Abstract
Mechanical brittleness index (\(B{I}_{mech}\)) of the rock is a necessary parameter for selecting appropriate drilling bits and proper depth intervals for hydraulic fracturing. The \(B{I}_{mech}\) measurement is possible through continuous coring followed by laboratory tests, which are extremely cost- and time-intensive. Although petrophysical logs provide us with some continuous pieces of information, the complex nonlinear relationship between the logs and the \(B{I}_{mech}\) calls for implementing intelligent approaches before one can predict \(B{I}_{mech}\) from the petrophysical logs. Therefore, the present research is an attempt to develop \(B{I}_{mech}\) prediction models using least-squares support-vector machine (LSSVM) and multilayer perceptron (MLP) neural network (NN) as well as their hybrid forms with cuckoo optimization algorithm (COA), particle swarm optimization (PSO), and genetic algorithm (GA) on data from wells penetrating Maroon Oilfield. For this purpose, we began by approximating the \(B{I}_{mech}\) from the Poisson’s ratio and static Young’s modulus – with the later obtained from laboratory test results-calibrated petrophysical logs. Next, the entire set of available data was split into two subsets, namely modeling and validation subsets. Application of the second version of the nondominated sorting genetic algorithm (NSGA-II) combined with the MLP-NN for feature selection showed that, among the eight features considered, five made the best set for developing estimator models, including P- and S-wave velocities, depth, density (RHOB), and gamma-ray (GR) readings. Accordingly, intelligent algorithms were developed by means of these five features on the basis of the modeling data. Results of the training and testing phases showed that the hybrid algorithms were more accurate than the simple forms of either MLP or LSSVM. Among the hybrid algorithms, the highest levels of accuracy and generalizability were achieved with the LSSVM-COA. Application of the developed models on the validation data and a well in the Azadegan oil field further confirmed the high accuracy and generalizability of this model for predicting the \(B{I}_{mech}\). Therefore, at a high level of confidence, the proposed model can be recommended for predicting \(B{I}_{mech}\) at wells penetrating similar formations.
Similar content being viewed by others
Data availability
The dataset used in the current study is not publicly available due to the data confidentiality concerns, imposed by the providing company.
References
Ahmadi M, Chen Z (2020) Machine learning-based models for predicting permeability impairment due to scale deposition. J Pet Explor Prod Technol 10:2873–2884
Altindag R (2002) The evaluation of rock brittleness concept on rotary blast hole drills. J South African Inst Min Metall 102:61–66
Altindag R (2003) Correlation of specific energy with rock brittleness concepts on rock cutting. J South African Inst Min Metall 103:163–171
Altindag R (2010) Assessment of some brittleness indexes in rock-drilling efficiency. Rock Mech Rock Eng 43:361–370
Alzahabi A, Al Qahtani G, Soliman MY et al (2015) Fracturability index is a mineralogical index: A new approach for fracturing decision. In: Society of Petroleum Engineers - Saudi Arabia Section Annual Technical Symposium and Exhibition. Paper Number: SPE-178033-MS
Nait Amar M, Jahanbani Ghahfarokhi A, Ng CSW, Zeraibi N (2021) Optimization of WAG in real geological field using rigorous soft computing techniques and nature-inspired algorithms. J Pet Sci Eng 206:109038. https://doi.org/10.1016/j.petrol.2021.109038
Anemangely M, Ramezanzadeh A, Tokhmechi B, Molaghab A, Mohammadian A (2018a) Development of a new rock drillability index for oil and gas reservoir rocks using punch penetration test. J Pet Sci Eng 166:131–145
Anemangely M, Ramezanzadeh A, Tokhmechi B, Molaghab A, Mohammadian A (2018b) Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network. J Geophys Eng 15:1146–1159
Anemangely M, Ramezanzadeh A, Amiri H, Hoseinpour SA (2019a) Machine learning technique for the prediction of shear wave velocity using petrophysical logs. J Pet Sci Eng 174:306–327
Anemangely M, Ramezanzadeh A, Mohammadi Behboud M (2019b) Geomechanical parameter estimation from mechanical specific energy using artificial intelligence. J Pet Sci Eng 175:407–429
Anemangely M, Ramezanzadeh A, Tokhmechi B (2017) Safe Mud weight window determination using log based methodology. In: 79th EAGE Conference and Exhibition 2017. European Association of Geoscientists & Engineers, p 1–5
Blindheim OT, Bruland A (1998) Norwegian TBM tunnelling: 30 years of experience with TBMs in Norwegian tunnelling. Norwegian Soil and Rock Engineering Association:21–27
Brotons V, Tomás R, Ivorra S, Grediaga A (2014) Relationship between static and dynamic elastic modulus of calcarenite heated at different temperatures: the San Julián’s stone. Bull Eng Geol Environ 73:791–799
Brotons V, Tomás R, Ivorra S, Grediaga A, Martínez-Martínez J, Benavente D, Gómez-Heras M (2016) Improved correlation between the static and dynamic elastic modulus of different types of rocks. Mater Struct 49:3021–3037
Chen J, Xiao XM (2013) Mineral composition and brittleness of three sets of Paleozoic organic-rich shales in China South area. Meitan Xuebao/J China Coal Soc 38:822–826
Davoodi S, Mehrad M, Wood DA, Ghorbani H, Rukavishnikov VS (2023a) Hybridized machine-learning for prompt prediction of rheology and filtration properties of water-based drilling fluids. Eng Appl Artif Intell 123:106459
Davoodi S, Mehrad M, Wood DA, Rukavishnikov VS, Bajolvand M (2023b) Predicting uniaxial compressive strength from drilling variables aided by hybrid machine learning. Int J Rock Mech Min Sci 170:105546
Davoodi S, Thanh HV, Wood DA, Mehrad M, Rukavishnikov VS (2023c) Combined machine-learning and optimization models for predicting carbon dioxide trapping indexes in deep geological formations. Appl Soft Comput 143:110408
de Moura Meneses AA, Machado MD, Schirru R (2009) Particle swarm optimization applied to the nuclear reload problem of a pressurized water reactor. Prog Nucl Energy 51:319–326
Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6:182–197
Dursun AE, Gokay MK (2016) Cuttability assessment of selected rocks through different brittleness values. Rock Mech Rock Eng 49:1173–1190
Fjaer E, Holt RM, Horsrud P, Raaen AM, Risnes R (1992) Petroleum related rock mechanics, Petroleum related rock mechanics. Elsevier
Glorioso JC, Rattia A (2012) Unconventional reservoirs: Basic petrophysical concepts for shale gas. In: Society of Petroleum Engineers - SPE/EAGE European Unconventional Resources Conference and Exhibition 2012. European Association of Geoscientists & Engineers, pp 748–785. https://doi.org/10.2118/153004-ms
Goktan RM, Yilmaz NG (2005) A new methodology for the analysis of the relationship between rock brittleness index and drag pick cutting efficiency. J South African Inst Min Metall 105:727–732
Gong QM, Zhao J (2007) Influence of rock brittleness on TBM penetration rate in Singapore granite. Tunn Undergr Space Technol 22:317–324
Guo T, Zhang S, Ge H, Wang X, Lei X, Xiao B (2015) A new method for evaluation of fracture network formation capacity of rock. Fuel 140:778–787
Guyon I, Gunn S, Nikravesh M, Zadeh LA (2006) Feature extraction foundations and applications Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-35488-8
Harris NB, Miskimins JL, Mnich CA (2011) Mechanical anisotropy in the Woodford Shale, Permian Basin: Origin, magnitude, and scale. Lead Edge (Tulsa, OK) 30:284–291
Heidari AA, Faris H, Aljarah I, Mirjalili S (2019) An efficient hybrid multilayer perceptron neural network with grasshopper optimization. Soft Comput 23:7941–7958
Hemmati-Sarapardeh A, Amar MN, Soltanian MR, Dai Z, Zhang X (2020) Modeling CO2 Solubility in Water at High Pressure and Temperature Conditions. Energy Fuels 34:4761–4776
Hu Y, Perdomo MEG, Wu K et al (2015) A novel model of brittleness index for shale gas reservoirs: Confining pressure effect. In: Society of Petroleum Engineers - SPE Asia Pacific Unconventional Resources Conference and Exhibition. OnePetro. https://doi.org/10.2118/176886-MS
Jafarizadeh F, Larki B, Kazemi B et al (2022) A new robust predictive model for lost circulation rate using convolutional neural network: A case study from Marun Oilfield. Petroleum. https://doi.org/10.1016/j.petlm.2022.04.002
Jarvie DM, Hill RJ, Ruble TE, Pollastro RM (2007) Unconventional shale-gas systems: The Mississippian Barnett Shale of north-central Texas as one model for thermogenic shale-gas assessment. Am Assoc Pet Geol Bull 91:475–499
Jin X, Shah S, Truax J, Roegiers JC (2014a) A practical petrophysical approach for brittleness prediction from porosity and sonic logging in shale reservoirs. In: Proceedings - SPE Annual Technical Conference and Exhibition. OnePetro, pp 5199–5216. https://doi.org/10.2118/170972-ms
Jin X, Shah SN, Roegiers JC, Zhang B (2014b) Fracability evaluation in shale reservoirs - An integrated petrophysics and geomechanics approach. In: Society of Petroleum Engineers - SPE Hydraulic Fracturing Technology Conference 2014. SPE, pp 153–166. https://doi.org/10.2118/168589-ms
Kahraman S (2002) Correlation of TBM and drilling machine performances with rock brittleness. Eng Geol 65:269–283
Kahraman S, Bilgin N, Feridunoglu C (2003) Dominant rock properties affecting the penetration rate of percussive drills. Int J Rock Mech Min Sci 40:711–723
Kaunda RB, Asbury B (2016) Prediction of rock brittleness using nondestructive methods for hard rock tunneling. J Rock Mech Geotech Eng 8(4):533–540
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks, IEEE, pp 1942–1948
Kim T, Hwang S, Jang S (2017) Petrophysical approach for S-wave velocity prediction based on brittleness index and total organic carbon of shale gas reservoir: A case study from Horn River Basin. Canada J Appl Geophys 136:513–520
Lai J, Wang G, Huang L, Li W, Ran Y, Wang D, Zhou Z, Chen J (2015) Brittleness index estimation in a tight shaly sandstone reservoir using well logs. J Nat Gas Sci Eng 27:1536–1545
Liu QS, Liu JP, Shi K, Pan YC, Huang X, Liu XW, Wei L (2016) Evaluation of rock brittleness indexes on rock fragmentation efficiency by disc cutter. Chin J Rock Mech Eng 35:498–510
Mahdaviara M, Larestani A, Amar MN, Hemmati-Sarapardeh A (2022) On the evaluation of permeability of heterogeneous carbonate reservoirs using rigorous data-driven techniques. J Pet Sci Eng 208:109685
Matinkia M, Sheykhinasab A, Shojaei S, VojdaniTazehKand A, Elmi A, Bajolvand M, Mehrad M (2022b) Developing a New Model for Drilling Rate of Penetration Prediction Using Convolutional Neural Network. Arab J Sci Eng 47:11953–11985
Matinkia M, Hashami R, Mehrad M et al (2022) Prediction of permeability from well logs using a new hybrid machine learning algorithm. Petroleum 9:108–123. https://doi.org/10.1016/j.petlm.2022.03.003
Mehrad M, Bajolvand M, Ramezanzadeh A, Neycharan JG (2020) Developing a new rigorous drilling rate prediction model using a machine learning technique. J Pet Sci Eng 192:107338
Mehrad M, Ramezanzadeh A, Bajolvand M, Reza Hajsaeedi M (2022) Estimating shear wave velocity in carbonate reservoirs from petrophysical logs using intelligent algorithms. J Pet Sci Eng 212:110254
Mehrjoo H, Riazi M, Nait Amar M, Hemmati-Sarapardeh A (2020) Modeling interfacial tension of methane-brine systems at high pressure and high salinity conditions. J Taiwan Inst Chem Eng 114:125–141
Meng F, Zhou H, Zhang C, Xu R, Lu J (2015) Evaluation methodology of brittleness of rock based on post-peak stress–strain curves. Rock Mech Rock Eng 48:1787–1805
Meng F, LNY W, Zhou H (2021) Rock brittleness indices and their applications to different fields of rock engineering: A review. J Rock Mech Geotech Eng 13:221–247. https://doi.org/10.1016/j.jrmge.2020.06.008
Mews KS, Alhubail MM, Barati RG (2019) A review of brittleness index correlations for unconventional tight and ultra-tight reservoirs. Geosciences 9:319
Mohamadian N, Ghorbani H, Wood DA, Mehrad M, Davoodi S, Rashidi S, Soleimanian A, Shahvand AK (2021) A geomechanical approach to casing collapse prediction in oil and gas wells aided by machine learning. J Pet Sci Eng 196:107811
Mustafa A, Tariq Z, Abdulraheem A, Mahmoud M, Kalam S, Khan RA (2022) Shale brittleness prediction using machine learning—A Middle East basin case study. Am Assoc Pet Geol Bull 106:2275–2296
Nait Amar M, Ouaer H, Abdelfetah Ghriga M (2022) Robust smart schemes for modeling carbon dioxide uptake in metal − organic frameworks. Fuel 311:122545
Najibi AR, Ghafoori M, Lashkaripour GR, Asef MR (2015) Empirical relations between strength and static and dynamic elastic properties of Asmari and Sarvak limestones, two main oil reservoirs in Iran. J Pet Sci Eng 126:78–82
Ng CSW, Djema H, Nait Amar M, Jahanbani Ghahfarokhi A (2022) Modeling interfacial tension of the hydrogen-brine system using robust machine learning techniques: Implication for underground hydrogen storage. Int J Hydrogen Energy 47:39595–39605
Ore T, Gao D (2023) Prediction of reservoir brittleness from geophysical logs using machine learning algorithms. Comput Geosci 171:105266
Osman H, Ghafari M, Nierstrasz O (2018) The impact of feature selection on predicting the number of bugs. arXiv Prepr arXiv180704486. https://doi.org/10.48550/arXiv.1807.04486
Özkaraca O (2018) A review on usage of optimization methods in geothermal power generation. Mugla J Sci Technol 4:130–136
Rajabi M, Hazbeh O, Davoodi S, Wood DA, Tehrani PS, Ghorbani H, Mehrad M, Mohamadian N, Rukavishnikov VS, Radwan AE (2022) Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms. J Pet Explor Prod Technol 2022:1–24
Rajabioun R (2011) Cuckoo optimization algorithm. Appl Soft Comput 11:5508–5518
Rickman R, Mullen M, Petre E et al (2008) A practical use of shale petrophysics for stimulation design optimization: All shale plays are not clones of the Barnett Shale. Proceedings - SPE Annual Technical Conference and Exhibition. Society of Petroleum Engineers, pp 840–850. https://doi.org/10.2118/115258-MS
Rybacki E, Meier T, Dresen G (2016) What controls the mechanical properties of shale rocks?–Part II: Brittleness. J Pet Sci Eng 144:39–58
Sabah M, Mehrad M, Ashrafi SB, Wood DA, Fathi S (2021) Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field. J Pet Sci Eng 198:108125
Sheykhinasab A, Mohseni AA, Bahari AB, Naruei E, Davoodi S, Aghaz A, Mehrad M (2022) Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms. J Pet Explor Prod Technol 2022:1–29
Shi X, Liu G, Cheng Y, Yang L, Jiang H, Chen L, Jiang S, Wang J (2016) Brittleness index prediction in shale gas reservoirs based on efficient network models. J Nat Gas Sci Eng 35:673–685
Sondergeld CH, Newsham KE, Comisky JT et al (2010) Petrophysical considerations in evaluating and producing shale gas resources. In: Society of Petroleum Engineers - Canadian Unconventional Resources and International Petroleum Conference 2010. OnePetro, pp 1–34. https://doi.org/10.2118/131768-MS
Tabatabaei SME, Kadkhodaie-Ilkhchi A, Hosseini Z, Moghaddam AA (2015) A hybrid stochastic-gradient optimization to estimating total organic carbon from petrophysical data: A case study from the Ahwaz oilfield, SW Iran. J Pet Sci Eng 127:35–43
Tian Z (2020) Backtracking search optimization algorithm-based least square support vector machine and its applications. Eng Appl Artif Intell 94:103801
Verma S, Zhao T, Marfurt KJ, Devegowda D (2016) Estimation of total organic carbon and brittleness volume. Interpretation 4:T373–T385
Wang D, Ge H, Wang X, Wang J, Meng F, Suo Y, Han P (2015a) A novel experimental approach for fracability evaluation in tight-gas reservoirs. J Nat Gas Sci Eng 23:239–249
Wang M, Wilkins RWT, Song G, Zhang L, Xu X, Li Z, Chen G (2015b) Geochemical and geological characteristics of the Es3L lacustrine shale in the Bonan sag, Bohai Bay Basin. China Int J Coal Geol 138:16–29
Wang FP, Gale JFW (2009) Screening criteria for shale-gas systems. Gulf Coast Assoc Geol Soc Trans 59:779–793
Wood DA (2021a) Brittleness index predictions from Lower Barnett Shale well-log data applying an optimized data matching algorithm at various sampling densities. Geosci Front 12:101087. https://doi.org/10.1016/j.gsf.2020.09.016
Wood DA (2021b) Assessing the brittleness and total organic carbon of shale formations and their role in identifying optimum zones to fracture stimulate. In: Sustainable Geoscience for Natural Gas SubSurface Systems, vol 2. Elsevier, pp 129–157. https://doi.org/10.1016/B978-0-323-85465-8.00014-5
Xia YJ, Li LC, Tang CA, Li XY, Ma S, Li M (2017) A new method to evaluate rock mass brittleness based on stress–strain curves of class I. Rock Mech Rock Eng 50:1123–1139
Yagiz S (2008) Utilizing rock mass properties for predicting TBM performance in hard rock condition. Tunn Undergr Sp Technol 23:326–339
Yagiz S (2009) Assessment of brittleness using rock strength and density with punch penetration test. Tunn Undergr Sp Technol 24:66–74
Yang XS (2020) Nature-inspired optimization algorithms: Challenges and open problems. J Comput Sci 46. https://doi.org/10.1016/j.jocs.2020.101104
Ye Y, Tang S, Xi Z, Jiang D, Duan Y (2022) A new method to predict brittleness index for shale gas reservoirs: Insights from well logging data. J Pet Sci Eng 208:109431
Yuan Y, Zhenxue J, Chen YU, Tianxu GUO, Yushan S, Ruotong Z (2015) Mineral compositions and brittleness of the middle jurassic iacustrine shale reservoirin northern qaidam basin. Geol J China Univ 21:117
Zhang D, Ranjith PG, Perera MSA (2016) The brittleness indices used in rock mechanics and their application in shale hydraulic fracturing: A review. J Pet Sci Eng 143:158–170
Zhang F, Deng S, Zhao H, Liu X (2022) A new hybrid method based on sparrow search algorithm optimized extreme learning machine for brittleness evaluation. J Appl Geophys 207:104845
Zoback MD (2007) Reservoir geomechanics. Cambridge University Press. https://doi.org/10.1017/CBO9780511586477
Author information
Authors and Affiliations
Contributions
M.Z.: Investigation, data curation, visualization, writing– original draft. S.D.: Conceptualization, methodology, investigation, writing – original draft, software, writing – review & editing, validation, supervision. B.L.: Investigation, writing – review & editing, formal analysis, visualization. M. M. Methodology, Conceptualization, investigation, software, writing – review & editing, validation. S. R.: Data curation, Writing – review & editing. M.V.: Writing – review & editing, visualization. All authors reviewed the final manuscript.
Corresponding author
Ethics declarations
Consent for publication
All authors carefully reviewed and approved the final manuscript to be submitted to Earth Science Informatics for publication.
Competing interests
The authors declare no competing interests.
Additional information
Communicated by: H. Babaie
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendices
k-fold cross validation
This technique is used to cluster a dataset into k sets of equal size. Out of this k sets, (k – 1) sets are then used to train the model and the remaining set is used to have it tested. The training–testing process is repeated for k runs so that each set is once used for testing and (k – 1) times used for training the model. At each run, the value of error is recorded and an average error is calculated at the end. In this approach, since all data points contribute to the training process, the dependence of final results on the training data alone is reduced and undesirable effect of random initializations (for hyperparameters of the estimator model or initial population of optimization algorithms) on the model development processes is attenuated, ending up with an error value which closely captures the reality.
Model evaluation criteria
Percent deviation (PD) or relative error (RE) for each data point (i) in the dataset (including n data points) are calculated based on the measured brittleness index (\(B{I}_{measured}\)) and predicted brittleness index (\(B{I}_{predicted}\)) by means of the following relationship:
Given the value of PD for each data point in the dataset, average percent deviation (APD) can be evaluated through Equation (A2).
Absolute average percent deviation (AAPD) can be computed from Equation (A3).
Standard deviation (SD) of error is also given from Equation (A4) based on mean error values (\(E{r}_{mean}\)) and error value at each data point (\(Er\)).
Root-mean-square error (RMSE) for model can be calculated from Equation (A5).
Finally, coefficient of determination (COD, \({R}^{2}\)) is expressed as follows:
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zamanzadeh Talkhouncheh, M., Davoodi, S., Larki, B. et al. A new approach to mechanical brittleness index modeling based on conventional well logs using hybrid algorithms. Earth Sci Inform 16, 3387–3416 (2023). https://doi.org/10.1007/s12145-023-01098-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01098-1