• Products
    • Products Overview
    • Oil and Gas Data
    • Oil and Gas Software
  • ML in Oil & Gas Blog
  • Resources
  • News & Events
    • Company News
    • Conference Presentations
  • About
    • About Novi Labs
    • Careers
  • Contact
Novi Labs
  • Skip to primary navigation
  • Skip to main content
  • Skip to footer
get started on your future of well planning with Novi

Novi Labs

  • Products
    • Products Overview
    • Oil and Gas Data
    • Oil and Gas Software
  • ML in Oil & Gas Blog
  • Resources
  • News & Events
    • Company News
    • Conference Presentations
  • About
    • About Novi Labs
    • Careers
  • Contact

Analyzing Vista’s Record-Setting Vaca Muerta Wells with Oil and Gas Machine Learning Models

August 26, 2020

About the author

Ted Cross

Ted Cross is a Technical Advisor at Novi, where he applies his background in geology to ensure Novi's predictive analytics align with customer development planning problems. Prior to Novi, Ted was a Senior Geologist with ConocoPhillips.

After the Great Coronavirus Shut-In, Vista Oil & Gas turned back on their new Vaca Muerta pad. A pleasant surprise greeted them. Their oil and gas machine learning model showed the highest production the play had ever seen. Both the MDM-2063 and MDM-2061 wells produced over 2,000 bbl/d on average for the month, with peak daily rates breaching 3,000 boe/d.

Why did these wells produce so much? Was it a novel completion design, a geologic hot spot, or a heavy tailwind of flush production? Lets explore this oil and gas machine learning use case. We will put these wells under the microscope with our Vaca Muerta public-data model.

Breakdown:

  1. Background: Vista and their record-setting pad
    1. Investigating “outlier” performance with oil and gas Machine Learning Models
      1. Vista Well Model Forecasts
        1. Flush Production Analysis
        2. Assessing production drivers with SHAP values
          1. Studying the SHAP Values with oil and gas machine learning models
          2. Digging Deeper into the oil and gas machine learning model: analyzing the results of Vista’s V2 & V3 Completion Tests on total production and product mix
            1. 6-month and 3-Year Analyses
            2. Conclusions

              Background: Vista and their record-setting pad

              Vista Oil & Gas is led by the former CEO of YPF, Miguel Galuccio. Originally backed by Riverstone and the Abu Dhabi investment council, Vista pitches itself as ‘the only pure shale play of Vaca Muerta listed on the New York Stock Exchange’. The company has over 137,000 acres in the play, along with some legacy production (mostly located in the Neuquen Basin). That background alone makes the company worth following.

              Vista has brought on three Vaca Muerta Pads, with the latest coming online in February. The first two pads had strong results, but the third.…was excellent.

              Machine learning in oil and gas model showing SHAP values (colored bars), and baseline production expectation (gray) for Vista Pad 3, including the record setting wells (MDM-2061 and MDM-2063).
              Histogram of peak-month production (average daily rate) for Vaca Muerta wells. Bars are colored by operator (the dark red is YPF). The huge chunk of wells near-zero are wells form the gas window of the play. Just how outstanding were the Vista wells? Basically, they fell off the end of the chart. These were P99.9 results.

              Let’s take a look in a little more detail at Vista’s record-setting pad. When we build a machine learning oil and gas data model, we also produce a cleaned, joined one-line file that is published to Novi Cloud. This is a great dataset for competitor surveillance. Their two La Cocina wells set records while their two Orgánico target wells produced significantly less.

              Vista's machine learning driven well design specs for the record-setting pad
              Well designs from Vista’s record-setting pad.

              The record-setting wells were long laterals with BIG jobs: 8,871′ and 9,839′ length, with 2,750 #/ft proppant and ~2,400 gal/ft fluid loading. Furthermore, these put them near the high end of North American designs. As the visualization below shows, they’re at the far high end for all Vaca Muerta wells.

              lateral length, proppant loading and fluid loading as examples of using machine learning models in oil and gas
              Distribution of lateral length, stage spacing, proppant loading, and fluid loading for Vaca Muerta wells, colored by operator. Vista’s record-setting wells are called out on each chart. For each design parameter, Vista’s wells sit on or near the edge of the distribution.

              This quick data exploration using Novi Cloud outputs gives us a straightforward line of investigation. How much did the huge design impact the production?

              Investigating “outlier” performance with oil and gas Machine Learning Models

              One of the most common use cases of our ML models and Novi Cloud data outputs is investigating outlier performance. In truth, we don’t even like to talk about outlier production values, so long as there’s not a true issue with the data, like a transcription error. “Outlier” producers often have something to teach us, and too much hand-curation of data can open the door to bias.

              Each model we train learns what drives performance by intelligently splitting and grouping wells across the training variables. This is similar to what a reservoir engineer would do in an analog type curve process, just at computerized speed.

              Vista Well Model Forecasts

              Firstly for this model, we included proppant loading, fluid loading, stage length, and some publicly available geologic grids for training data. Secondly, all our model training is done in lateral, length normalized space. Thirdly, we predict per-foot production using per-foot completions variables, (we find this gives better model results–reach out if you’d like to learn more). Finally, after normalizing for lateral length, the Vista wells fall slightly off of their perch at the top:

              Histogram for peak-month oil and gas well production for Vaca Muerta wells.
              Histogram of peak-month production (average daily rate, normalized to 7500′ lateral), for Vaca Muerta wells. The Vista wells then fall slightly off the highest end of the distribution.

              Next, let’s look at the model forecasts for the Vista wells. During training, the model will make a forecast for every well. For each well on the pad, the model forecasts are broadly in line with what the wells have been producing. Our model expects these wells to be monsters, with over 200,000 bbl 6-month cumulative production. The most recent (peak) month does show higher than expected production–though only when viewed with the downtime corrected.

              Machine learning oil and gas drilling production: Cumulative for the Vista Pad 3 Wells.
              Cumulative oil production (bbl) for the Vista Pad 3 wells. Novi Forecast in orange, the raw actuals in black, and downtime-corrected actuals in purple.

              Flush Production Analysis

              Disentangling the role of flush production in driving these rates to stratospheric heights is tough off of public data. For instance, it’s lacking daily production and lacking pressure measurements. However, Vista’s Q2 investor deck shows significant flush production from their 1st and 2nd pads. Pad 2, which is closer geographically to Pad 3 (the record pad), also has similar completions designs. Surprisingly, It nearly returned to its peak rate after shut-in. So, it seems likely that flush production has played a role in driving these Vista wells to stratospheric rates.

              Well production after coronavirus shut-in using oil and gas machine learning applications
              Pad 1 and Pad 2 show flush production after shut-in. Source: Vista 2020 Q2 Earnings Webcast

              Assessing production drivers with SHAP values

              After model training, we turn the oil and gas machine learning model learnings into a powerful reconnaissance dataset with Shapley values. The Shapley value (or SHAP value) estimates how much each variable impacted the model forecast. Additionally, it shows how much it moved the forecast away from the average well’s production for that IP Day. SHAP values are expressed in units of production (bbl or mcf) and can be positive or negative. For example, they can be used for completions sensitivities, studying the changing impact of variables through time, or researching variable interaction.

              On an individual well basis, you can look at the SHAP values to see how the model came up with its forecast for that well. For the Vista wells, the geology and completions design both have a strong positive force on the prediction.

              Machine learning model showing SHAP values (colored bars), and baseline production expectation (gray) for Vista Pad 3, including the record setting wells (MDM-2061 and MDM-2063).
              Model forecast (black line), SHAP values (colored bars), and baseline production expectation (gray) for Vista Pad 3, including the record setting wells (MDM-2061 and MDM-2063). The average production in grey represents the baseline production expectation — it’s the Model Average(bbl/ft) * Lateral Length. The purple bar shows the contribution of the geology to the forecast — very strong! And the completions variables are in the shades of pink/red. Proppant loading shows a larger impact than fluid loading or stage length for these wells. All lines and bars are in cumulative production (barrels of oil).

              Looking at the above SHAP plots, it’s clear that the geology at the Pad 3 location is a main driver of the well performance. But, just how good are the rocks compared to the rest of the play?

              Studying the SHAP Values with oil and gas machine learning models

              We will use the SHAP values for the training geologic parameters to estimate the total rock quality. This is what we term geoSHAP. The plot below shows geoSHAP for every well drilled in the play. The bimodal distribution reflects the windows of the play. This is rock quality for producing oil (the chart would look similar for our Vaca Muerta gas model outputs). Vista’s rock quality at those well locations is great — though not as good as at their earlier pads.

              Histogram of geoSHAP at each oil and gas well location drilled in the Vaca Muerta.
              Histogram of geoSHAP at each well location drilled in the Vaca Muerta. GeoSHAP is calculated by summing the SHAP values of each geologic parameter for each stream at each IP day. While Vista’s record-setting wells are near the high-end of rock quality, the model thinks the rock quality at their previous locations was better.

              Of course, that leads to a question. If the rock quality at Vista’s earlier locations was better, why is Pad 3 the one setting records??

              The answer: Vista has been drilling longer laterals and trialing larger completions. Plus those pads did not see flush production coincide with their peak month, of course.

              Vista Pad Production Outputs in the machine learning model
              Average design parameters for Vista pads. Note that Pad 3 contained three wells with their V2 completion, and one well with their V3 completion

              Digging Deeper into the oil and gas machine learning model: analyzing the results of Vista’s V2 & V3 Completion Tests on total production and product mix

              Vista has now trialed three completions designs. Here are the details:

              Vista Pad Well Designs with fluid loading.

              Vista’s second pad outperformed their first pad despite having laterals that were 1,500′ shorter, on average. This is because Vista’s larger V2 completion design was trialed. For their third pad, they set records with the MDM-2061 and MDM-2063 wells, both long laterals with V2 designs. However, Vista snuck in another “larger job, shorter lateral” trial.

              This time they pushed proppant to a staggering 4,100 pounds per foot, and shortening stages to 130 ft. Early results look promising. The MDM-2064 produces about the same amount as the MDM-2062 (both Orgánico tests), despite a much shorter lateral. Will these results hold? Let’s take a look at the oil and gas machine learning SHAP values at two timesteps: periods of six months and three years.

              6-month and 3-Year Analyses

              6-Month and 3-year Pad production SHAP values
              Comparison of SHAP values
              SHAP Values for proppant and fluid loading for 6-month and 3-year cumulative production. The left panel of each represents the impact on the oil forecast, and the right on the gas forecast. These SHAP values suggest that the V3 oil advantage over the V2 completion will diminish through time, with product mix shifting towards gas.

              In conclusion, looking at the SHAP values across Vista’s designs for 6-month cum and 3-year cum, we can see the early advantage in production that the super-intense V3 design has over the V2 is expected to diminish through time, with the product mix shifting towards gas. Whether Vista will continue testing this large design remains to be seen. Certainly, the incremental uplift going from V1 to V2 looks lower than going from V2 to V3.

              Conclusions

              • To the model, Vista’s record-setting wells aren’t really a surprise. The majority of their performance can be explained by the combination of long laterals, great geology, and intense completions.
              • It does appear that flush production played a role. Production is slightly higher than expected, and Vista’s older pads showed a significant flush.
              • Vista’s V3 completions trial has increased oil production over V2, though that outperformance is expected to moderate through time as the well goes gassier.
              • This is an example of using machine learning in oil and gas exploration. All of this analysis was performed with Novi’s public data Vaca Muerta model. This is available to be licensed and deployed through our cloud-based oil and gas software. Simply reach out through the form below to learn more or schedule a demo.
              • Take a look at another ML use case studying well water analysis here.

              Filed Under: Well Completions, Well Designs, Machine Learning in Oil and Gas Blog

              Previous postMaking sense of it all: extracting actionable core-data from pXRF using PCA and K-means cluster analysis
              Next postNovi Releases Next Generation of AI-Driven Modeling Pipeline, Increasing the Accuracy and Efficiency of PDP Forecasting
              If you would like more information, please reach out using the form below.
              • This field is for validation purposes and should be left unchanged.

              Footer

              Connect

              • LinkedIn
              • YouTube

              oil and gas analysis by novi

              Contact

              1905 Aldrich Street, Suite 220
              Austin, Texas 78723

              intro@novilabs.com
              512.368.9042

              • Home
              • Products
              • Resources
              • About
              • ML in O&G Blog
              • Privacy Policy

              Copyright © 2021 Novi Labs
              All rights reserved.