the data merged in an open, NoSQL back end, and have presented that processed data to end users through Spotfire where the data can be visualized and interrogated to answer our questions. We can get the well-well and well-top spacing. We can see the extent of vertical frac propagation from the micro seismic data. From here we can characterize the frac response at each stage to determine where we went out of zone. We’re building a 360 view of the reservoir to form a computational model that can be used to pull out insights.

In the third and final post of this series, we will continue this containment example and review how we can extend our analysis across an asset. We’ll also revisit the data integration challenges as we expand our approach to other questions we may want to ask while designing completions.

 

Categories
Data Science & Analytics Drilling & Completions Transfer

Demystifying Completions Data: Collecting and Organizing Data for Analytics (Part 1)

The oil and gas industry collects a huge amount of data trying to better understand what’s happening in the subsurface. These observations and measurements come in a range of data types that must be pieced together to garner insights. In this blog series we’ll review some of these data types and discuss an approach to integrating data to better inform decision making processes.

Before getting into the data, it’s important to note why every company needs a data strategy. Capital efficiency is now the name of the game in unconventionals. Investors are pushing for free cash flow, not just year over year increases in production. The nearby slide is from one operator but virtually every investor deck has a slide like this one. There are positive trends that operators can show – price concessions from service providers, efficiency gains in drilling, completions, facilities and increases in lateral length. Despite these gains, as an industry, shale is still not profitable. How much further can operators push these trends? How will this chart be created next year? Single-silo efficiencies are gone, and the next step change will only come from an integrated approach where the data acquired across the well lifecycle can be unlocked to fuel cross-silo insights.

Figure 1: Virtually every investor deck has a figure like this one. There are positive trends that operators can show– price concessions from service providers, efficiency gains in drilling, completions, facilities and increases in lateral length. Despite these gains, as an industry, shale is still not profitable. How much further can operators push these trends? How will this chart be created next year?

This is especially true in completions, which represent 60% of the well costs and touches so many domains. What does completions optimization mean? It’s a common phrase that gets thrown around a lot. Let’s unpack this wide-ranging topic into a series of specific questions.

  1. How does frac geometry change with completions design?
  2. How do you select an ideal landing zone?
  3. What operations sequence will lead to the best outcomes?
  4. What effect does well spacing have on production?
  5. Will diverter improve recovery?

This is just a small subset, but we can see these are complex, multidisciplinary questions. As an industry, we’re collecting and streaming massive amounts of data to try and figure this out. Companies are standing up centers of excellence around data science to get to the bottom of it. However, these issues require input from geology, geomechancis, drilling, reservoir engineering, completions, and production – the entire team. It’s very difficult to connect all the dots.

There’s also no one size fits all solution; shales are very heterogenous and your assets are very different from someone else’s, both in the subsurface and surface. Tradeoffs exist and design parameters need to be tied back to ROI. Here again, there are significant differences in strategy depending on your company’s strategy and goals.

Managing a data tsunami

When we don’t know what’s happening, we can observe, and there’s a lot of things we can observe, a lot of data we can collect. Here are some examples that I’ve grouped into two buckets: diagnostic data that you would collect specifically to better understand what’s happening and operational data that is collected as part of the job execution.

The amount of data available is massive – and only increasing as new diagnostics techniques, new acquisition systems and new edge devices come out. What data is important? What data do we really need? Collecting data is expensive so we need to make sure the value is there.

Figure 2: Here are some examples of diagnostic data that you would collect specifically to better understand what’s happening and operational data that is collected as part of the job execution.

The data we collect is of little value in isolation. Someone needs to piece everything together before we can run analytics and before we can start to see trends and insights. However, there is not standards around data formats or delivery mechanisms and so operators have had to bear the burden of stitching everything together. This is a burden not only for the operators, but also creates problems for service providers whose data is delivered as a summary pdf with raw data in Excel and is difficult to use beyond of the original job. The value of their data and their services is diminished when their work product has only limited use.

Thinking through an approach

A common approach to answering questions and collecting data is the science pad, the scope of which can vary significantly. The average unconventional well costs between $6 and 8M but a science pad can easily approach $12M and that doesn’t take into account costs of the time people will spend planning and analyzing the job. This exercise requires collecting and integrating data, applying engineering knowledge, and then building models. Taking science learnings to scale is the only way to justify the high costs associated with these projects.

Whether on a science pad or just as part of a normal completions process, data should be collected and analyzed to improve the development strategy. A scientific approach to completions optimization can help ensure continuous improvement. This starts with a hypothesis – not data collection. Start with a very specific question. This hypothesis informs what data needs to be collected. The analysis should then either validate or invalidate our hypothesis. If we end there, we’ve at least learned something, but if we can go one step further and find common or bulk data that are proxies for these diagnostics, we can scale the learnings with predictive models. Data science can play a major role here to avoid making far reaching decisions based off very few sample points. Just because we observed something in 2 or 3 wells where we collected all this data does not mean we will always see the same response. We can use data science to validate these learnings against historical data and understand the limits where we can apply them versus where we may need to collect more data.

In part 2 of this series, we’ll walk through an example of this approach that addresses vertical frac propagation. Specifically, we’ll dive into collecting, integrating, and interacting with the required data. Stay tuned!