Neural Network Well Log Synthesis Reducing Radioisotopic Source Usage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The use of radioisotopic sources in hydrocarbon reservoir exploration poses health risks to workers and significant regulatory and logistical challenges due to radiation exposure and supply shortages, necessitating a reduction in their usage while maintaining accurate neutron porosity and density logging.
Innovation Solution
Implementing a method that uses neural network ensembles to predict neutron porosity and density logs from non-radioisotopic source measurements, combining data from various logging tools like pulsed neutron capture tools and other cased hole logs, to generate synthetic logs that are more accurate and reduce reliance on radioisotopic sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radioisotopic sources are used for neutron porosity and density logging, then measurement accuracy is improved, but health risks to workers and regulatory challenges increase
Solution Approach 1:
The patent creates synthetic copies of radioisotopic source logs by using neural networks to generate artificial neutron porosity and density logs from non-radioisotopic measurements. These synthetic logs replicate the information content of traditional radioisotopic logs without requiring actual radioactive sources, thereby eliminating radiation exposure risks while maintaining measurement accuracy.
Solution Approach 2:
The patent replaces the physical radioisotopic source system with a computational system based on neural networks. Instead of using radioactive materials to generate neutron porosity and density data, the system uses machine learning models trained on existing data to compute synthetic logs from other well logging measurements, substituting a mechanical/physical system with an information-processing system.
2Measurement precision
If radioisotopic sources are used for neutron porosity logging, then measurement capability is improved, but regulatory compliance costs and logistical complexity increase
Solution Approach 1:
The patent generates synthetic copies of the desired neutron porosity logs through neural network processing of available well logging data. This eliminates the need to manage, transport, and store actual radioisotopic sources, thereby removing all associated regulatory compliance requirements and logistical complexities while preserving the measurement capability.
Solution Approach 2:
The patent extracts the essential information content from radioisotopic source measurements and separates it from the problematic physical source itself. By using neural networks to derive neutron porosity data from other logging measurements, the method extracts only the useful informational component while leaving behind the regulatory and logistical burden of handling radioactive materials.
3Measurement precision
If radioisotopic sources are used for density and neutron porosity logging, then data quality is improved, but supply availability decreases due to shortages and theft
Solution Approach 1:
The patent creates synthetic log data that replicates the quality and information content of radioisotopic source measurements without requiring physical sources. By training neural networks on existing high-quality radioisotopic logs and then generating synthetic logs from non-radioisotopic measurements, the system ensures continuous data availability independent of radioisotopic source supply constraints.
Solution Approach 2:
The patent enables the logging system to generate its own neutron porosity and density data internally through neural network processing of other available measurements. This self-service capability eliminates dependence on external radioisotopic sources, allowing continuous operation regardless of source availability, theft, or supply chain disruptions.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach provides accurate density and neutron porosity logs with reduced radioisotopic source usage, potentially surpassing the accuracy of traditional measurements and minimizing health and logistical risks, while also addressing supply shortages.
Implementation Method 1
a computer processes the input well logging data with a neural network ensemble to predict a set of output synthetic well logs
Data Source
AI summary
Logging systems and methods are disclosed to reduce usage of radioisotopic sources. Some embodiments comprise collecting at least one output log of a training well bore from measurements with a radioisotopic source; collecting at least one input log of the training well bore from measurements by a non-radioisotopic logging tool; training a neural network to predict the output log from the at least one input log; collecting at least one input log of a development well bore from measurements by the non-radioisotopic logging tool; and processing the at least one input log of the development well bore to synthesize at least one output log of the development well bore. The output logs may include formation density and neutron porosity logs.