View source for 17946346. Quantitative Prediction and Sorting of Carbon Underground Treatment and Sequestration of Potential Formations simplified abstract (Saudi Arabian Oil Company)

=Quantitative Prediction and Sorting of Carbon Underground Treatment and Sequestration of Potential Formations=


==Organization Name==

[[:Category:Saudi Arabian Oil Company|Saudi Arabian Oil Company]]


[[Category:Saudi Arabian Oil Company]]

==Inventor(s)==

[[:Category:Weichang Li of Katy TX (US)|Weichang Li of Katy TX (US)]][[Category:Weichang Li of Katy TX (US)]]

[[:Category:Katherine Leigh Hull of Houston TX (US)|Katherine Leigh Hull of Houston TX (US)]][[Category:Katherine Leigh Hull of Houston TX (US)]]

[[:Category:Younane N. Abousleiman of Norman OK (US)|Younane N. Abousleiman of Norman OK (US)]][[Category:Younane N. Abousleiman of Norman OK (US)]]

==Quantitative Prediction and Sorting of Carbon Underground Treatment and Sequestration of Potential Formations - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17946346 titled 'Quantitative Prediction and Sorting of Carbon Underground Treatment and Sequestration of Potential Formations

==Simplified Explanation==

The computer-implemented method described in the abstract focuses on predicting and sorting carbon underground treatment and sequestration potential using machine learning models on multi-modal and multiscale data sets. Here is a simplified explanation of the abstract:

* Preprocessing multiple data sets, including multi-modal and multiscale data sets.
* Predicting geological structural properties, chemical properties, and geological properties using trained machine learning models.
* Ranking the storage and treatment potential of a formation based on the predicted properties.

== Potential Applications ==
The technology described in this patent application could have potential applications in the following areas:
* Environmental monitoring and management
* Energy industry for carbon capture and storage projects
* Geological exploration and resource management

== Problems Solved ==
The technology addresses the following problems:
* Efficient prediction and sorting of carbon underground treatment and sequestration potential
* Utilizing multi-modal and multiscale data sets for accurate predictions
* Ranking formations based on storage and treatment potential

== Benefits ==
The benefits of this technology include:
* Improved decision-making in carbon sequestration projects
* Enhanced understanding of geological properties for resource management
* Optimization of underground carbon treatment processes

== Potential Commercial Applications ==
The technology could be commercially applied in:
* Energy companies for optimizing carbon capture and storage operations
* Environmental consulting firms for assessing carbon sequestration potential
* Research institutions for studying geological properties and carbon storage

== Possible Prior Art ==
One possible prior art related to this technology could be the use of machine learning models for predicting geological properties in the energy industry. Additionally, there may be prior art on the preprocessing of multi-modal and multiscale data sets for environmental monitoring purposes.

== Unanswered Questions ==
=== How does the method handle uncertainties in the predicted properties? ===
The article does not provide information on how uncertainties in the predicted geological and chemical properties are addressed in the method.

=== Are there any limitations to the types of formations that can be analyzed using this method? ===
The article does not mention any potential limitations in analyzing specific types of geological formations for carbon treatment and sequestration potential.


==Original Abstract Submitted==

A computer-implemented method for quantitative prediction and sorting of carbon underground treatment and sequestration is described. The method includes preprocessing multiple data sets, wherein the multiple datasets are multi-modal and multiscale data sets. The method also includes predicting geological structural properties, chemical properties, and geological properties by inputting the preprocessed multiple data sets into trained machine learning models. Additionally, the method includes ranking the storage and treatment potential of a formation based on the predicted geological structural properties, chemical properties, and geological properties.



[[Category:E21B47/12]]