Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan
Accurate prediction of reservoir properties through linear transformation and regression methods are successful in limited cases but are often geologically unrealistic and have no concrete theoretical foundation. Artificial Neural Network’s (ANN’s) have emerged as an effective tool for deriving nonl...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2024.1516420/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539900115681280 |
|---|---|
| author | Furqan Aftab Furqan Aftab Furqan Aftab Furqan Aftab Mohammad Zafar Muhammad Iqbal Hajana John H. Shaw |
| author_facet | Furqan Aftab Furqan Aftab Furqan Aftab Furqan Aftab Mohammad Zafar Muhammad Iqbal Hajana John H. Shaw |
| author_sort | Furqan Aftab |
| collection | DOAJ |
| description | Accurate prediction of reservoir properties through linear transformation and regression methods are successful in limited cases but are often geologically unrealistic and have no concrete theoretical foundation. Artificial Neural Network’s (ANN’s) have emerged as an effective tool for deriving nonlinear mathematical relationships between seismic attributes and well logs that are theoretically plausible and may prove geologically realistic. In this paper, we devise a methodology to integrate rock physics analysis, seismic inversion, multi-attribute transformation, and Feedforward Neural Network (FNN) modeling for accurate inter-well reservoir property predictions. We test this methodology on well logs and seismic data from the Cretaceous sandstones of the Sembar Formation, Southern Indus Basin, Pakistan. Viable productive gas zones are identified through rock physics and Model Based Inversion (MBI) analyses. Five volume-based seismic attributes are sequentially calculated through forward stepwise regression and cross-validated for inter-well porosity prediction. When a Probabilistic Neural Network (PNN) is trained in a non-linear mode integrated with multi-attribute transformation, correlation (r2) is improved from 72% to 88% between seismic attributes and porosity derived from logs. The PNN-derived porosity distribution is geologically more realistic than linear transformation and regression methods, supporting our model’s validity. We suggest that it is theoretically possible for the ANN to make predictions about any attribute of the reservoir via bridging target logs and seismic data within a short computation time. |
| format | Article |
| id | doaj-art-64c77e84ac72417fa2623c5e9e6b7571 |
| institution | Kabale University |
| issn | 2296-6463 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj-art-64c77e84ac72417fa2623c5e9e6b75712025-02-05T07:33:00ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-02-011210.3389/feart.2024.15164201516420Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast PakistanFurqan Aftab0Furqan Aftab1Furqan Aftab2Furqan Aftab3Mohammad Zafar4Muhammad Iqbal Hajana5John H. Shaw6Department of Earth and Environmental Sciences, Bahria School of Engineering and Applied Sciences, Bahria University, Islamabad, PakistanDepartment of Earth and Planetary Sciences, Harvard University, Cambridge, MA, United StatesDepartment of Geology, University of Vienna, Vienna, AustriaDepartment of Earth and Climate Sciences, Tufts University, Medford, United StatesDepartment of Earth and Environmental Sciences, Bahria School of Engineering and Applied Sciences, Bahria University, Islamabad, PakistanDepartment of Earth and Environmental Sciences, Bahria School of Engineering and Applied Sciences, Bahria University, Islamabad, PakistanDepartment of Earth and Planetary Sciences, Harvard University, Cambridge, MA, United StatesAccurate prediction of reservoir properties through linear transformation and regression methods are successful in limited cases but are often geologically unrealistic and have no concrete theoretical foundation. Artificial Neural Network’s (ANN’s) have emerged as an effective tool for deriving nonlinear mathematical relationships between seismic attributes and well logs that are theoretically plausible and may prove geologically realistic. In this paper, we devise a methodology to integrate rock physics analysis, seismic inversion, multi-attribute transformation, and Feedforward Neural Network (FNN) modeling for accurate inter-well reservoir property predictions. We test this methodology on well logs and seismic data from the Cretaceous sandstones of the Sembar Formation, Southern Indus Basin, Pakistan. Viable productive gas zones are identified through rock physics and Model Based Inversion (MBI) analyses. Five volume-based seismic attributes are sequentially calculated through forward stepwise regression and cross-validated for inter-well porosity prediction. When a Probabilistic Neural Network (PNN) is trained in a non-linear mode integrated with multi-attribute transformation, correlation (r2) is improved from 72% to 88% between seismic attributes and porosity derived from logs. The PNN-derived porosity distribution is geologically more realistic than linear transformation and regression methods, supporting our model’s validity. We suggest that it is theoretically possible for the ANN to make predictions about any attribute of the reservoir via bridging target logs and seismic data within a short computation time.https://www.frontiersin.org/articles/10.3389/feart.2024.1516420/fullartificial neural networkfeedforward neural networkprobabilistic neural networkmulti-attribute transformationvolume-based seismic attributesSembar Formation |
| spellingShingle | Furqan Aftab Furqan Aftab Furqan Aftab Furqan Aftab Mohammad Zafar Muhammad Iqbal Hajana John H. Shaw Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan Frontiers in Earth Science artificial neural network feedforward neural network probabilistic neural network multi-attribute transformation volume-based seismic attributes Sembar Formation |
| title | Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan |
| title_full | Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan |
| title_fullStr | Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan |
| title_full_unstemmed | Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan |
| title_short | Correlation of artificial neural network and multi-attribute transformation: a test case to predict the effective porosity of Cretaceous sandstones of the Sembar Formation, southeast Pakistan |
| title_sort | correlation of artificial neural network and multi attribute transformation a test case to predict the effective porosity of cretaceous sandstones of the sembar formation southeast pakistan |
| topic | artificial neural network feedforward neural network probabilistic neural network multi-attribute transformation volume-based seismic attributes Sembar Formation |
| url | https://www.frontiersin.org/articles/10.3389/feart.2024.1516420/full |
| work_keys_str_mv | AT furqanaftab correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT furqanaftab correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT furqanaftab correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT furqanaftab correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT mohammadzafar correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT muhammadiqbalhajana correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan AT johnhshaw correlationofartificialneuralnetworkandmultiattributetransformationatestcasetopredicttheeffectiveporosityofcretaceoussandstonesofthesembarformationsoutheastpakistan |