Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Modeling of Reference Crop Evapotranspiration in Wet and Dry Climates Using Data-Mining Methods and Empirical Equations12814266710.22115/scce.2022.298173.1347ENMohammad Sadegh ZakeriGraduated MSc., Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, IranSayed Farhad MousaviProfessor, Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, IranSaeed FarzinAssociate Professor, Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, Iran0000-0003-4209-9558Hadi SanikhaniAssistant Professor, Department of Water Engineering, Faculty of Agriculture, Kurdistan University, Sanandaj, IranJournal Article20210803In the present study, performance of data-mining methods in modeling and estimating reference crop evapotranspiration (ET<sub>o</sub>) is investigated. To this end, different machine learning, including Artificial Neural Network (ANN), M5 tree, Multivariate Adaptive Regression Splines (MARS), Least Square Support Vector Machine (LS-SVM), and Random Forest (RF) are employed by considering different criteria including impacts of climate (eight synoptic stations in humid and dry climates), accuracy, uncertainty and computation time. Furthermore, to show the application of data-mining methods, their results are compared with some empirical equations, that indicated the superiority of data- mining methods. In the humid climate, it was demonstrated that M5 tree model is the best if only accuracy criterion is considered, and MARS is a better data-mining method by considering accuracy, uncertainty, and computation time criteria. While in the dry climate, the ANN has better results by considering accuracy and all other criteria. In the final step, for a comprehensive investigation of data-mining ability in ET<sub>o</sub> modeling, all data in humid and dry climates are combined. Results showed the highest accuracy by MARS and ANN models.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Identifying and Ranking of Mechanized Tunneling Project's Risks by Using A Fuzzy Multi-Criteria Decision Making Technique294514266810.22115/scce.2022.305718.1366ENSina Shaffiee HaghshenasPh.D. Candidate, Department of Civil Engineering, University of Calabria, 87036 Rende, Italy0000-0003-2859-3920Sami Shaffiee HaghshenasM.Sc., Department of Civil Engineering, University of Calabria, 87036 Rende, Italy0000-0002-9301-8677Mohammed AdelAbduelrhmanM.Sc., Department of Civil Engineering, University of Calabria, 87036 Rende, ItalyShervin ZareM.Sc., Department of Mechanical, Energy and Management Engineering, University of Calabria, Rende, ItalyReza MikaeilAssociate Professor, Department of Mining and Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran0000-0001-8404-3216Journal Article20210920A tunneling project is one of the most significant infrastructure projects. Its implementation requires access to adequate data and use of unique proceedings; hence it has a special position among civil engineering projects. Unexpected and uncertain conditions in tunneling projects lead to an increase of potential risks during project implementation. Identifying and evaluating risks in tunneling projects are considered one of the significant challenges among civil engineers, which can cause proper risk management during tunnel construction. Therefore, this study aims to evaluate and rank the risks of the second part of the Emamzadeh Hashem tunnel in the north of Iran which was considered as a case study. For this purpose, twelve potential risks were identified by using geological studies and experts. Then, they were evaluated and ranked using effective fuzzy multi-criteria decision-making (FMCDM) techniques, namely fuzzy analytical hierarchical process (FAHP). The three decision variables were considered, including repeat chance, occurrence possibility, and efficacy. The results obtained indicated that the occurrence possibility was the most effective among the decision variables in this case study. In addition, Instability of the wall and lack of contractor’s experiences had the highest and lowest ranks with 0.103 and 0.052, respectively.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Identifying and Prioritizing Arising Claim's Factors by the Combined Approach of DEMATEL and ANP Method (Case Study: Urban Development and Civil Organization of Shiraz Municipality Projects)466514266910.22115/scce.2022.288877.1328ENAmir AkbariMaster of Construction Management, Management Department, Apadana Institute, Shiraz, IranArdalan FeiliAssistant Professor, Management Department, Apadana Institute, Shiraz, Iran0000000159334572Mohsen DashtipourMaster Student of Business Administration, Management Department, Apadana Institute, Shiraz, IranJournal Article20210602Claim management describes the process required to eliminate or prevent construction claims from arising and for the expedition handling of claims when they do occur. The present study aimed to identify the factors affecting the claimed design and their ranking. This research is applied and descriptive. The effective factors have been identified by reviewing the claims filed by the contractors of Shiraz Municipality during one year and have been classified according to their nature in the four main areas of the Claims (scope, time, quality and cost). To collect data, questionnaires based on the multi-adjective decision-making method used in this study were used, which were completed by experts of civil engineering projects in Shiraz Municipality. Data were analyzed using a combined approach of Decision-making Trial and Evaluation Laboratory (DEMATEL) and Analytic Network Process (ANP). According to the results, 3 factors: Deviation from the project schedule plan, Changes in the technical specifications of and the resources of tasks and Not controlling the actual values on-site before execution with the initial estimate of the contract have the most effect and factors: Not to prepare a joint mapping with the presence of the consultant and the contractor at the beginning and Contractor financial loss due to bidding a lower price offer than the market have the least effect on claim. In general, factors related to time and quality areas have a greater effect on claim than factors related to scope and cost areas.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Shear Strength Prediction of Reinforced Concrete Shear Wall Using ANN, GMDH-NN and GEP668714413110.22115/scce.2022.283486.1308ENHosein NaderpourProfessor, Faculty of Civil Engineering, Semnan University, Semnan, Iran0000-0002-4179-7816Mohammadreza ShareiFaculty of Civil Engineering, Semnan University, Semnan, IranPouyan FakharianFaculty of Civil Engineering, Semnan University, Semnan, Iran0000-0003-4307-1944Mohammad Ali HeraviFaculty of Civil Engineering, Semnan University, Semnan, Iran0000-0001-6079-5106Journal Article20210426To provide lateral resistance in structures as well as buildings, there are some types of structural systems such as shear walls. The utilization of lateral loads occurs on a plate on the wall's vertical dimension. Conventionally, these sorts of loads are transferred to the wall collectors. There is a significant resistance between concrete shear walls and lateral seismic loading. To guarantee the building's seismic security, the shear strength of the walls has to be prognosticated by using models. This paper aims to predict shear strength by using Artificial Neural Network (ANN), Neural Network-Based Group Method of Data Handling (GMDH-NN), and Gene Expression Programming (GEP). The concrete's compressive strength, the yield strength of transverse reinforcement, the yield strength of vertical reinforcement, the axial load, the aspect ratio of the dimensions, the wall length, the thickness of the reinforced concrete shear wall, the transverse reinforcement ratio, and the vertical reinforcement ratio are the input parameters for the neural network model. And the shear strength of the reinforced concrete shear wall is considered as the target parameter of the ANN model. The results validate the capability of the models predicted by ANN, GMDH-NN, and GEP, which are suitable for use as a tool for predicting the shear strength of concrete shear walls with high accuracy.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Evaluation of Dimension Stone According to Resistance to Freeze–Thaw Cycling to Use in Cold Regions8810914467610.22115/scce.2022.325638.1398ENReza MikaeilAssociate Professor, Department of Mining Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran0000-0001-8404-3216Akbar EsmaeilzadehAssistant Professor, Department of Mining Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran0000-0002-8633-9683Sina Shaffiee HaghshenasPh.D. Candidate, Department of Civil Engineering, University of Calabria, 87036 Rende, Italy0000-0003-2859-3920Mohammad AtaeiProfessor, Department of Mining, Petroleum & Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran0000-0002-7016-8170Sina HajizadehigdirM.S., Department of Civil Engineering, Faculty of Environment, Urmia University of Technology, Urmia, IranAmir JafarpourPh.D. Candidate, Department of Mining and Metallurgical Engineering, Yazd University, Yazd, IranTae-Hyung KimProfessor, Department of Civil Engineering, Korea Maritime and Ocean University, Pusan 49112, KoreaZong Woo GeemProfessor, College of IT Convergence, Gachon University, Seongnam 13120, Korea0000-0002-0370-5562Journal Article20220120Freezing is one of the most effective natural and environmental factors on the physical and mechanical characteristics of dimension stones. Since, freezing is a destructive agent, thus causes the undesirable stone conditions and reduces quality and its efficiency. This study, it was aimed to evaluate and rank the dimension stones according to their changes in physical and mechanical properties due to freezing conditions. For this purpose, 14 rock types of the most widely used dimension stones in cold regions were collected and transferred to the laboratory to determine their physical and mechanical characteristics. In laboratory tests, standard samples of stones were prepared, and for all of the samples Uniaxial Compressive Strength (UCS), Durability Index (DI), Density (D), and Water absorption percentage (Wa) were determined before and after different freezing–thawing cycles. Then utility degree of studied stones in frost condition was assessed using the preference ranking organization method for enrichment of evaluations (PROMETHEE) multi-criteria decision-making method. The results of the study showed that samples of A3 (Piranshahr Granat), A10 (Hamadan black granite), A8 (Azarshahr yellow travertine), and A4 (Mahabad gray granite) are in order from the highest degree of desirability in a condition of freezing–thawing and for use in cold climates are especially suitable for use in outdoor and urban spaces. In addition, the results of the laboratory were evaluated by the PSO algorithm for clustering analysis and com-pared with the ranking result by PROMETHEE. The results obtained demonstrated the proposed approach could be an efficient tool in the evaluation of the freezing phenomenon on physical and mechanical properties of dimension stones.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Simulation and Prediction of Groundwater Quality of a Semi-Arid Region Using Fuzzy Inference System and Neural Network Techniques11012614534710.22115/scce.2022.285106.1314ENJegathambal PalanichamyProfessor, Water Institute, Karunya Institute of Technology and Sciences, Coimbatore, India0000-0003-4494-8664Sundarambal PalaniResearch Fellow, College of Design and Engineering, National University of Singapore, Singapore0000-0002-5644-9128G. Anita HebsibaWater Institute, Karunya Institute of Technology and Sciences, Coimbatore, IndiaJansi ViolaWater Institute, Karunya Institute of Technology and Sciences, Coimbatore, IndiaApinun TungsrimvongWater Institute, Karunya Institute of Technology and Sciences, Coimbatore, IndiaBabithesh BabuWater Institute, Karunya Institute of Technology and Sciences, Coimbatore, IndiaJournal Article20210507The groundwater is the main source of domestic and agricultural purposes in the arid and semi-arid regions where the surface water availability is limited. To protect and manage the groundwater system effectively, a thorough knowledge and understanding of groundwater quality and application of computational methods to simulate the complex and nonlinear groundwater system are paramount necessary. Generally, three types of models such as physically based model, conceptual models and Blackbox models are applied to study the interconnected processes in the subsurface media. In this study, Artificial Neural Network (ANN) (3 Models with 1, 2 and 3 outputs) was used to simulate and predict the concentration of groundwater quality parameters and Mamdani Fuzzy Inference System (MFIS) was used to simulate the water quality indices. Classification algorithms of NEUROSHELL and MATLAB were used to predict the class of items in a data set. The model was constructed using already-labelled items of similar data sets. The WQI of 29 samples was determined using weighted average method. Based on MFIS, 10 samples were classified as ‘good’, four samples as ‘poor’ and remaining samples as ‘very poor’. The simulation model using the classification algorithm of ANN was used to predict the concentration of groundwater quality parameters and it was observed that three ANN models values and the actual data fit well with correlation coefficient varying from 0.93 to 0.99. When the soft computing techniques can be coupled with geospatial and geostatical method to map the spatial and temporal distribution of water quality parameters.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726120220101Process Parameter Optimization of 6061AA Friction Stir Welded Joints Using Supervised Machine Learning Regression-Based Algorithms12713714751810.22115/scce.2022.299913.1350ENEyob MesseleSefeneGraduated M.Sc., Faculty of Mechanical and Industrial Engineering, Bahir Dar Institute of Technology, Bahir Dar University, P.O. Box 26, Bahir Dar, Ethiopia0000-0003-4660-6262Assefa AsmareTsegawAssistant Professor, Faculty of Mechanical and Industrial Engineering, Bahir Dar Institute of Technology, Bahir Dar University, P.O. Box 26, Bahir Dar, Ethiopia0000-0002-5453-3764Akshansh MishraGraduate M.Sc., Department of Chemistry, Materials, and Chemical Engineering “Giulio Natta”, Politecnico di Milano, Milan, Italy0000-0003-4939-359XJournal Article20210815In this contemporary technology epoch, material utilization is crucial concerning saving energy demand. One of the thinking points of the interest domain is weight reduction. The highest strength to weight ratio criterion of the welded joint has enthralled keenness in virtually all areas where heft reduction is indispensable. Lightweight materials and their joining processes are also a recent point of research demands in the manufacturing industries. Friction Stir Welding (FSW) is one of the recent advancements for joining materials without adding any third material (filler rod) and joining below the melting point of the parent material. The process is widely used for joining similar and dissimilar metals, especially lightweight non-ferrous materials like aluminum, copper, and magnesium alloys. This paper presents verdicts of optimum process parameters on attaining enhanced mechanical properties of the weld joint. The experiment was conducted on a 5 mm 6061 aluminum alloy sheet. Process parameters; tool material, rotational speed, traverse speed, and axial forces were utilized. Mechanical properties of the weld joint are examined employing a tensile test, and the maximum joint strength efficiency was reached 94.2%. Supervised Machine Learning based Regression algorithms such as Decision Trees, Random Forest, and Gradient Boosting algorithms were used. The results showed that the Random Forest algorithm yielded the highest coefficient of determination value of 0.926, giving the best fit compared to other algorithms. Furthermore, this method can be extended in large-scale and thick aluminum base materials.