Finding a Trend Out of Chaos, A Machine Learning Approach for Well Spacing Optimization
- Zheren Ma (Quantum Reservoir Impact LLC) | Ehsan Davani (Quantum Reservoir Impact LLC) | Xiaodan Ma (Quantum Reservoir Impact LLC) | Hanna Lee (Quantum Reservoir Impact LLC) | Izzet Arslan (Quantum Reservoir Impact LLC) | Xiang Zhai (Quantum Reservoir Impact LLC) | Hamed Darabi (Quantum Reservoir Impact LLC) | David Castineira (Quantum Reservoir Impact LLC)
- Document ID
- Society of Petroleum Engineers
- SPE Annual Technical Conference and Exhibition, 26-29 October, Virtual
- Publication Date
- Document Type
- Conference Paper
- 2020. Society of Petroleum Engineers
- 5.6.9 Production Forecasting, 7.6.6 Artificial Intelligence, 5 Reservoir Desciption & Dynamics, 2.1 Completion Selection and Design, 5.6 Formation Evaluation & Management, 7 Management and Information, 7.6.1 Knowledge Management, 7.1.6 Field Development Optimization and Planning, 5.1.5 Geologic Modeling, 2.1 Completion Selection and Design, 7.1 Asset and Portfolio Management
- Midland Shale, Well Spacing, AI, Delaware, Machine Learning
- 115 in the last 30 days
- 125 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Data-driven decisions powered by machine-learning methods are increasing in popularity when it comes to optimizing field development in unconventional reservoirs. However, since well performance is impacted by many factors (e.g., geological characteristics, completion design, well design, etc.), the challenge is uncovering trends from all the noise.
By leveraging basin-level knowledge captured by big data sculpting, integrating private and public data with the use of uncertainty quantification, Augmented AI (a combination of expert-based knowledge and advanced AI frameworks) can provide quick and science-based answers for well spacing and fracking optimization and assess the full potential of an asset in unconventional reservoirs.
Augmented AI is artificial intelligence powered by engineering wisdom. The Augmented AI workflow starts with data sculpting, which includes information retrieval, data cleaning and standardization, and finally a smart, deep and systematic data QC. Feature engineering generates all the relevant parameters going into the machine learning model—over 50 features have been generated for this work and categorized. The final step is to perform model tuning and ensemble, evaluating the model robustness, generating model explanation and uncertainty quantification. Augmented AI adopts an iterative machine learning modeling approach. This approach combines new and innovative engineering and G&G workflows with data-driven models so that a deep understanding of the field behavior can be developed. Loops from feature selection to model tuning are used until good model results are achieved. The loop is automated using Bayesians optimization. All machine learning models have different strengths and weaknesses for prediction. Instead of manually determining which machine learning model to use, this approach uses an adaptive ensemble machine learning approach that is a stacking algorithm that combines multiple regression models via a second level machine learning model. It smartly aggregates opinions from different models with reduced variance and better robustness.
Augmented AI has been applied in unconventional reservoirs with great results. A case study in Midland Basin is presented in this paper. Domain-induced feature engineering was performed to obtain important features for predicting well performance, and initial feature selection was conducted using feature correlation analysis. A trusted and explainable ML model was built and enhanced with uncertainty quantification. After running several sensitivity analyses, Augmented AI optimized the attributes of interest, then vetted the outcome, generating a report and visualizing the results.
In addition, further information about the direct impact of well spacing on EUR was deconvoluted from other parameters using an ML explanation technique for Wolfcamp Formation in Permian Basin and subsequently well spacing optimization was presented for the case study in Midland Basin.
An innovative model was created using Augmented AI to optimize well spacing, leveraging big data sculpting, domain and physics-induced feature engineering, and machine learning. The learning was transferred from the basin model to the specific region of interest. Augmented AI provides efficient and systematic private data organization, an explainable machine learning model, robust production forecast with quantified uncertainty and well spacing and frac parameters optimization.
Augmented AI models are already built for major basins such as Midland and Delaware basins. The learning and knowledge of the model can be transferred to any region in a basin and can be refined using more accurate private data. This allows conclusions to be drawn even with a limited number of wells.
|File Size||1 MB||Number of Pages||17|
Amr, S., El Ashhab, H., El-Saban, M., Schietinger, P., Caile, C., Kaheel, A., and Rodriguez, L., 2018. A Large-Scale Study for a Multi-Basin Machine Learning Model Predicting Horizontal Well Production. Society of Petroleum Engineers. DOI: 10.2118/191538-MS
Arslan, I., Rajabi, F., and Ibrahima, F., 2019. Practical Automated Detection of Remaining Oil in Mature Fields Using Production and Geology Data. Society of Petroleum Engineers. doi:10.2118/195321-MS
Belyadi, H. and Smith, M., 2018. A Fast-Paced Workflow for Well Spacing and Completions Design Optimization in Unconventional Reservoirs. Society of Petroleum Engineers. DOI: 10.2118/191779-18ERM-MS
Castineira, D., Toronyi, R., and Saleri, N., 2018. Automated Identification of Optimal Deviated and Horizontal Well Targets. Society of Petroleum Engineers. DOI:10.2118/192279-MS
Castineira, D., Zhai, X., Darabi, H., Valle, M., Maqui, A., Shahvali, M., & Yunuskhojayev, A, 2018. Augmented AI Solutions for Heavy Oil Reservoirs: Innovative Workflows That Build from Smart Analytics, Machine Learning And Expert-Based Systems. Society of Petroleum Engineers. DOI:10.2118/193650-MS
Darabi, H., Zhai, X., Kianinejad, A., Ma, Z., Castineira, D., Suicmez, V.S. and Toronyi, R., 2020, January. Augmented AI Framework for Well Performance Prediction and Opportunity Identification in Unconventional Reservoirs. In International Petroleum Technology Conference. International Petroleum Technology Conference. DOI: 10.2523/IPTC-20099-MS
Defeu, C., Garcia Ferrer, G., Ejofodomi, E., Shan, D., and Alimahomed, F., 2018. Time Dependent Depletion of Parent Well and Impact on Well Spacing in the Wolfcamp Delaware Basin. Society of Petroleum Engineers. DOI: 10.2118/191799-MS
Deng, L., Davani, E., Darabi, H., 2018. Rapid and Comprehensive Artificial Lift Systems Performance Analysis Through Data Analytics, Diagnostics and Solution Evaluation. Society of Petroleum Engineers. DOI: 10.2118/192460-MS
Deng, L., Olalotiti-Lawal, F., Davani, E., 2019. Hypervolume-Based Multiobjective Optimization for Gas Lift Systems. Society of Petroleum Engineers. DOI: 10.2118/195208-MS
Feder, J., 2019. Machine Learning Optimizes Duvernay Shale-Well Performance. Society of Petroleum Engineers. DOI: 10.2118/0519-0065-JPT
Ganpule, S., Waters G., and Al-Jalal, Z., 2015. Impact of Stimulation Net to Gross Ratio on Hydraulic Fracture Deliverability in Unconventional Resources. Society of Petroleum Engineers. DOI: 10.2118/173998-MS
Gurina, Ekaterina, , 2019. Application of Machine Learning to accidents detection at directional drilling, o Journal of Petroleum Science and Engineering. DOI:10.1016/j.petrol.2019.106519
Izadi G, Junca JP, Cade R, Rowan T., 2014. Production Performance in Marcellus Shale: Multidisciplinary Study of Hydraulic Fracturing. Society of Petroleum Engineers. DOI: 10.2118/171817-MS
Lafollette R., Izadi G., and Zhong M., 2014. Application of Multivariate Statistical Modeling and Geographic Information Systems Pattern-Recognition Analysis to Production Results in the Eagle Ford Formation of South Texas. Society of Petroleum Engineers. DOI: 10.2118/168628-MS.
Lalehrokh, F. and Bouma J., 2014. Well Spacing Optimization in Eagle Ford. Society of Petroleum Engineers. DOI: 10.2118/171640-MS
Lundberg, S.M., Erion, G., Chen, H., DeGrave, A., Prutkin, J.M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N. and Lee, S.I., 2020. From local explanations to global understanding with explainable AI for trees. Nature machine intelligence, 2(1), pp.2522-5839. DOI: 10.1038/s42256-019-0138-9
Luo, G., Tian, Y., Bychina, M. and Ehlig-Economides, C., 2018. Production Optimization Using Machine Learning in Bakken Shale. Unconventional Resources Technology Conference. DOI: 10.15530/URTEC-2018-2902505
Luo, G., Tian, Y., Sharma, A., and Ehlig-Economides, C., 2019. Eagle Ford Well Insights Using Data-Driven Approaches. International Petroleum Technology Conference. DOI: 10.2523/IPTC-19260-MS
Ma, Z., Karimi, A., Lee, H., 2018. Applications of Machine Learning and Data Mining in SpeedWise® Drilling Analytics: A Case Study. Society of Petroleum Engineers. DOI: 10.2118/193224-MS
Maucec, M., and Garni, S., 2019. Application of Automated Machine Learning for Multi-Variate Prediction of Well Production. Society of Petroleum Engineers. DOI:10.2118/195022-MS
Maucec, M., Singh, A., Bhattacharya, S., Yarus, J., Fulton, D., and Orth, J., 2015. Multivariate Analysis and Data Mining of Well-Stimulation Data by Use of Classification-and-Regression Tree with Enhanced Interpretation and Prediction Capabilities. Society of Petroleum Engineers. DOI:10.2118/166472-PA
Pan, Y., Deng, L. and Lee, J., 2020. A novel data-driven pressure/rate deconvolution algorithm to enhance production data analysis in unconventional reservoirs. Journal of Petroleum Science and Engineering, p.107332. DOI: 10.1016/j.petrol.2020.107332
Pankaj, P., Shukla, P., Kavousi, P., and Carr, T., 2018. Hydraulic Fracture and Reservoir Characterization for Determining Optimal Well Spacing in the Marcellus Shale. Society of Petroleum Engineers. DOI: 10.2118/191802-MS
Sen, V., Min, K., Ji, L., and Sullivan, R., 2018. Completions and Well Spacing Optimization by Dynamic SRV Modeling for Multi-Stage Hydraulic Fracturing. Society of Petroleum Engineers. DOI:10.2118/191571-MS
Shahkarami, A., Wang, G., and Belyadi, H., 2016. Horizontal Well Spacing and Hydraulic Fracturing Design Optimization: A Case Study on Utica-Point Pleasant Shale Play. Unconventional Resources Technology Conference (URTeC). DOI: 10.15530-urtec-2016-2459851
Shirangi, M.G., Oruganti, Y., Wilson T., and Furlong E., Winter E., Martin, J. and Yancy R., 2019. Prescriptive Analytics for Completion Optimization in Unconventional Resources. Society of Petroleum Engineers. DOI:10.2118/195311-MS
Texas Department of Transportation (TxDOT), 2019. Texas County Boundaries. http://gis-txdot.opendata.arcgis.com/datasets/texas-county-boundaries/, accessed on September 6, 2019.
U.S. Energy Information Administration, the U.S Department of Energy. Permian Basin, Wolfcamp Shale Play, October 2018 Update. www.eia.gov/maps/pdf/, accessed on April 10, 2020.
Walser, D. and Siddiqui S., 2016. Quantifying and Mitigating the Impact of Asymmetric Induced Hydraulic Fracturing from Horizontal Development Wellbores. Society of Petroleum Engineers. DOI:10.2118/181656-MS
Xu, T., Zheng, W., Baihly, J., Dwivedi, P., Shan, D., Utech, R., and Miller, G., 2019. Permian Basin Production Performance Comparison Over Time and the Parent-Child Well Study. Society of Petroleum Engineers. DOI: 10.2118/194310-MS
Yadav, H. and Motealleh, S., 2017. Improving Quantitative Analysis of Frac-Hits and Refracs in Unconventional Plays Using RTA. Society of Petroleum Engineers. DOI: 10.2118/184812-MS