An Interactive 5-Day Training Course
Digital Subsurface Workflows & Automation
Digital Workflows and Automation for Subsurface
Secure your spot now!
Duration
5 Days
Price
$ 3,500
Starting From
12 Jul 2027
Home Geology and Geoscience Digital Subsurface Workflows & Automation
Digital Subsurface Workflows & Automation
Have Questions ?
Digital Subsurface Workflows & Automation - GG-DIGI-PEA27
| Code | Date | Time | Duration | Location | Currency | Early Bird Fee Per Person |
|---|---|---|---|---|---|---|
| GG-DIGI-PEA27 | 12 - 16 Jul 2027 | 10 AM CST | 4 Hours Per Day |
Online |
USD |
3500 |
Need this for a group? We deliver the same course in-house — face-to-face at your location or online — tailored to your assets and team level. Contact info@peassociations.com
Boost your team's skills and your budget! Enjoy group discounts for collaborative learning. Send an inquiry to info@peassociations.com.
Digital Subsurface Workflows & Automation
This training covers the design and automation of digital subsurface workflows. It works through workflow identification and assessment, process mapping, automation technology selection, data pipeline construction, parameterisation and configuration, quality control within automated workflows, version control and reproducibility, scaling to many wells or scenarios, deployment and maintenance and the measurement of automation benefit.
Description
Automating a subsurface workflow is a design task before it is a coding task. The step most often skipped is deciding what the workflow actually does, which parts of it are judgement and which are mechanical, where the quality control sits and what happens when the input data is wrong. Automation applied to a poorly understood process produces wrong answers faster, which is worse than doing it by hand. Automation applied to a well-understood process transforms what a team can do.
This training covers the whole exercise. Workflow identification and assessment are established first, covering how to find the tasks worth automating and how to recognise those that are not. Process mapping follows, covering the documentation of a workflow in enough detail to automate it. Automation technology selection is then developed, covering the options from spreadsheet macros through scripting to platform workflows. Data pipeline construction follows. Parameterisation and configuration are then addressed, since a workflow with hard-coded values is not reusable. Quality control within automated workflows follows, covering the checks that must run automatically. Version control and reproducibility are then developed. Scaling to many wells or scenarios follows. Deployment and maintenance are addressed. The training closes with benefit measurement.
The task worth automating is repetitive, rule-based and currently done by hand. Reformatting log files, building the same set of plots for every well, extracting zone averages, checking data against ranges, generating a standard report and transferring results between applications are all in this category. Interpretation is not: deciding where a correlation goes, judging whether a facies scheme makes sense or choosing a model concept requires judgement and should not be automated. The useful distinction is whether a competent person would reach the same answer every time, and if so the computer should do it.
A workflow with hard-coded values is used once. A script with the file path, the cut-off values, the zone names and the well list written into the body of the code works for the case it was written for and requires editing for anything else, which means only its author can use it. Moving all of those into a configuration at the top, or into a separate file, converts it into a tool that the team can apply to other fields, other wells and other parameter sets without touching the logic.
Automated quality control is the part that makes automation safe. A manual workflow has a person looking at the data who notices that a log reads a nonsense value or that a well is missing its deviation survey. An automated workflow does not notice unless it is told to check. Every automated workflow therefore needs validation on its inputs, range and consistency checks on its intermediate results, and an explicit failure behaviour that stops and reports rather than producing a plausible wrong answer. This is more important than the processing code itself.
Finally, automation that nobody maintains stops working. Data formats change, software versions update, file locations move and the person who wrote the workflow changes role. An automated workflow that is used regularly needs an owner, documentation, a record of what it depends on and a plan for what happens when it breaks. Without that, a team ends up with a collection of scripts nobody dares to run, which is a worse position than having none.
By the end of this training, participants will be able to:
- Identify tasks suitable for automation and reject those that are not
- Map processes in sufficient detail to automate them
- Select automation technology appropriate to the task and team
- Build data pipelines from source to deliverable
- Parameterise workflows so they are reusable
- Embed quality control and validation in automated workflows
- Define failure behaviour and error reporting
- Apply version control and ensure reproducibility
- Scale workflows to many wells, scenarios or data sets
- Deploy, maintain and measure the benefit of automated workflows
The training works on real workflows that participants bring or are supplied. Each is mapped, assessed for automation suitability, and then built with parameterisation and quality control included. Workflows are deliberately fed bad input data to test their failure behaviour. Benefit is measured against the manual time the workflow replaces.
Organisations sending participants to this training will:
- Automate the repetitive work that consumes technical time
- Build workflows the whole team can use rather than one person
- Embed quality control in automated processing
- Improve reproducibility of technical results
- Maintain automated workflows rather than abandoning them
- Measure and demonstrate automation benefit
Participants will:
- Identify and assess automation opportunities
- Map and document workflows properly
- Build parameterised reusable workflows
- Embed validation and error handling
- Scale processing to large data sets
- Deliver automation that others use
- Geoscientists automating their own workflows
- Petrophysicists processing multi-well data
- Reservoir engineers handling repetitive analyses
- Data analysts supporting subsurface teams
- Digital and innovation staff in subsurface functions
- Subsurface team leaders planning automation
- Technical staff with recurring data tasks
Module 1 - Workflow Identification
- Finding tasks worth automating
- Repetitive and rule-based criteria
- Frequency and volume assessment
- Time currently spent measurement
- Error rate in manual execution
- Tasks requiring judgement
- Partial automation with human decision points
- Prioritising opportunities by value
- Effort estimation for automation
- Tasks not worth automating
- Building an automation backlog
- Starting small and building credibility
Module 2 - Process Mapping
- Documenting a workflow as it is performed
- Inputs and their sources
- Steps and their sequence
- Decision points and their rules
- Outputs and their consumers
- Exception handling in the manual process
- Undocumented knowledge in the process
- Interviewing the current practitioner
- Identifying variation between practitioners
- Standardising before automating
- Mapping notation and its use
- Validating the map with the users
Module 3 - Technology Selection
- Automation technology options
- Spreadsheet formulas and macros
- Scripting languages
- Application programming interfaces
- Software workflow builders
- Platform and cloud workflow services
- Scheduled and event driven execution
- Selection criteria for the task
- Team capability as a criterion
- Maintainability as a criterion
- Licensing and access constraints
- Avoiding over-engineering
Module 4 - Data Pipelines
- Pipeline concept and stages
- Data extraction from sources
- Database and file system access
- Application data extraction
- Transformation and standardisation
- Unit and format harmonisation
- Joining data from multiple sources
- Loading to destinations
- Intermediate storage and caching
- Incremental against full processing
- Pipeline dependencies and ordering
- Pipeline monitoring
Module 5 - Parameterisation
- Hard-coded values and their cost
- Separating configuration from logic
- Configuration file formats
- Parameter naming and documentation
- Default values and overrides
- Well lists and selection criteria
- Cut-offs and calculation parameters
- Path and location parameters
- Environment specific settings
- Validating configuration inputs
- Making workflows reusable across assets
- Configuration version control
Module 6 - Quality Control and Error Handling
- Input validation requirements
- Checking data completeness
- Range and physical plausibility checks
- Cross-data consistency checks
- Intermediate result validation
- Output sanity checks
- Comparison against known results
- Failure behaviour design
- Stopping against continuing on error
- Error messages and their usefulness
- Logging and audit trails
- Reporting quality issues to users
Module 7 - Reproducibility and Scaling
- Reproducibility requirements
- Version control for code and configuration
- Recording input data versions
- Environment and dependency management
- Documenting workflow provenance
- Scaling to many wells
- Batch processing design
- Parallel execution options
- Memory and performance management
- Handling partial failures in batches
- Progress reporting on long runs
- Scenario and ensemble processing
Module 8 - Deployment, Maintenance and Benefit
- Deployment to users
- User documentation requirements
- Training users on the workflow
- Ownership and support arrangements
- Dependency documentation
- Responding to format and software changes
- Testing after changes
- Retiring obsolete workflows
- Measuring time saved
- Measuring error reduction
- Reporting automation benefit
- Building an automation capability in a team
Upon successful completion of this training course, delegates will be awarded an official Certificate of Completion issued by the Petroleum Engineers Association (PEA), an ISO 9001:2015 certified training organization. The certificate carries 10 Credits and formally records the total learning hours completed.
Each certificate is signed by the Course Facilitator and the CEO of the Petroleum Engineers Association, and serves as verifiable proof of professional training that delegates can present to employers and professional bodies worldwide.
Frequently Asked Questions
All course bookings made through PEA are strictly non-refundable. By registering for a course, you acknowledge and accept that all fees are payable in full and are not subject to refund under any circumstances, including changes in personal or professional commitments or partial attendance.
PEA reserves the right to make reasonable adjustments to course content, trainers, or schedules where necessary, without entitling delegates to a refund. Comprehensive details of each course — including objectives, target audience, and content — are clearly outlined before enrolment, and it is the responsibility of the delegate to ensure the course's suitability prior to booking.
For any inquiries related to cancellations or bookings, please contact our support team, who will be happy to assist you.
