A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs
Accurately measuring wettability is of the utmost importance because it influences several reservoir parameters while also impacting reservoir potential, recovery, development, and management plan. As such, this study proposes a new formulated mathematical model based on the correlation between the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/2942 |
| _version_ | 1797447156034961408 |
|---|---|
| author | Daniel Asante Otchere Mohammed Abdalla Ayoub Mohammed Tarek Omar Arbi Ganat Raoof Gholami Zulkifli Merican Aljunid Merican |
| author_facet | Daniel Asante Otchere Mohammed Abdalla Ayoub Mohammed Tarek Omar Arbi Ganat Raoof Gholami Zulkifli Merican Aljunid Merican |
| author_sort | Daniel Asante Otchere |
| collection | DOAJ |
| description | Accurately measuring wettability is of the utmost importance because it influences several reservoir parameters while also impacting reservoir potential, recovery, development, and management plan. As such, this study proposes a new formulated mathematical model based on the correlation between the Amott-USBM wettability measurement and field NMR T<sub>2</sub>LM log. The exponential relationship based on the existence of immiscible fluids in the pore space had a correlation coefficient of 0.95. Earlier studies on laboratory core wettability measurements using <i>T<sub>2</sub></i> distribution as a function of increasing water saturation were modified to include T<sub>2</sub>LM field data. Based on the trends observed, water-wet and oil-wet conditions were qualitatively identified. Using the mean T<sub>2</sub>LM for the intervals of interest and the formulated mathematical formula, the various wetting conditions in existence were quantitatively measured. Results of this agreed with the various core wettability measurements used to develop the mathematical equation. The results expressed the validity of the mathematical equation to characterise wettability at the field scale. With the cost of running NMR logs not favourable, and hence not always run, a deep ensemble super learner was employed to establish a relationship between NMR T<sub>2</sub>LM and wireline logs. This model is based on the architecture of a deep learning model and the theoretical background of ensemble models due to their reported superiority. The super learner was developed using nine ensemble models as base learners. The performance of nine ensemble models was compared to the deep ensemble super learner. Based on the RMSE, R<sup>2</sup>, MAE, MAPD and MPD the deep ensemble super learner greatly outperformed the base learners. This indicates that the deep ensemble super learner can be used to predict NMR T<sub>2</sub>LM in the field. By applying the methodology and mathematical formula proposed in this study, the wettability of reservoirs can be accurately characterised as illustrated in the field deployment. |
| first_indexed | 2024-03-09T13:51:48Z |
| format | Article |
| id | doaj.art-2167c6b6d1344076b0ac7696a3830162 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:51:48Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2167c6b6d1344076b0ac7696a38301622023-11-30T20:49:18ZengMDPI AGApplied Sciences2076-34172022-03-01126294210.3390/app12062942A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well LogsDaniel Asante Otchere0Mohammed Abdalla Ayoub Mohammed1Tarek Omar Arbi Ganat2Raoof Gholami3Zulkifli Merican Aljunid Merican4Department of Petroleum Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak Darul Ridzuan, MalaysiaDepartment of Petroleum Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak Darul Ridzuan, MalaysiaDepartment of Petroleum and Chemical Engineering, Sultan Qaboos University, Muscat 123, OmanDepartment of Energy Resources, University of Stavanger, Kitty Kielland’s house Rennebergstien 30, 4021 Stavanger, NorwayDepartment of Fundamental & Applied Science, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak Darul Ridzuan, MalaysiaAccurately measuring wettability is of the utmost importance because it influences several reservoir parameters while also impacting reservoir potential, recovery, development, and management plan. As such, this study proposes a new formulated mathematical model based on the correlation between the Amott-USBM wettability measurement and field NMR T<sub>2</sub>LM log. The exponential relationship based on the existence of immiscible fluids in the pore space had a correlation coefficient of 0.95. Earlier studies on laboratory core wettability measurements using <i>T<sub>2</sub></i> distribution as a function of increasing water saturation were modified to include T<sub>2</sub>LM field data. Based on the trends observed, water-wet and oil-wet conditions were qualitatively identified. Using the mean T<sub>2</sub>LM for the intervals of interest and the formulated mathematical formula, the various wetting conditions in existence were quantitatively measured. Results of this agreed with the various core wettability measurements used to develop the mathematical equation. The results expressed the validity of the mathematical equation to characterise wettability at the field scale. With the cost of running NMR logs not favourable, and hence not always run, a deep ensemble super learner was employed to establish a relationship between NMR T<sub>2</sub>LM and wireline logs. This model is based on the architecture of a deep learning model and the theoretical background of ensemble models due to their reported superiority. The super learner was developed using nine ensemble models as base learners. The performance of nine ensemble models was compared to the deep ensemble super learner. Based on the RMSE, R<sup>2</sup>, MAE, MAPD and MPD the deep ensemble super learner greatly outperformed the base learners. This indicates that the deep ensemble super learner can be used to predict NMR T<sub>2</sub>LM in the field. By applying the methodology and mathematical formula proposed in this study, the wettability of reservoirs can be accurately characterised as illustrated in the field deployment.https://www.mdpi.com/2076-3417/12/6/2942surface wettabilityempirical formulaNMR characterisationartificial intelligencewater saturationdeep neural network |
| spellingShingle | Daniel Asante Otchere Mohammed Abdalla Ayoub Mohammed Tarek Omar Arbi Ganat Raoof Gholami Zulkifli Merican Aljunid Merican A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs Applied Sciences surface wettability empirical formula NMR characterisation artificial intelligence water saturation deep neural network |
| title | A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs |
| title_full | A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs |
| title_fullStr | A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs |
| title_full_unstemmed | A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs |
| title_short | A Novel Empirical and Deep Ensemble Super Learning Approach in Predicting Reservoir Wettability via Well Logs |
| title_sort | novel empirical and deep ensemble super learning approach in predicting reservoir wettability via well logs |
| topic | surface wettability empirical formula NMR characterisation artificial intelligence water saturation deep neural network |
| url | https://www.mdpi.com/2076-3417/12/6/2942 |
| work_keys_str_mv | AT danielasanteotchere anovelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT mohammedabdallaayoubmohammed anovelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT tarekomararbiganat anovelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT raoofgholami anovelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT zulkiflimericanaljunidmerican anovelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT danielasanteotchere novelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT mohammedabdallaayoubmohammed novelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT tarekomararbiganat novelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT raoofgholami novelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs AT zulkiflimericanaljunidmerican novelempiricalanddeepensemblesuperlearningapproachinpredictingreservoirwettabilityviawelllogs |