# Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

_{c}) in marine structures. For this purpose, the values of C

_{c}in tidal, splash, and submerged zones were collected from an extensive literature survey and incorporated into the article. Gene expression programming (GEP), the decision tree (DT), and an artificial neural network (ANN) were used to predict the surface chloride concentrations, and the most accurate algorithm was then selected. The GEP model was the most accurate when compared to ANN and DT, which was confirmed by the high accuracy level of the K-fold cross-validation and linear correlation coefficient (R2), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) parameters. As is shown in the article, the proposed method is an effective and accurate way to predict the surface chloride concentration without the inconveniences of laboratory tests.

## 1. Introduction

^{3};

_{o}—concentration of chloride ions in concrete at the initial stage of their occurrence, mol/m

^{3};

^{2}/s;

_{s}—apparent surface chloride amount, mol/m

^{3};

_{o}is constant and is not affected by any type of concrete. However, the movement of chloride ions in the marine environment is determined by C

_{s}and D. The coefficient of apparent chloride diffusion is a material property that depends primarily on time. It can be determined based on information referring to the composition and microstructure of a material. C

_{s}concentration in diffusion law has a complex nature, as it not only depends on a material’s properties, but also on the environmental conditions and time. This creates ambiguity when making an accurate prediction of chloride ingress in a marine environment. Therefore, studies are needed to build a strong model that uses machine learning approaches, which can accurately predict the amount of apparent surface chloride.

## 2. Materials and Methods

#### 2.1. Apparent Surface Chloride Content

_{s}is an important variable when describing the transmission of chloride into structures [17]. It is obtained on site, or during laboratory investigations, as depicted in Figure 2. It can be seen that a convention zone is present in the investigated concrete element of the marine structure; however, there is no such zone in the concrete element investigated during the laboratory tests. The value of C

_{s}was obtained through the use of the bulk diffusion profile of chloride using a fitting curve. This variable is the most significant, as it describes the aggression of chloride, quantitative durability, and the prediction of service life of RCC structures.

_{s}value used in the calculations is considered to be constant for the zone in which an element is located. This creates uncertainty due to the complex nature of chloride ion transmission, as it depends on many factors, such as material properties (cement composition, binder properties, and water-to-cement ratio), and environmental factors (zonation, chloride content, depth, relative humidity, and temperature). Many attempts have been made to predict apparent chloride concentrations using logarithmic and exponential functions, or by correlating a concentration with the binder-to-water ratio, material variables, and environmental effects. However, there is still no accurate prediction model that is based on only a small number of variables. In contrast, when using machine learning algorithms, prediction models are more accurate and might be successfully used [18]. In this article, 642 data samples obtained from the literature survey [19] were used to predict surface chloride concentrations through the use of machine learning algorithms.

#### 2.2. Machine Learning (ML) and Ensemble Learning (EL) Approaches

_{2}and Cl

^{‒}ingress models. Suguru et al. [26] developed a model to automatically detect cracks in concrete structures with the use of machine learning. Photographs of concrete structures were used as learning data, and then deep learning was used to detect the cracks. Similarly, Wassim et al. [27] indicated that machine learning models have a high level of accuracy.

#### 2.3. Description of the Obtained Data

#### 2.4. Machine Learning Algorithms

_{s}was made using ANN, DT and GEP. A detailed flowchart of the used methodology is presented in Figure 4.

^{2}—equal to 0.83 [74]. Even though algorithms were previously used to predict the chloride concentration in concrete elements, there are no records of using gene expression programming for predicting chloride concentrations on the surface of marine concrete elements.

## 3. Results and Their Analyses

#### 3.1. Statistical Analysis

_{s}and the value identified by the machine learning algorithms) and the error distribution charts are presented in Figure 7. ANN gives a strong relation in the form of R

^{2}= 0.84, as can be seen in Figure 7a—with its error distribution shown in Figure 7b. The error distribution in Figure 7b illustrates that the average error of the training set is equal to 0.108 MPa. Moreover, the maximum and minimum error values of the training set were noted as 0.801 MPa and 0.0035 MPa, respectively. In addition, 69.1 percent of the data showed an error of less than 0.10 MPa, however, 64.3 percent of the data showed an error between 0.01 MPa and 0.10 MPa, as illustrated in Figure 7b.

^{2}value of 0.88 had a better accuracy when compared to the ANN (R

^{2}equal to 0.84) and DT (R

^{2}equal to 0.72), as depicted in Figure 7. In turn, Figure 7d indicates the error distribution of the linear regression model. It can be seen that 72.86 percent of the data showed an error between 0.01 MPa and 0.10 MPa, and that the average error of the training set was equal to 0.080 MPa. Moreover, the maximum and minimum errors were equal to 0.76 MPa and 0.004 MPa.

^{2}being equal to 0.72, as shown in Figure 7e. In addition, Figure 7f presents the error distribution of the linear regression model and shows an average value of error equal to 0.12 MPa, with a maximum error value of 1.36 MPa. In turn, 82.1 percent of the model has an error between 0.005 MPa and 0.25 MPa.

#### 3.2. K-Fold Cross Validation

- $e{x}_{i}$—experimental value;
- $m{o}_{i}$—predicted value;
- ${\overline{ex}}_{i}$—mean experimental value;
- ${\overline{mo}}_{i}$—mean predicted value obtained by the model;
- n—number of samples.

^{2}), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were all used to evaluate the result of cross-validation, as can be seen in Figure 8. A comparison of all three individual model techniques indicated fluctuation in their outputs. The GEP model showed fewer errors with a much better R

^{2}value when compared to the ANN and DT. The average R

^{2}value of GEP modeling was equal to 0.79, with maximum and minimum values being 0.94 and 0.65, as illustrated in Figure 8a. The average value of R

^{2}for the ANN model was equal to 0.71, with the maximum and minimum values being 0.89 and 0.62. Similarly, the DT model gave an average R

^{2}value of 0.82, with maximum and minimum values being 0.93 and 0.68, as illustrated in Figure 8b,c. The values of the errors of all the models were relatively low in the case of the validation process. For GEP, they were: MAE = 7.03 MPa, MSE = 6.12 MPa, and RMSE = 2.46 MPa (Figure 8a). In the case of the ANN, they were: MAE = 7.56 MPa, MSE = 6.60 MPa, and RMSE = 2.54 MPa (Figure 8b); and in the case of the decision tree, they were: MAE = 7.66 MPa, MSE = 6.85 MPa, and RMSE = 2.61 MPa (Figure 8c). Moreover, the K-fold cross validation of all the applied models and statistical checks are listed in Table 4 and Table 5, respectively.

## 4. Discussion

^{2}value of 0.88, was the most accurate when compared to the ANN (R

^{2}equal to 0.84) and DT (R

^{2}equal to 0.72). This algorithm was also compared with those used in [18], and the results of the comparison accuracy are presented in Figure 9.

^{2}, which is on a comparable level to other algorithms used in the literature.

## 5. Conclusions

- ●
- The GEP algorithm is very effective for predicting chloride surface concentrations and can be successfully used for this purpose. This was also proved by comparing it with other algorithms used in the literature.
- ●
- The presented method does not depend on the zone in which it is used (except the atmospheric zone where the transport of chloride ions is more difficult to describe).
- ●
- The high performance of the GEP algorithm was also proved using k-fold validation.

- ●
- The dataset can be expanded with laboratory tests, field tests, or numerical analyses using different upsizing methods (e.g., Monte Carlo).
- ●
- There is still the possibility of expanding the dataset with the results of surface chloride concentrations obtained for elements located in the atmospheric zone.
- ●
- Due to the fact that there is no model in the literature that is 100% accurate, there is still the possibility of using a different, more accurate, algorithm.

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## Abbreviations

Notations | |

ML | Machine learning |

HPC | High performance concrete |

GGBS | Ground granulated blast furnace slag |

GEP | Genetic engineering programming |

ANN | Artificial neural network |

Dt | Decision tree |

DL | Deep learning |

DM | Deep machine |

RF | Random forest |

GB | Gradient boosting |

FA | Fly ash |

SF | Silica fume |

POFA | Palm oil fuel ash |

SCC | Self-compacting concrete |

RHA | Rice husk ash |

RKSA | Random kitchen sink algorithm |

SVM | Support vector machine |

ANFIS | Adaptive neuro fuzzy inference system |

IREMSVM-FR | Intelligent rule-based enhanced multiclass support vector machine |

RMS | Response surface method |

## References

- Scott, R.H.; Chikermane, S.; Vidakovic, M.; McKinley, B.; Sun, T.; Banerji, P.; Grattan, K.T.V. Development of low cost packaged fibre optic sensors for use in reinforced concrete structures. Meas. J. Int. Meas. Confed.
**2019**, 135, 617–624. [Google Scholar] [CrossRef] - Ryl, J.; Wysocka, J.; Cieslik, M.; Gerengi, H.; Ossowski, T.; Krakowiak, S.; Niedzialkowski, P. Understanding the origin of high corrosion inhibition efficiency of bee products towards aluminium alloys in alkaline environments. Electrochim. Acta
**2019**, 304, 263–274. [Google Scholar] [CrossRef] - Moreno, J.D.; Bonilla, M.; Adam, J.M.; Borrachero, M.V.; Soriano, L. Determining corrosion levels in the reinforcement rebars of buildings in coastal areas. A case study in the Mediterranean coastline. Constr. Build. Mater.
**2015**, 100, 11–21. [Google Scholar] [CrossRef] - Zhang, P.; Cong, Y.; Vogel, M.; Liu, Z.; Müller, H.S.; Zhu, Y.; Zhao, T. Steel reinforcement corrosion in concrete under combined actions: The role of freeze-thaw cycles, chloride ingress, and surface impregnation. Constr. Build. Mater.
**2017**, 148, 113–121. [Google Scholar] [CrossRef] - Balafas, I.; Burgoyne, C.J. Environmental effects on cover cracking due to corrosion. Cem. Concr. Res.
**2010**, 40, 1429–1440. [Google Scholar] [CrossRef] - Ann, K.Y.; Ahn, J.H.; Ryou, J.S. The importance of chloride content at the concrete surface in assessing the time to corrosion of steel in concrete structures. Constr. Build. Mater.
**2009**, 23, 239–245. [Google Scholar] [CrossRef] - Nikoo, M.; Sadowski, Ł.; Nikoo, M. Prediction of the Corrosion Current Density in Reinforced Concrete Using a Self-Organizing Feature Map. Coatings
**2017**, 7, 160. [Google Scholar] [CrossRef] [Green Version] - Sadowski, L. Non-destructive investigation of corrosion current density in steel reinforced concrete by artificial neural networks. Archiv. Civ. Mech. Eng.
**2013**, 13, 104–111. [Google Scholar] [CrossRef] - Ali, B.; Qureshi, L.A.; Shah, S.H.A.; Rehman, S.U.; Hussain, I.; Iqbal, M. A step towards durable, ductile and sustainable concrete: Simultaneous incorporation of recycled aggregates, glass fiber and fly ash. Constr. Build. Mater.
**2020**, 251, 118980. [Google Scholar] [CrossRef] - Zhou, Y.; Fan, Z.; Du, J.; Sui, L.; Xing, F. Bond behavior of FRP-to-concrete interface under sulfate attack: An experimental study and modeling of bond degradation. Constr. Build. Mater.
**2015**, 85, 9–21. [Google Scholar] [CrossRef] - Akiyama, M.; Frangopol, D.M.; Suzuki, M. Integration of the effects of airborne chlorides into reliability-based durability design of reinforced concrete structures in a marine environment. Struct. Infrastruct. Eng.
**2012**, 8, 125–134. [Google Scholar] [CrossRef] - Sadowski, L.; Nikoo, M. Corrosion current density prediction in reinforced concrete by imperialist competitive algorithm. Neural Comput. Appl.
**2014**, 25, 1627–1638. [Google Scholar] [CrossRef] [Green Version] - Dai, J.G.; Akira, Y.; Wittmann, F.H.; Yokota, H.; Zhang, P. Water repellent surface impregnation for extension of service life of reinforced concrete structures in marine environments: The role of cracks. Cem. Concr. Compos.
**2010**, 32, 101–109. [Google Scholar] [CrossRef] - Moradllo, M.K.; Shekarchi, M.; Hoseini, M. Time-dependent performance of concrete surface coatings in tidal zone of marine environment. Constr. Build. Mater.
**2012**, 30, 198–205. [Google Scholar] [CrossRef] - Zuquan, J.; Xia, Z.; Tiejun, Z.; Jianqing, L. Chloride ions transportation behavior and binding capacity of concrete exposed to different marine corrosion zones. Constr. Build. Mater.
**2018**, 177, 170–183. [Google Scholar] [CrossRef] - Liu, Q.-F.; Hu, Z.; Lu, X.-Y.; Yang, J.; Azim, I.; Sun, W. Prediction of Chloride Distribution for Offshore Concrete Based on Statistical Analysis. Materials
**2020**, 13, 174. [Google Scholar] [CrossRef] [Green Version] - Bastidas-Arteaga, E.; Chateauneuf, A.; Sánchez-Silva, M.; Bressolette, P.; Schoefs, F. A comprehensive probabilistic model of chloride ingress in unsaturated concrete. Eng. Struct.
**2011**, 33, 720–730. [Google Scholar] [CrossRef] [Green Version] - Chen, W.B.; Zhou, W.H.; Sadowski, Ł.; Yin, Z.Y. Metaheuristic model for the interface shear strength between granular soil and structure considering surface morphology. Comput. Geotech.
**2021**, 135, 104141. [Google Scholar] [CrossRef] - Cai, R.; Han, T.; Liao, W.; Huang, J.; Li, D.; Kumar, A.; Ma, H. Prediction of surface chloride concentration of marine concrete using ensemble machine learning. Cem. Concr. Res.
**2020**, 136, 106164. [Google Scholar] [CrossRef] - Hoang, N.D.; Chen, C.T.; Liao, K.W. Prediction of chloride diffusion in cement mortar using Multi-Gene Genetic Programming and Multivariate Adaptive Regression Splines. Measurement
**2017**, 112, 141–149. [Google Scholar] [CrossRef] - Behnood, A.; Golafshani, E.M. Predicting the compressive strength of silica fume concrete using hybrid artificial neural network with multi-objective grey wolves. J. Clean. Prod.
**2018**, 202, 54–64. [Google Scholar] [CrossRef] - Getahun, M.A.; Shitote, S.M.; Gariy, Z.C.A. Artificial neural network based modelling approach for strength prediction of concrete incorporating agricultural and construction wastes. Constr. Build. Mater.
**2018**, 190, 517–525. [Google Scholar] [CrossRef] - Ling, H.; Qian, C.; Kang, W.; Liang, C.; Chen, H. Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment. Constr. Build. Mater.
**2019**, 206, 355–363. [Google Scholar] [CrossRef] - Yaseen, Z.M.; Deo, R.C.; Hilal, A.; Abd, A.M.; Bueno, L.C.; Salcedo-Sanz, S.; Nehdi, M.L. Predicting compressive strength of lightweight foamed concrete using extreme learning machine model. Adv. Eng. Softw.
**2018**, 115, 112–125. [Google Scholar] [CrossRef] - Taffese, W.Z.; Sistonen, E. Machine learning for durability and service-life assessment of reinforced concrete structures: Recent advances and future directions. Autom. Constr.
**2017**, 77, 1–14. [Google Scholar] [CrossRef] - Yokoyama, S.; Matsumoto, T. Development of an Automatic Detector of Cracks in Concrete Using Machine Learning. Procedia Eng.
**2017**, 1250–1255. [Google Scholar] [CrossRef] - Chaabene, W.B.; Flah, M.; Nehdi, M.L. Machine learning prediction of mechanical properties of concrete: Critical review. Constr. Build. Mater.
**2020**, 260. [Google Scholar] [CrossRef] - Farooq, F.; Ahmed, W.; Akbar, A.; Aslam, F.; Alyousef, R. Predictive modelling for sustainable high-performance concrete from industrial wastes: A comparison and optimization of models using ensemble learners. J. Clean. Prod.
**2021**, 126032. [Google Scholar] [CrossRef] - Balf, F.R.; Kordkheili, H.M.; Kordkheili, A.M. A New Method for Predicting the Ingredients of Self-Compacting Concrete (SCC) Including Fly Ash (FA) Using Data Envelopment Analysis (DEA). Arab. J. Sci. Eng.
**2020**, 1–22. [Google Scholar] [CrossRef] - Bušić, R.; Benšić, M.; Miličević, I.; Strukar, K. Prediction models for the mechanical properties of self-compacting concrete with recycled rubber and silica fume. Materials
**2020**, 13, 1821. [Google Scholar] [CrossRef] [Green Version] - Azimi-Pour, M.; Eskandari-Naddaf, H.; Pakzad, A. Linear and non-linear SVM prediction for fresh properties and compressive strength of high volume fly ash self-compacting concrete. Constr. Build. Mater.
**2020**, 230, 117021. [Google Scholar] [CrossRef] - Saha, P.; Debnath, P.; Thomas, P. Prediction of fresh and hardened properties of self-compacting concrete using support vector regression approach. Neural Comput. Appl.
**2020**, 32, 7995–8010. [Google Scholar] [CrossRef] - Al-Mughanam, T.; Aldhyani, T.H.H.; Alsubari, B.; Al-Yaari, M. Modeling of compressive strength of sustainable self-compacting concrete incorporating treated palm oil fuel ash using artificial neural network. Sustainability
**2020**, 12, 9322. [Google Scholar] [CrossRef] - Javed, M.F.; Farooq, F.; Memon, S.A.; Akbar, A.; Khan, M.A.; Aslam, F.; Alyousef, R.; Alabduljabbar, H.; Rehman, S.K.U. New prediction model for the ultimate axial capacity of concrete-filled steel tubes: An evolutionary approach. Crystals
**2020**, 10, 741. [Google Scholar] [CrossRef] - Aslam, F.; Farooq, F.; Amin, M.N.; Khan, K.; Waheed, A.; Akbar, A.; Javed, M.F.; Alyousef, R.; Alabdulijabbar, H. Applications of Gene Expression Programming for Estimating Compressive Strength of High-Strength Concrete. Adv. Civ. Eng.
**2020**. [Google Scholar] [CrossRef] - Farooq, F.; Amin, M.N.; Khan, K.; Sadiq, M.R.; Javed, M.F.; Aslam, F.; Alyousef, R. A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC). Appl. Sci.
**2020**, 10, 7330. [Google Scholar] [CrossRef] - Asteris, P.G.; Kolovos, K.G. Self-compacting concrete strength prediction using surrogate models. Neural Comput. Appl.
**2019**, 31, 409–424. [Google Scholar] [CrossRef] - Selvaraj, S.; Sivaraman, S. Prediction model for optimized self-compacting concrete with fly ash using response surface method based on fuzzy classification. Neural Comput. Appl.
**2019**, 31, 1365–1373. [Google Scholar] [CrossRef] - Zhang, J.; Ma, G.; Huang, Y.; Sun, J.; Aslani, F.; Nener, B. Modelling uniaxial compressive strength of lightweight self-compacting concrete using random forest regression. Constr. Build. Mater.
**2019**, 210, 713–719. [Google Scholar] [CrossRef] - Kaveh, A.; Bakhshpoori, T.; Hamze-Ziabari, S.M. M5’ and mars based prediction models for properties of selfcompacting concrete containing fly ash. Period. Polytech. Civ. Eng.
**2018**, 62, 281–294. [Google Scholar] [CrossRef] [Green Version] - Sathyan, D.; Anand, K.B.; Prakash, A.J.; Premjith, B. Modeling the Fresh and Hardened Stage Properties of Self-Compacting Concrete using Random Kitchen Sink Algorithm. Int. J. Concr. Struct. Mater.
**2018**, 12, 1–10. [Google Scholar] [CrossRef] - Vakhshouri, B.; Nejadi, S. Prediction of compressive strength of self-compacting concrete by ANFIS models. Neurocomputing
**2018**, 280, 13–22. [Google Scholar] [CrossRef] - Douma, O.B.; Boukhatem, B.; Ghrici, M.; Tagnit-Hamou, A. Prediction of properties of self-compacting concrete containing fly ash using artificial neural network. Neural Comput. Appl.
**2017**, 28, 707–718. [Google Scholar] [CrossRef] - Yaman, M.A.; Abd Elaty, M.; Taman, M. Predicting the ingredients of self compacting concrete using artificial neural network. Alex. Eng. J.
**2017**, 56, 523–532. [Google Scholar] [CrossRef] - Asteris, P.G.; Kolovos, K.G.; Douvika, M.G.; Roinos, K. Prediction of self-compacting concrete strength using artificial neural networks. Eur. J. Environ. Civ. Eng.
**2016**, 20, s102–s122. [Google Scholar] [CrossRef] - Siddique, R.; Aggarwal, P.; Aggarwal, Y. Prediction of compressive strength of self-compacting concrete containing bottom ash using artificial neural networks. Adv. Eng. Softw.
**2011**, 42, 780–786. [Google Scholar] [CrossRef] - Prasad, B.K.R.; Eskandari, H.; Reddy, B.V.V. Prediction of compressive strength of SCC and HPC with high volume fly ash using ANN. Constr. Build. Mater.
**2009**, 23, 117–128. [Google Scholar] [CrossRef] - Chalee, W.; Jaturapitakkul, C.; Chindaprasirt, P. Predicting the chloride penetration of fly ash concrete in seawater. Mar. Struct.
**2009**, 22, 341–353. [Google Scholar] [CrossRef] - Costa, A.; Appleton, J. Chloride penetration into concrete in marine environment-Part I: Main parameters affecting chloride penetration. Mater. Struct. Constr.
**1999**, 32, 252–259. [Google Scholar] [CrossRef] - Huan, X.U.E.; Zuquan, J.I.N.; Xiaojie, W. Chloride ion penetration into concrete exposed to marine environment for a long period. Ocean Eng.
**2015**, 33, 60–65. [Google Scholar] - Moradllo, M.K.; Sadati, S.; Shekarchi, M. Quantifying maximum phenomenon in chloride ion profiles and its influence on service-life prediction of concrete structures exposed to seawater tidal zone-A field oriented study. Constr. Build. Mater.
**2018**, 180, 109–116. [Google Scholar] [CrossRef] - Wang, Y.; Wu, L.; Wang, Y.; Li, Q.; Xiao, Z. Prediction model of long-term chloride diffusion into plain concrete considering the effect of the heterogeneity of materials exposed to marine tidal zone. Constr. Build. Mater.
**2018**, 159, 297–315. [Google Scholar] [CrossRef] - Zhang, Y.R.; Zhang, Y.; Huang, J.; Zhuang, H.X.; Zhang, J.Z. Time dependence and similarity analysis of peak value of chloride concentration of concrete under the simulated chloride environment. Constr. Build. Mater.
**2018**, 181, 609–617. [Google Scholar] [CrossRef] - Safehian, M.; Ramezanianpour, A.A. Assessment of service life models for determination of chloride penetration into silica fume concrete in the severe marine environmental condition. Constr. Build. Mater.
**2013**, 48, 287–294. [Google Scholar] [CrossRef] - Nanukuttan, S.V.; Basheer, L.; McCarter, W.J.; Robinson, D.J.; Basheer, P.M. Muhammed Basheer, Full-scale marine exposure tests on treated and untreated concretes-initial 7-year results. ACI Mater. J.
**2008**, 105, 81–87. [Google Scholar] [CrossRef] [Green Version] - Markeset, G.; Skjølsvold, O. Time Dependent Chloride Diffusion Coefficient-Field Studies of Concrete Exposed to Marine Environment in Norway. In Proceedings of the 2nd International Symposium on Service Life Design for Infrastructure, Delft, The Netherlands, 4–6 October 2010; pp. 83–90. [Google Scholar]
- Safehian, M.; Ramezanianpour, A.A. Prediction of RC structure service life from field long term chloride diffusion. Comput. Concr.
**2015**, 15, 589–606. [Google Scholar] [CrossRef] - Song, H.W.; Lee, C.H.; Ann, K.Y. Factors influencing chloride transport in concrete structures exposed to marine environments. Cem. Concr. Compos.
**2008**, 30, 113–121. [Google Scholar] [CrossRef] - Pack, S.W.; Jung, M.S.; Song, H.W.; Kim, S.H.; Ann, K.Y. Prediction of time dependent chloride transport in concrete structures exposed to a marine environment. Cem. Concr. Res.
**2010**, 40, 302–312. [Google Scholar] [CrossRef] - Ghods, P.; Chini, M.; Alizadeh, R.; Hoseini, M. The Effect of Different Exposure Conditions on the Chloride Diffusion into Concrete in the Persian Gulf Region. In Proceedings of the 3th ConMAT; University of British Columbia: Vancouver, BC, Canada, 2005. [Google Scholar]
- Farahani, A.; Taghaddos, H.; Shekarchi, M. Prediction of long-term chloride diffusion in silica fume concrete in a marine environment. Cem. Concr. Compos.
**2015**, 59, 10–17. [Google Scholar] [CrossRef] - Gao, Y.H.; Zhang, J.Z.; Zhang, S.; Zhang, Y.R. Probability distribution of convection zone depth of chloride in concrete in a marine tidal environment. Constr. Build. Mater.
**2017**, 140, 485–495. [Google Scholar] [CrossRef] - Pang, L.; Li, Q. Service life prediction of RC structures in marine environment using long term chloride ingress data: Comparison between exposure trials and real structure surveys. Constr. Build. Mater.
**2016**, 113, 979–987. [Google Scholar] [CrossRef] - Valipour, M.; Pargar, F.; Shekarchi, M.; Khani, S.; Moradian, M. In situ study of chloride ingress in concretes containing natural zeolite, metakaolin and silica fume exposed to various exposure conditions in a harsh marine environment. Constr. Build. Mater.
**2013**, 46, 63–70. [Google Scholar] [CrossRef] - Alizadeh, R.; Ghods, P.; Chini, M.; Hoseini, M.; Ghalibafian, M.; Shekarchi, M. Effect of Curing Conditions on the Service Life Design of RC Structures in the Persian Gulf Region. J. Mater. Civ. Eng.
**2008**, 20, 2–8. [Google Scholar] [CrossRef] - Tang, L. Chloride Ingress in Concrete Exposed to Marine Environment—Field Data up to 10 Years Exposure; Swedish National Testing and Research Institute: Borås, Sweden, 2003; ISBN 91-7848-948-2. [Google Scholar]
- Lindvall, A. Chloride ingress data from field and laboratory exposure-Influence of salinity and temperature. Cem. Concr. Compos.
**2007**, 29, 88–93. [Google Scholar] [CrossRef] - Dousti, A.; Rashetnia, R.; Ahmadi, B.; Shekarchi, M. Influence of exposure temperature on chloride diffusion in concretes incorporating silica fume or natural zeolite. Constr. Build. Mater.
**2013**, 49, 393–399. [Google Scholar] [CrossRef] - Gandomi, A.H.; Roke, D.A. Assessment of artificial neural network and genetic programming as predictive tools. Adv. Eng. Softw.
**2015**, 88, 63–72. [Google Scholar] [CrossRef] - Jahangir, H.; Eidgahee, D.R. A new and robust hybrid artificial bee colony algorithm-ANN model for FRP-concrete bond strength evaluation. Compos. Struct.
**2021**, 257, 113160. [Google Scholar] [CrossRef] - Asteris, P.G.; Skentou, A.D.; Bardhan, A.; Samui, P.; Pilakoutas, K. Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models. Cem. Concr. Res.
**2021**, 145, 106449. [Google Scholar] [CrossRef] - Ju, X.; Wu, L.; Lin, C.; Yang, X.; Yang, C. Prediction of chloride concentration with elevation in concrete exposed to cyclic drying-wetting conditions in marine environments. Constr. Build. Mater.
**2021**, 278, 122370. [Google Scholar] [CrossRef] - Oluwaseun Azeez, M.; Abd El Fattah, A. Service Life Modeling of Concrete with SCMs Using Effective Diffusion Coefficient and a New Binding Model. Crystals
**2020**, 10, 967. [Google Scholar] [CrossRef] - Hadzima-Nyarko, M.; Nyarko, E.K.; Ademović, N.; Miličević, I.; Kalman Šipoš, T. Modelling the Influence of Waste Rubber on Compressive Strength of Concrete by Artificial Neural Networks. Materials
**2019**, 12, 561. [Google Scholar] [CrossRef] [PubMed] [Green Version]

**Figure 7.**The results of the numerical analyses, which present the relationship between the predicted variable and the experimentally determined variable, as well as the distribution of errors for the ANN (

**a**,

**b**); GEP (

**c**,

**d**); and DT (

**e**,

**f**).

**Figure 8.**Statistical indicator for k-fold cross-validation. (

**a**) GEP model. (

**b**) ANN model. (

**c**) DT model.

Lp. | Algorithm Name | Notation | Dataset | Prediction Properties | Year | Waste Material Used | References |
---|---|---|---|---|---|---|---|

1. | Individual with ensemble modeling | ANN, bagging and boosting | 1030 | Compressive strength | 2021 | FA | [28] |

2. | Data envelopment analysis | DEA | 114 | Compressive strength Slump test L-box test V-funnel test | 2021 | FA | [29] |

3. | Multivariate | MV | 21 | Compressive strength | 2020 | Crumb rubber with SF | [30] |

4. | Support vector machine | SVM | - | Compressive strength | 2020 | FA | [31] |

5. | Support vector machine | SVM | 115 | Slump test L-box test V-funnel test Compressive strength | 2020 | FA | [32] |

6. | Adaptive neuro fuzzy inference system | ANFIS with ANN | 7 | Compressive strength | 2020 | POFA | [33] |

7. | Gene expression programming | GEP | 277 | Axial capacity | 2020 | - | [34] |

8. | Gene expression programming | GEP | 357 | Compressive strength | 2020 | - | [35] |

9. | Random forest and gene expression programming | RF and GEP | 357 | Compressive strength | 2020 | - | [36] |

10. | Artificial neural network | ANN | 205 | Compressive strength | 2019 | FA GGBFS SF RHA | [37] |

11. | Intelligent rule-based enhanced multiclass support vector machine and fuzzy rules | IREMSVM-FR with RSM | 114 | Compressive strength | 2019 | FA | [38] |

12. | Random forest | RF | 131 | Compressive strength | 2019 | FA GGBFS FA | [39] |

13. | Multivariate adaptive regression spline | M5 MARS | 114 | Compressive strength Slump test L-box test V-funnel test | 2018 | FA | [40] |

14. | Random kitchen sink algorithm | RKSA | 40 | V-funnel test J-ring test Slump test Compressive strength | 2018 | FA | [41] |

15. | Adaptive neuro fuzzy inference system | ANFIS | 55 | Compressive strength | 2018 | - | [42] |

16. | Artificial neural network | ANN | 114 | Compressive strength | 2017 | FA | [43] |

17. | Artificial neural network | ANN | 69 | Compressive strength | 2017 | FA | [44] |

18. | Artificial neural network | ANN | 169 | Compressive strength | 2016 | FA GGBFS FA RHA | [45] |

19. | Artificial neural network | ANN | 80 | Compressive strength | 2011 | FA | [46] |

20. | Artificial neural network | ANN | 300 | Compressive strength | 2009 | FA | [47] |

Parameters | Abbreviation | Units | Minimum | Maximum |
---|---|---|---|---|

Cement | C | kg/m^{3} | 110 | 519 |

Fly ash | FA | kg/m^{3} | 0 | 239 |

Ground furnace slag | GFS | kg/m^{3} | 0 | 292.5 |

Silica fume | SF | kg/m^{3} | 0 | 50 |

Super plasticizer | SP | kg/m^{3} | 0 | 10.2 |

Water | W | kg/m^{3} | 38.5 | 311 |

Fine aggregate | FA | kg/m^{3} | 552 | 1232 |

Coarse aggregate | CA | kg/m^{3} | 410 | 1305 |

Water/binder | W/C | - | 0.3 | 0.75 |

Exposure time | T | years | 0.08 | 48.65 |

Annual mean temperature | AMT | °C | 7 | 50 |

Chloride concentration in seawater | CCS | kg/m^{3} | 13 | 27.37 |

Surface chloride concentration | SCC | kg/m^{3} | 0.023 | 1.945 |

Parameters Descriptionr | C | FA | GFS | SF | SP | W | FA | CA | W/C | T | AMT | CCS |
---|---|---|---|---|---|---|---|---|---|---|---|---|

Mean | 370.70 | 33.97 | 11.41 | 5.41 | 1.47 | 187.54 | 765.77 | 993.81 | 0.46 | 4.24 | 17.78 | 18.99 |

Standard Error | 2.98 | 2.36 | 1.79 | 0.51 | 0.08 | 1.74 | 4.60 | 5.35 | 0.00 | 0.25 | 0.37 | 0.11 |

Median | 375.00 | 0.00 | 0.00 | 0.00 | 1.00 | 180.00 | 800.00 | 1020.00 | 0.45 | 2.67 | 16.80 | 19.00 |

Mode | 340.00 | 0.00 | 0.00 | 0.00 | 1.00 | 180.00 | 800.00 | 1020.00 | 0.45 | 5.00 | 7.00 | 19.00 |

Standard Deviation | 75.61 | 59.88 | 45.45 | 12.85 | 1.99 | 44.08 | 116.46 | 135.43 | 0.08 | 6.28 | 9.38 | 2.79 |

Sample Variance | 5716.21 | 3585.21 | 2066.15 | 165.02 | 3.95 | 1943.32 | 13,563.76 | 18,342.52 | 0.01 | 39.46 | 88.06 | 7.81 |

Kurtosis | 0.60 | 3.46 | 15.48 | 4.11 | 4.67 | 2.80 | 4.74 | 7.56 | 1.04 | 24.71 | −0.85 | 0.72 |

Skewness | −0.65 | 1.99 | 4.03 | 2.29 | 2.09 | 0.82 | 1.46 | −1.85 | 0.96 | 4.45 | 0.42 | 0.52 |

Range | 409.00 | 239.00 | 292.50 | 50.00 | 10.20 | 272.50 | 680.00 | 895.00 | 0.45 | 48.57 | 43.00 | 14.37 |

Minimum | 110.00 | 0.00 | 0.00 | 0.00 | 0.00 | 38.50 | 552.00 | 410.00 | 0.30 | 0.08 | 7.00 | 13.00 |

Maximum | 519.00 | 239.00 | 292.50 | 50.00 | 10.20 | 311.00 | 1232.00 | 1305.00 | 0.75 | 48.65 | 50.00 | 27.37 |

Sum | 237,992.50 | 21,809.50 | 7324.00 | 3475.00 | 942.56 | 120,398.80 | 491,625.00 | 638,027.00 | 292.43 | 2720.83 | 11,417.40 | 12,190.73 |

Count | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 | 642.00 |

K-Fold | GEP | ANN | DT | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|

R^{2} | MAE | MSE | RMSE | R^{2} | MAE | MSE | RMSE | R^{2} | MAE | MSE | RMSE | |

1 | 0.78 | 7.66 | 5.67 | 2.38 | 0.89 | 8.98 | 4.67 | 2.16 | 0.91 | 10.56 | 7.58 | 2.75 |

2 | 0.86 | 6.55 | 6.38 | 2.53 | 0.74 | 7.29 | 5.98 | 2.45 | 0.86 | 7.28 | 9.39 | 3.06 |

3 | 0.89 | 6.65 | 4.89 | 2.21 | 0.87 | 7.98 | 8.98 | 3.00 | 0.72 | 7.25 | 6.93 | 2.63 |

4 | 0.92 | 9.79 | 3.89 | 1.97 | 0.88 | 9.10 | 6.25 | 2.50 | 0.93 | 7.84 | 6.77 | 2.60 |

5 | 0.73 | 5.38 | 6.89 | 2.62 | 0.62 | 5.98 | 5.47 | 2.34 | 0.68 | 9.18 | 6.21 | 2.49 |

6 | 0.65 | 5.73 | 7.26 | 2.69 | 0.71 | 8.40 | 6.87 | 2.62 | 0.75 | 6.84 | 5.39 | 2.32 |

7 | 0.74 | 6.21 | 6.98 | 2.64 | 0.65 | 8.32 | 4.22 | 2.05 | 0.84 | 9.10 | 6.16 | 2.48 |

8 | 0.94 | 5.11 | 7.24 | 2.69 | 0.78 | 6.98 | 5.18 | 2.28 | 0.93 | 6.84 | 5.89 | 2.43 |

9 | 0.69 | 9.36 | 5.55 | 2.36 | 0.75 | 5.78 | 9.37 | 3.06 | 0.69 | 5.77 | 7.21 | 2.69 |

10 | 0.75 | 7.89 | 6.43 | 2.54 | 0.82 | 6.74 | 8.96 | 2.99 | 0.90 | 5.98 | 6.98 | 2.64 |

Machine Learning Methods | MAE (MPa) | MSE (MPa) | RMSE (MPa) |
---|---|---|---|

Gene Expression Program | 4.36 | 28.51 | 5.33 |

Artificial Neural Network | 4.48 | 31.86 | 5.64 |

Decision Tree | 4.55 | 36.73 | 6.06 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 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

**MDPI and ACS Style**

Ahmad, A.; Farooq, F.; Ostrowski, K.A.; Śliwa-Wieczorek, K.; Czarnecki, S.
Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material. *Materials* **2021**, *14*, 2297.
https://doi.org/10.3390/ma14092297

**AMA Style**

Ahmad A, Farooq F, Ostrowski KA, Śliwa-Wieczorek K, Czarnecki S.
Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material. *Materials*. 2021; 14(9):2297.
https://doi.org/10.3390/ma14092297

**Chicago/Turabian Style**

Ahmad, Ayaz, Furqan Farooq, Krzysztof Adam Ostrowski, Klaudia Śliwa-Wieczorek, and Slawomir Czarnecki.
2021. "Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material" *Materials* 14, no. 9: 2297.
https://doi.org/10.3390/ma14092297