Machine Learning-Based Prediction of Scale Inhibitor Efficiency in Oilfield Operations
Abstract
1. Introduction
2. Data and Methods
2.1. Algorithms Used in This Study
2.1.1. Data Preparation (Common to All Models in This Study)
- Input structuring:
- -
- Features (‘X’): Transpose raw matrix ‘D’ to *N × M* (N = samples, M = features);
- -
- Target (‘T’): Convert ‘S’ to column vector, clip to experimental range (e.g., [11%, 98%] for inhibition efficiency).
- Train-Test split:
- ▪
- Training: First 432 samples (≈65% for model development);
- ▪
- Test: Remaining samples (≈35% for unbiased evaluation).
2.1.2. Model-Specific Hyperparameter Tuning
- Decision Tree: Minimum leaf size = [1, 2, 4, …, 32]; Optimization Criterion: Minimal MAE.
- Random Forest: Number of Trees = [10, 50, 100, …, 500]; Optimization Criterion: Minimal MAE + OOB error.
- Neural Network: Hidden Layer Size = [5, 10, …, 20]; Optimization Criterion: Minimal MAE
- KNN: K = 1 to 50; Optimization Criterion: Minimal MAE
- Gaussian Process: Length Scale, Sigma (log-scale); Optimization Criterion: Minimal MAE + R2
- ▪
- Length Scale: Controls how far two inputs need to be for their outputs to be considered uncorrelated;
- ▪
- Sigma (Signal Standard Deviation): Represents the signal variance, determining the overall scale of variation in predictions.
- Efficiency in Exploration:
- 2.
- Computational Advantages:
- ▪
- Fewer total test points needed compared to linear spacing;
- ▪
- Better coverage of the parameter space;
- ▪
- More likely to find the true optimum;
- ▪
- Standard practice in machine learning optimization.
- Gradient Boosting: NumTrees, LearnRate, MaxDepth; Optimization Criterion: Minimal MAE + feature importance.
- Number of Trees (50–200): Common range for ensemble methods (too few→underfitting, too many→overfitting);
- Learning Rates (0.01–0.2): Standard GBM practice (lower rates need more trees but generalize better);
- Max Depth (2–4 via MinLeafSize): Controls complexity (deeper trees risk overfitting)
- Linear Regression: None (closed-form solution)
2.1.3. Model Training & Validation
- -
- Common steps:
- Train: Fit model to training data with optimal hyperparameters;
- Predict: Generate test predictions, clip to physical bounds;
- Evaluate: Compute metrics (MAE and R2).
2.1.4. Performance Comparison
- -
- Visualization: Overlay predicted vs. actual plots for all models (subplots);
- -
- Metric table: Compare MAE and R2;
- -
- Critical analysis:
- ○
- Interpretability: Decision trees > linear regression > others;
- ○
- Flexibility: GPR/NN > ensemble methods > linear models;
- ○
- Computation: GPR/NN > RF/GBM > others.
2.2. Data Collection
3. Results and Discussion
- ▪
- Complex models (GPR/Neural Networks) perform best when data is abundant and high accuracy is required;
- ▪
- Simpler models (Linear Regression/Random Forest) are more suitable for routine monitoring;
- ▪
- The optimal model choice depends on specific operational requirements.
4. Conclusions
Supplementary Materials
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Hashemi, S.H.; Hashemi, S.A. Prediction of Scale formation according to water injection operations in Nosrat Oil Field. Model. Earth Syst. Environ. 2020, 6, 585–589. [Google Scholar] [CrossRef]
- Hashemi, S.H.; Torghabeh, A.K.; Niknam, A.; Hashemi, S.A.; Gharaie, M.H.M.; Pimentel, N. Geochemical and Thermodynamic Study of Formation Water for Reservoir Management in Bibi Hakimeh Oil and Gas Field, Iran. Fuels 2025, 6, 11. [Google Scholar] [CrossRef]
- Hashemi, S.H.; Besharati, Z.; Torabi, F.; Pimentel, N. Thermodynamic Prediction of Scale Formation in Oil Fields During Water Injection: Application of SPsim Program Through Utilizing Advanced Visual Basic Excel Tool. Processes 2024, 12, 2722. [Google Scholar] [CrossRef]
- Haghtalab, A.; Kamali, J.; Shahrabadi, A. Prediction mineral scale formation in oil reservoirs during water injection. Fluid Phase Equilibria 2014, 373, 43–54. [Google Scholar] [CrossRef]
- Shabani, A.; Sisakhti, H.; Sheikhi, S.; Barzega, F. A reactive transport approach for modeling scale formation and deposition in water injection wells. J. Pet. Sci. Eng. 2020, 190, 107031. [Google Scholar] [CrossRef]
- Ardakani, S.F.G.; Hosseini, S.T.; Kazemzadeh, Y. A review of scale inhibitor methods during modified smart water injection. Can. J. Chem. Eng. 2024, 102, 3922. [Google Scholar] [CrossRef]
- Mpelwa, M.; Tang, S.F. State of the art of synthetic threshold scale inhibitors for mineral scaling in the petroleum industry: A review. Pet. Sci. 2019, 16, 830–849. [Google Scholar] [CrossRef]
- Housse, M.E.; Hadfi, A.; Iberache, N.; Karmal, I.; El-Ghazouani, F.; Ben-aazza, S.; Belattar, M.; Ammayen, I.; Nassiri, M.; Darbal, S.; et al. Eco-friendly and sustainable approaches to control scaling in industrial plants: Challenges and advantages of the application of plant extracts as a probable alternative for traditional inhibitor-A review. Ind. Crops Prod. 2024, 222, 120030. [Google Scholar] [CrossRef]
- Chaussemier, M.; Pourmohtasham, E.; Gelus, D.; Pécoul, N.; Perrot, H.; Lédion, J.; Cheap-Charpentier, H.; Horner, O. State of art of natural inhibitors of calcium carbonate scaling. A review article. Desalination 2015, 356, 47–55. [Google Scholar] [CrossRef]
- Husna, U.Z.; Elraies, K.A.; Shuhili, J.A.B.M.; Elryes, A.A. A review: The utilization potency of biopolymer as an eco-friendly scale inhibitors. J. Pet. Explor. Prod. Technol. 2022, 12, 1075–1094. [Google Scholar] [CrossRef]
- Freitas, V.M.S.; Paschoalino, W.J.; Vieira, L.C.S.; Silva, J.M.; Couto, B.C.; Gobbi, A.L.; Lima, R.S. Sensitive Monitoring of the Minimum Inhibitor Concentration under Real Inorganic Scaling Scenarios. ACS Omega 2024, 9, 39724–39732. [Google Scholar] [CrossRef] [PubMed]
- Yang, J.; Jia, L.; Wang, Z.; Niu, C.; Zhou, H.; Wang, Z.; Li, Y.; Chen, Y. Synthesis and scale inhibition performance of a novel phosphorus-free scale inhibitor–polyethylenebismaleamic acid-ethylenediamine. J. Mol. Struct. 2025, 1335, 141950. [Google Scholar] [CrossRef]
- Hu, H.; Wang, J.-J.; Ma, W.; Li, G.; Wang, L.-C. Effect of the ratio of carboxyl group to ethylene oxide on performance of acrylic acid based copolymer scale inhibitors. Desalination Water Treat. 2025, 321, 101035. [Google Scholar] [CrossRef]
- Zhang, P.; Zhang, Z.; Liu, Y.; Kan, A.; Tomson, M. Investigation of the impact of ferrous species on the performance of common oilfield scale inhibitors for mineral scale control. J. Pet. Sci. Eng. 2019, 172, 288–296. [Google Scholar] [CrossRef]
- Khormali, A.; Bahlake, G.; Struchkov, I.; Kazemzadeh, Y. Increasing inhibition performance of simultaneous precipitation of calcium and strontium sulfate scales using a new inhibitor—Laboratory and field application. J. Pet. Sci. Eng. 2021, 202, 10. [Google Scholar] [CrossRef]
- Khormali, A.; Sharifov, A.; Torba, D. Increasing efficiency of calcium sulfate scale prevention using a new mixture of phosphonate scale inhibitors during waterflooding. J. Pet. Sci. Eng. 2018, 164, 245–258. [Google Scholar] [CrossRef]
- Zakaria, K.; Salem, A.; Ramzi, M. Cost-effective and eco-friendly organophosphorus-based inhibitors for mineral scaling in Egyptian oil reservoirs: Theoretical, experimental and quantum chemical studies. J. Pet. Sci. Eng. 2020, 195, 107519. [Google Scholar] [CrossRef]
- Khodabakhshi, M.; Bijani, M. Predicting Scale Deposition in Oil Reservoirs Using Machine Learning Optimization Algorithms. Results Eng. 2024, 22, 102263. [Google Scholar] [CrossRef]
- Handhal, A.; Al-Abadi, A.; Chafeet, H.; Ismail, M. Prediction of total organic carbon at Rumaila oil field, Southern Iraq using conventional well logs and machine learning algorithms. Mar. Pet. Geol. 2020, 116, 104347. [Google Scholar] [CrossRef]
- Zaiery, M.; Kadkhodaie, A.; Arian, M.; Maleki, Z. Application of artificial neural network models and random forest algorithm for estimation of fracture intensity from petrophysical data. J. Pet. Explor. Prod. Technol. 2023, 13, 1877–1887. [Google Scholar] [CrossRef]
- Al-Mudhafar, W.J. Integrating well log interpretations for lithofacies classification and permeability modeling through advanced machine learning algorithms. J. Pet. Explor. Prod. Technol. 2017, 7, 1023–1033. [Google Scholar] [CrossRef]
- Mahdaviara, M.; Rostami, A.; Keivanimehr, F.; Shahbazi, K. Accurate determination of permeability in carbonate reservoirs using Gaussian Process Regression. J. Pet. Sci. Eng. 2020, 196, 107807. [Google Scholar] [CrossRef]
- Khormali, A.; Petrakov, D.G.; Nazari Moghaddam, R. Study of adsorption/desorption properties of a new scale inhibitor package to prevent calcium carbonate formation during water injection in oil reservoirs. J. Pet. Sci. Eng. 2017, 153, 257–267. [Google Scholar] [CrossRef]
- Khormali, A.; Petrakov, D.G.; Moein, M. Experimental analysis of calcium carbonate scale formation and inhibition in waterflooding of carbonate reservoirs. J. Pet. Sci. Eng. 2016, 147, 843–850. [Google Scholar] [CrossRef]
- Khormali, A.; Sharifov, A.R.; Torba, D.I. Investigation of Barium Sulfate Precipitation and Prevention Using Different Scale Inhibitors under Reservoir Conditions. Int. J. Eng. 2018, 31, 1796–1802. [Google Scholar]
- Khormali, A.; Petrakov, D.G.; Shcherbakov, G.Y. An In-depth Study of Calcium Carbonate Scale Formation and Inhibition. Iran. J. Oil Gas Sci. Technol. 2014, 3, 67–77. [Google Scholar]
- Khormali, A.; Petrakov, D.G.; Lamidi, A.-L.B.; Rastegar, R. Prevention of Calcium Carbonate Precipitation during Water Injection into High-Pressure High-Temperature Wells. In Proceedings of the SPE European Formation Damage Conference and Exhibition, Budapest, Hungary, 3–5 June 2015. [Google Scholar]
- Li, G.; Guo, S.; Zhang, J.; Liu, Y. Inhibition of scale buildup during produced-water reuse: Optimization of inhibitors and application in the field. Desalination 2014, 351, 213–219. [Google Scholar] [CrossRef]
- Azizi, J.; Shadizadeh, S.R.; Manshad, A.; Mohammadi, A. A dynamic method for experimental assessment of scale inhibitor efficiency in oil recovery process by water flooding. Petroleum 2019, 5, 303–314. [Google Scholar] [CrossRef]
- Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed.; Springer: New York, NY, USA, 2009. [Google Scholar]
- Cao, C. Prediction of concrete porosity using machine learning. Results Eng. 2023, 17, 100794. [Google Scholar] [CrossRef]
- Attanasi, E.D.; Coburn, T.C. Random Forest. In Encyclopedia of Mathematical Geosciences; Daya Sagar, B.S., Cheng, Q., McKinley, J., Agterberg, F., Eds.; Encyclopedia of Earth Sciences Series; Springer: Cham, Switzerland, 2023. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
Ionic Composition of Formation and Injection Waters | Inhibitor Type | Scale Inhibitor Concentration | Temperature Conditions | Target Scale Inhibition Efficiency | References |
---|---|---|---|---|---|
Cations: Na, K, Mg, Sr, Ca Anions: Cl, SO4 | DTPMP PBTC EDTMP ATMP HDTMP mixtures of reagents | 5–60 ppm | 40–150 °C | CaSO4SrSO4 | [15] |
Cations: Na, K, Mg, Ca Anions: Cl, SO4, HCO3 | HEDP ATMP DTPMP PPCA PPNMP New inhibitor as phosphonate Acid | 10–40 mg/L | 60–120 °C | CaSO4 | [16] |
Cations: Na, K, Mg, Ca Anions: Cl, SO4, HCO3 | Developed scale inhibitor package: HEDP: 3% Hydrochloric acid solution, 5 wt%: 10% Ammonium chloride: 4% Isopropyl alcohol: 2% PPNMP: 4% DTPMP: 4% Water: 73% | 5–50 mg/L | 60–100 °C | CaCO3 | [23] |
Cations: Na, K, Mg, Ca Anions: Cl, SO4, HCO3 | N1: 1-hydroxyethane 1, 1-diphosphonic acid (HEDP), C3 H8 O, NH 4Cl, HCl, polyethylene polyamine-N-methylphosphonic acid, water N2: Aminotrimethylenephosphonic acid (ATMP) | 15–30 mg/L | 60–120 °C | CaCO3 | [24] |
Cations: Na, K, Mg, Ba, Ca Anions: Cl, SO4, HCO3 | HEDP ATMP DTPMP PPCA New inhibitor as Phosphonate acid | 30 mg/L | 60–120 °C | BaSO4 | [25] |
Cations: Na, Mg, Ba, Ca, Sr, Li Anions: Cl, SO4, HCO3, CO32− | SI1: Mixture of C2H8O7P2 (3%), NH4Cl (4%), C12H5N7O12 -N- CH5O3P (4%), HCl (10%), C3H8O (2%) and water SI2: Mixture of H5P3O10, C2H7NO, (CH3)PO(OH)2 and C16H32O6 SI3: Mixture of (CH3)PO(OH)2, K4P2O7, C2H7NO and CH6NO3P | 10–50 mg/L | 75 °C | CaCO3 | [26] |
Cations: Na, Mg, Ca, Sr, K Anions: Cl, SO4, HCO3, CO32− | Nitrilotrimethylphosphonic acid Aqueous solution of acrylic Based on phosphorus Oxiethilidendiphosphone acid 4%, ammonium chloride5%, polyethylene polyamine-N-methylphosphonic acid 6%, hydrochloric acid 12%, isopropyl alcohol 3%, water remaining | 5–60 mg/L | 200 °C | CaCO3 | [27] |
Cations: Mg, Ca Anions: Cl, SO4, HCO3 | BTCA HEDP ATMP Compound inhibitor: PBTCA:HEDP:ATMP, 2:2:1; Zn2+, 30% ratio of compound inhibitor; OP-15, 4 mg/L | 10–100 mg/L | 85 °C | Different scales during the recycling and reuse of oilfield-produced water | [28] |
Cations: Na, Mg, Ca, Sr, K, Ba, Fe Anions: Cl, SO4, HCO3 | Phosphonate Phosphonate (Mix) Polymeric/Phosphonate | 5–35 ppm | 25–45 °C | Different scales during water flooding | [29] |
Cations: Na, K, Mg, Ca, Ba, Fe Anions: Cl, SO4, HCO3, CO32− | zoledronic acid (ZDA), alendronic acid (ADA) pamidronic acid (PDA) | 40, 60, and 80 ppm | 127 °C | BaSO4 FeCO3 CaSO4.2H2O | [17] |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hashemi, S.H.; Torabi, F. Machine Learning-Based Prediction of Scale Inhibitor Efficiency in Oilfield Operations. Processes 2025, 13, 1964. https://doi.org/10.3390/pr13071964
Hashemi SH, Torabi F. Machine Learning-Based Prediction of Scale Inhibitor Efficiency in Oilfield Operations. Processes. 2025; 13(7):1964. https://doi.org/10.3390/pr13071964
Chicago/Turabian StyleHashemi, Seyed Hossein, and Farshid Torabi. 2025. "Machine Learning-Based Prediction of Scale Inhibitor Efficiency in Oilfield Operations" Processes 13, no. 7: 1964. https://doi.org/10.3390/pr13071964
APA StyleHashemi, S. H., & Torabi, F. (2025). Machine Learning-Based Prediction of Scale Inhibitor Efficiency in Oilfield Operations. Processes, 13(7), 1964. https://doi.org/10.3390/pr13071964