AlexNet training hyperparameters.
<div><p>Seismic impedance inversion is a geophysical technique that transforms seismic data into quantitative subsurface properties, primarily acoustic impedance. This process enables the identification of rock boundaries, hydrocarbon reservoirs, and lithological variations, thus support...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1851482651213430784 |
|---|---|
| author | Irshad Ali (5562320) |
| author2 | Wakeel Ahmad (17000850) Syed M. Adnan (22290842) |
| author2_role | author author |
| author_facet | Irshad Ali (5562320) Wakeel Ahmad (17000850) Syed M. Adnan (22290842) |
| author_role | author |
| dc.creator.none.fl_str_mv | Irshad Ali (5562320) Wakeel Ahmad (17000850) Syed M. Adnan (22290842) |
| dc.date.none.fl_str_mv | 2025-09-22T17:34:49Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0331952.t004 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/AlexNet_training_hyperparameters_/30181202 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Genetics Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified synthetic seismogram generation refined subsurface characterization reducing exploration risks quantitative subsurface properties primarily acoustic impedance highest r2 score geologically complex areas conventional cnn architectures calculating acoustic impedance transforms seismic data seismic data reconstruction real seismic data 052 ), along 0031 ), rmse reduced geological risk improve seismic resolution oversimplified subsurface models log data 0557 ), reduced effectiveness low resolution thereby establishing study addresses specifically lenet rock boundaries robust benchmark reflection coefficients process enables often resulting noise sensitivity models evaluated lowest mse lithological variations hydrocarbon reservoirs geophysical technique feature extraction 993 ). |
| dc.title.none.fl_str_mv | AlexNet training hyperparameters. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Seismic impedance inversion is a geophysical technique that transforms seismic data into quantitative subsurface properties, primarily acoustic impedance. This process enables the identification of rock boundaries, hydrocarbon reservoirs, and lithological variations, thus supporting informed drilling decisions and reducing exploration risks. However, conventional inversion methods face limitations such as noise sensitivity, low resolution, and reduced effectiveness in geologically complex areas, often resulting in oversimplified subsurface models. This study addresses these challenges by employing deep learning approaches, specifically LeNet, AlexNet, and conventional CNN architectures, to improve seismic resolution and synthetic seismogram generation. The methodology involves preprocessing seismic and well-log data, calculating acoustic impedance and reflection coefficients, and applying Continuous Wavelet Transform (CWT) for feature extraction. The models are trained using synthetic seismograms and validated against real seismic data. Among the models evaluated, AlexNet demonstrates superior performance in seismic data reconstruction, achieving the lowest MSE (0.0031), RMSE (0.0557), and MAE (0.052), along with the highest R2 score (0.993). The proposed technique demonstrates superior predictive accuracy, refined subsurface characterization, and reduced geological risk, thereby establishing a robust benchmark for advanced geophysical data analysis.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_a8788b7ade9f45c9bafd4f173e5ab1a7 |
| identifier_str_mv | 10.1371/journal.pone.0331952.t004 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30181202 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | AlexNet training hyperparameters.Irshad Ali (5562320)Wakeel Ahmad (17000850)Syed M. Adnan (22290842)GeneticsBiotechnologySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedsynthetic seismogram generationrefined subsurface characterizationreducing exploration risksquantitative subsurface propertiesprimarily acoustic impedancehighest r2 scoregeologically complex areasconventional cnn architecturescalculating acoustic impedancetransforms seismic dataseismic data reconstructionreal seismic data052 ), along0031 ), rmsereduced geological riskimprove seismic resolutionoversimplified subsurface modelslog data0557 ),reduced effectivenesslow resolutionthereby establishingstudy addressesspecifically lenetrock boundariesrobust benchmarkreflection coefficientsprocess enablesoften resultingnoise sensitivitymodels evaluatedlowest mselithological variationshydrocarbon reservoirsgeophysical techniquefeature extraction993 ).<div><p>Seismic impedance inversion is a geophysical technique that transforms seismic data into quantitative subsurface properties, primarily acoustic impedance. This process enables the identification of rock boundaries, hydrocarbon reservoirs, and lithological variations, thus supporting informed drilling decisions and reducing exploration risks. However, conventional inversion methods face limitations such as noise sensitivity, low resolution, and reduced effectiveness in geologically complex areas, often resulting in oversimplified subsurface models. This study addresses these challenges by employing deep learning approaches, specifically LeNet, AlexNet, and conventional CNN architectures, to improve seismic resolution and synthetic seismogram generation. The methodology involves preprocessing seismic and well-log data, calculating acoustic impedance and reflection coefficients, and applying Continuous Wavelet Transform (CWT) for feature extraction. The models are trained using synthetic seismograms and validated against real seismic data. Among the models evaluated, AlexNet demonstrates superior performance in seismic data reconstruction, achieving the lowest MSE (0.0031), RMSE (0.0557), and MAE (0.052), along with the highest R2 score (0.993). The proposed technique demonstrates superior predictive accuracy, refined subsurface characterization, and reduced geological risk, thereby establishing a robust benchmark for advanced geophysical data analysis.</p></div>2025-09-22T17:34:49ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0331952.t004https://figshare.com/articles/dataset/AlexNet_training_hyperparameters_/30181202CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301812022025-09-22T17:34:49Z |
| spellingShingle | AlexNet training hyperparameters. Irshad Ali (5562320) Genetics Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified synthetic seismogram generation refined subsurface characterization reducing exploration risks quantitative subsurface properties primarily acoustic impedance highest r2 score geologically complex areas conventional cnn architectures calculating acoustic impedance transforms seismic data seismic data reconstruction real seismic data 052 ), along 0031 ), rmse reduced geological risk improve seismic resolution oversimplified subsurface models log data 0557 ), reduced effectiveness low resolution thereby establishing study addresses specifically lenet rock boundaries robust benchmark reflection coefficients process enables often resulting noise sensitivity models evaluated lowest mse lithological variations hydrocarbon reservoirs geophysical technique feature extraction 993 ). |
| status_str | publishedVersion |
| title | AlexNet training hyperparameters. |
| title_full | AlexNet training hyperparameters. |
| title_fullStr | AlexNet training hyperparameters. |
| title_full_unstemmed | AlexNet training hyperparameters. |
| title_short | AlexNet training hyperparameters. |
| title_sort | AlexNet training hyperparameters. |
| topic | Genetics Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified synthetic seismogram generation refined subsurface characterization reducing exploration risks quantitative subsurface properties primarily acoustic impedance highest r2 score geologically complex areas conventional cnn architectures calculating acoustic impedance transforms seismic data seismic data reconstruction real seismic data 052 ), along 0031 ), rmse reduced geological risk improve seismic resolution oversimplified subsurface models log data 0557 ), reduced effectiveness low resolution thereby establishing study addresses specifically lenet rock boundaries robust benchmark reflection coefficients process enables often resulting noise sensitivity models evaluated lowest mse lithological variations hydrocarbon reservoirs geophysical technique feature extraction 993 ). |