Geosteering Control Using ML Formation Top Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geosteering methods struggle to accurately control the directional wellbore within a pay zone, leading to potential gas or water breakthrough and reduced hydrocarbon production efficiency.
Innovation Solution
A method and system utilizing a trained machine learning model to predict the position of a formation top based on downhole data, enabling precise control of the drill bit operation to maintain the wellbore within the desired reservoir section.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional geosteering methods are used to control directional wellbore, then the control process is simpler, but the accuracy of keeping wellbore within pay zone deteriorates
Solution Approach 1:
The patent replaces traditional mechanical/geological interpretation methods with a machine learning-based prediction system. The ML model processes downhole sensor data to predict formation top positions, substituting manual geological analysis with automated intelligent algorithms, thereby improving positioning accuracy while managing system complexity through software-based solutions.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between downhole sensor data and geosteering control decisions. This ML intermediary processes raw sensor inputs and provides predicted formation top positions, enabling more accurate wellbore positioning without requiring direct complex control mechanisms.
2Manufacturing precision
If machine learning model is used to predict formation top position, then the directional control accuracy is improved, but the computational complexity increases
Solution Approach 1:
The patent applies preliminary action by training the machine learning model beforehand with historical well data and geological information. This pre-training phase prepares the model to make accurate predictions during actual drilling operations, reducing real-time computational complexity while maintaining high precision in wellbore placement.
Solution Approach 2:
The patent utilizes parameter changes by adjusting ML model inputs based on downhole conditions, sensor data quality, and drilling phase. The system dynamically modifies which parameters are fed to the model and how predictions are weighted, optimizing the balance between prediction accuracy and computational requirements during different stages of drilling.
Data Source
AI summary
A method may include receiving data acquired by a downhole tool of a tool string disposed at least in part in a borehole in a subsurface region; predicting a position of a formation top in the subsurface region using a trained machine learning model and at least a portion of the data; and controlling operation of the tool string based at least in part on the position of the formation top in the subsurface region.