United StatesEnergy and utilities2025 – ongoingSM Energy
Machine learning gas-lift optimization
SM Energy reported additional Midland Basin production from machine learning gas-lift optimization
Problem
SM Energy sought to increase production from existing Midland Basin wells by improving gas-lift injection rates. Engineers needed to determine which operating settings worked best.
Approach
The company used a model that learned from step-rate tests and suggested injection rates to try. Engineers connected compression to the machine learning model and used its output to inform well injection rates. Management reported incremental production from the operating wells.
Results
No published figures
Takeaway
The model learned from operating tests and informed subsequent injection settings. SM Energy did not quantify the additional production.
Categories
- Industry
- Energy and utilities
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Company's own claim
Sources
Source summaries
Management described a learning model used for gas-lift optimization in the Midland Basin. It reported additional production after connecting compression and well injection rates to the model, without disclosing a numerical gain.
Full details are in the original sources.