# US 2026/0065206 A1 · Hybrid modeling system for oilfield performance optimization

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065206 A1
- Document ID: US20260065206A1
- Status: Published application
- Kind: A1
- Application number: 19/361,421
- Filed: 2025-10-17
- Published: 2026-03-05
- Earliest claimed: 2024-08-27
- Assignees: Enovate AI Corporation
- Applicants: Enovate AI Corporation
- Inventors: Jose Contreras; Meisong Yan; Rebecca Nye; Daniel Martinez; Camilo Mejia
- Web page: https://patentgrep.com/patent/US20260065206A1

## CPC

- G06Q 10/0639: Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G01N 33/2841: {Gas in oils, e.g. hydrogen in insulating oils}
- G01N 33/2847: {Water in oils}
- G06N 20/00: Machine learning
- G06Q 50/02: Agriculture; Fishing; Forestry; Mining
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system for enhancing oilfield performance analysis and optimization, comprising a data collection module configured to collect real-time Gas-Oil Ratio (GOR) and Water Cut (WC) data from oilfield sensors a physics-based modeling module configured to simulate a vertical pressure profile based on the collected GOR and WC data, and a machine learning module configured to analyze outputs from the physics-based modeling module and historical data, classify wells based on the analysis, establish baseline metrics for evaluating reservoir productivity based on the analysis and classification, generate a recommendation for well operations based on the analysis, classification and baseline metrics, and a user interface configured to display the recommendation.

## Claims

### Claim 1

A system for enhancing oilfield performance analysis and optimization, comprising:
a controller configured to collect real-time Gas-Oil Ratio (GOR) and Water Cut (WC) data from oilfield sensors;
a processing server comprising a physics-based model configured to simulate a vertical pressure profile based on the collected GOR and WC data, and a machine learning model configured to:
analyze outputs from the physics-based model based on the simulated vertical pressure profile and historical data from a plurality of wells, the analysis determining performance characteristics of each of the wells,
classify the wells into performance categories based on the performance characteristics of the analysis,
establish baseline metrics for evaluating well productivity based on the analysis and classification,
generate operational parameters based on the analysis, classification and baseline metrics; and
a user interface configured to display the operational parameters,
wherein the controller is further configured to control the well operations based on the operational parameters by implementing operational changes of the well.

### Claim 2 (depends on 1)

The system of claim 1, wherein the physics-based model is configured to simulate the vertical pressure profile by applying fluid dynamics and thermodynamics principles to the collected GOR and WC data.

### Claim 3 (depends on 1)

The system of claim 1, wherein the machine learning model comprises supervised learning algorithms for performance prediction and unsupervised learning algorithms for well classification and pattern recognition.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processing server is configured to detect anomalies in real-time GOR and WC data and generate alerts when deviations from expected behavior occur.

### Claim 5 (depends on 4)

The system of claim 4, wherein the processing server is configured to generate different levels of alarms based on a severity of detected anomalies.

### Claim 6 (depends on 1)

The system of claim 1, wherein the machine learning model is configured to generate the operational parameters for gas allocation optimization based on predicted post-lifting production for each well.

### Claim 7 (depends on 1)

The system of claim 1, wherein the processing server is configured to update the physics-based model and the machine learning model with new performance data collected after implementing the operational parameters for the well operations.

### Claim 8 (depends on 7)

The system of claim 7, wherein the processing server is configured to refine predictions and optimization strategies based on the updated physics-based model and the updated machine learning model.

### Claim 9 (depends on 1)

The system of claim 1, wherein the user interface is configured to display data visualization dashboards comprising histograms, scatter plots, and statistical summaries of well performance metrics.

### Claim 10 (depends on 9)

The system of claim 9, wherein the data visualization dashboards include cross-plots of oil rate versus gas-oil ratio and oil rate versus depth.

### Claim 11

A method for enhancing oilfield performance analysis and optimization, comprising:
collecting, by a controller, real-time Gas-Oil Ratio (GOR) and Water Cut (WC) data from oilfield sensors;
simulating, by a processing server, a vertical pressure profile based on the collected GOR and WC data using a physics-based model;
analyzing, by the processing server, outputs from the physics-based model based on the simulated vertical pressure profile and historical data using a machine learning model from a plurality of wells, the analysis determining performance characteristics of each of the wells;
classifying, by the processing server, the wells into performance categories based on the performance characteristics of the analysis;
establishing, by the processing server, baseline metrics for evaluating reservoir productivity based on the analysis and classification;
generating, by the processing server, operational parameters based on the analysis, classification and baseline metrics;
displaying the operational parameters on a user interface; and
controlling, by the controller, the well operations based on the operational parameters by implementing operational changes of the well.

### Claim 12 (depends on 11)

The method of claim 11, wherein simulating the vertical pressure profile comprises applying fluid dynamics and thermodynamics principles to the collected GOR and WC data.

### Claim 13 (depends on 11)

The method of claim 11, wherein the machine learning model comprises supervised learning algorithms for performance prediction and unsupervised learning algorithms for well classification and pattern recognition.

### Claim 14 (depends on 11)

The method of claim 11, comprising detecting anomalies in real-time GOR and WC data and generating alerts when deviations from expected behavior occur.

### Claim 15 (depends on 14)

The method of claim 14, comprising generating different levels of alarms based on a severity of detected anomalies.

### Claim 16 (depends on 11)

The method of claim 11, comprising generating the operational parameters for gas allocation optimization based on predicted post-lifting production for each well.

### Claim 17 (depends on 11)

The method of claim 11, comprising updating the physics-based model and the machine learning model with new performance data collected after implementing the operational parameters for the well operations.

### Claim 18 (depends on 17)

The method of claim 17, comprising refining predictions and optimization strategies based on the updated physics-based model and the updated machine learning model.

### Claim 19 (depends on 11)

The method of claim 11, comprising displaying data visualization dashboards comprising histograms, scatter plots, and statistical summaries of well performance metrics.

### Claim 20 (depends on 19)

The method of claim 19, wherein the data visualization dashboards include cross-plots of oil rate versus gas-oil ratio and oil rate versus depth.
