Amirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201Clockwork Recurrent Neural Network- M5T: A New Machine Learning Model for Predicting Reservoir Inflow297310589010.22060/ajce.2025.23240.5866ENElhamGhanbari-AdiviDepartment of Water Engineering, Shahrekord University, Shahrekord, IranHamidHosseinkhaniDepartment of Water Engineering, Shahrekord University, Shahrekord, IranJournal Article20240530Reservoir inflow prediction is critical for effective water management. By accurately forecasting these inflows, reservoir operators can make well-informed choices regarding water releases, which can influence both the availability of water downstream and the potential for flooding. This research introduces a novel predictive model called the Clockwork Recurrent Neural Network (CWRNN)-M5T, specifically designed to forecast monthly reservoir inflow. By synthesizing these two models, this study proposes a groundbreaking method that significantly improves prediction accuracy and provides critical insights for effective water resource management. The CWRNN-M5T model can predict inflow for one, two, and three months ahead. This study showcases the model's effectiveness, contributing to advancements in engineering informatics for water resource management and optimal dam operations. It also explores how the model's performance changes with longer prediction horizons, emphasizing its limitations and potential real-world applications. The models utilized the lagged reservoir inflow values as inputs. For one month predictions, the CWRNN model yielded the best results. However, the CWRNN-M5T model surpassed all others, achieving a Nash Sutcliffe efficiency (NSE) of 0.98, compared to 0.94 for the CWRNN model. Additionally, the CWRNN-M5T model recorded the lowest mean absolute error (MAE) at 0.123, while the CWRNN model had an MAE of 0.210. For two months predictions, the CWRNN-M5T model achieved the lowest root mean square error (RMSE) of 0.254. Overall, the CWRNN-M5T model has proven to be a highly effective tool for predicting reservoir inflow.https://ajce.aut.ac.ir/article_5890_fc95fa5740ba01a870cfa52f671fe1e4.pdfAmirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201A Machine Learning Framework for Predicting Maximum Displacement of Reinforced Masonry Shear Walls under Lateral Loading311324591010.22060/ajce.2025.24820.5953ENShoaibMansouriDepartment of Civil Engineering, Amirkabir University of Technology, Tehran, Iran0009-0008-7480-7292Seyed HadiRashediDepartment of Civil Engineering, Amirkabir University of Technology, Tehran, Iran0009-0002-0737-2512AlirezaRahaiDepartment of Civil Engineering, Amirkabir University of Technology, Tehran, Iran0000-0002-9101-0794Journal Article20250927Accurate estimation of the maximum displacement capacity of masonry shear walls under lateral loading is essential for performance-based seismic design, yet conventional analytical and numerical approaches remain computationally intensive, sensitive to modeling assumptions, and highly dependent on expert interpretation. These limitations restrict their applicability for rapid assessment and design optimization. To address this challenge, this study proposes a machine learning (ML) framework that integrates predictive accuracy, interpretability, and mechanical validation. A database of 93 fully grouted masonry walls tested under cyclic displacement-controlled loading is utilized to develop a systematically optimized Multi-Layer Perceptron Artificial Neural Network (MLP-ANN). The model incorporates geometric, reinforcement, material, and axial-load parameters under the assumption of rectangular, fully grouted walls with consistent boundary conditions. Extensive architectural trials yielded an optimized ANN achieving R² values of 0.98, 0.97, and 0.90 for training, validation, and testing datasets, respectively. Complementary Random Forest (RF) analysis identified wall length, height, reinforcement ratios, masonry strength, and axial-load ratio as the most influential predictors governing displacement response. To verify the mechanical plausibility of the ML predictions, a finite element model (FEM) of a representative specimen was developed, reproducing experimental backbone curves within 5–10% deviation. The combined ANN–RF–FEM framework offers a fast, interpretable, and reliable tool for evaluating seismic displacement capacity of masonry walls. Future research should expand the dataset to include diverse wall geometries, boundary conditions, and materials, and explore hybrid ML–FEM or physics-informed models to further improve generalization and design applicability.https://ajce.aut.ac.ir/article_5910_79385312dbee4c9e7270b26e4b3e1459.pdfAmirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201Enhancing Construction Sustainability through the Use of Recycled Aggregates in Concrete Production325336591910.22060/ajce.2025.24090.5916ENMehrdadKhoshoeiFaculty of Engineering, University of Kashan, Kashan, Iran0009-0008-8996-0425KhaleghBaratiSchool of Civil and Environmental Engineering, University of New South Wales, Australia0000-0003-1992-8573Journal Article20250421The construction industry is a major consumer of natural resources and a significant contributor to environmental degradation, necessitating a shift towards more sustainable practices. This study comprehensively evaluates the emergy performance of concrete produced with recycled aggregates as a substitute for natural aggregates, with the aim of quantifying its potential to reduce total resource consumption and enhance sustainability within the built environment. A robust solar emergy accounting method was applied to quantify and compare all emergy inputs associated with the entire life cycle, including material extraction, processing, transportation, and the concrete production phase itself. The results clearly indicate that replacing 50% of natural coarse aggregates with recycled alternatives leads to a substantial 24.3% reduction in total emergy consumption and a 12.6% improvement in the Emergy Sustainability Index (ESI) compared to conventional natural aggregate concrete (NAC). The majority of these emergy savings are directly attributed to the avoidance of energy-intensive quarry extraction and the significantly reduced processing requirements for recycled materials. A sensitivity analysis further confirmed that the emergy advantage of recycled aggregate concrete remains significant even with increased transportation distances. These findings conclusively demonstrate that the strategic use of recycled aggregates can significantly improve the environmental performance of concrete by reducing its pressure on natural capital. This supports the transition toward more circular and resource-efficient construction practices. The study provides critical new insights and quantitative data for policymakers and industry stakeholders, highlighting the substantial emergy benefits of material substitution and informing strategies for sustainable concrete production.https://ajce.aut.ac.ir/article_5919_cd755a6c6b699f3262bcc2aa46ab507e.pdfAmirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201The behavior of high-strength LC3 concrete reinforced with recycled steel fiber under uniaxial compression and splitting tensile337356592010.22060/ajce.2025.24264.5927ENSaeedSedighiDepartment of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, IranAlirezaRahaiDepartment of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, Iran0000-0002-9101-0794FaramarzMoodiDepartment of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, IranJournal Article20250609This study assesses the stress-strain and load-deflection behavior of ordinary Portland cement (OPC) and limestone low kaolinite calcined clay cement (LC3) concrete under uniaxial compressive and indirect splitting loads. For this, ten concrete mixes were designed, half of which were LC3-based concrete. In the LC3-based concrete, 30% of cement was substituted with the limestone and calcined clay mixture. Four different contents of recycled tire steel fiber (RTSF) were used for reinforcing the concrete. The uniaxial compression and indirect splitting tensile tests were performed on the cylinder specimens. Peak strain, ultimate strain, absorbed energy, and toughness in compression were evaluated to assess the uniaxial compression behavior of plain and RTSF-reinforced OPC and LC3-based concrete. Also, absorbed energy and toughness in splitting were determined to examine the splitting behavior. The results demonstrated that at least 0.6% RTSF is required to develop the post-peak phase of the stress-strain curve under uniaxial compression. Further, the LC3 concrete resulted in lower peak and ultimate strains under compressive load. Incorporating 1.2% RTSF into OPC concrete enhanced the peak and ultimate strains by about 20% and 94%, respectively. In addition, the inclusion of 0.9% RTSF in LC3 concrete improved the peak and ultimate strains by approximately 18% and 100%, respectively. Furthermore, the LC3 concrete demonstrated better performance in the post-peak phase of splitting tensile. Moreover, digital image correlation (DIC) results demonstrated that incorporating RTSF into concrete effectively controls the initiation and propagation of cracks.https://ajce.aut.ac.ir/article_5920_4c4ea5258ef3fb3fb1fc48fee9b4408c.pdfAmirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201Ductility-based strength reduction factor for pulse-like and non-pulse-like ground motions357378592310.22060/ajce.2025.24151.5922ENSeyyed EbrahimMotallebiFaculty of Civil Engineering, Tabriz University of Technology, Tabriz, IranMehdiPourshaFaculty of Civil Engineering, Tabriz University of Technology, Tabriz, IranJournal Article20250512Reduction in forces, which results in inelastic deformations, is controlled by a coefficient called the strength reduction factor (R_µ). In the vicinity of active faults, ground motions are influenced by forward directivity and fling step (characterized by permanent ground displacement) effects. Previous studies have not addressed the R_µ factor considering the influence of fling step and non-pulse-like near-fault ground motion records. This paper attempts to evaluate the strength reduction factor for single-degree-of-freedom (SDOF) systems subjected to 78 pulse-like and non-pulse-like near-fault and far-fault ground motions recorded on the site classes C and D. The influence of the period of vibration, pulse period, and ductility level was studied in this paper. Moreover, in order to investigate the effect of cyclic deterioration, the modified Ibarra-Medina-Krawinkler (IMK) deterioration model with bilinear hysteretic behavior was employed. Finally, equations were proposed to obtain R_µ for different types of earthquakes. The results indicate that R_µ is strongly influenced by the period of vibration, ductility level, and cyclic deterioration. The results also show that the existing equations for calculating R_µ which are based on far-fault ground motions, can not be used for pulse-type near-fault records. Especially, for near-fault ground motions with fling step effect, applying the existing equations makes the design unsafe.https://ajce.aut.ac.ir/article_5923_418db2ea5d227a9ea8db8e5357ca2084.pdfAmirkabir University of TechnologyAUT Journal of Civil Engineering2588-28999420251201Influence of Multi-Directional Expanded Metal Mesh Reinforcement on Cement Mortar Flexural Performance379388592410.22060/ajce.2025.24780.5949ENShubbar JawadKadhimDepartment of Civil Engineering, University of Technology, Baghdad, Iraq.Journal Article20250920This study investigates the effect of varying the number and orientation of expanded metal mesh EMM layers as internal reinforcement on the flexural performance of mortar prisms, including flexural strength, toughness, first crack-load, and deflection at mid-span. Mixes were prepared using EMM layers embedded in prisms of dimensions 40 cm × 10 cm × 10 cm. The number of EMM layers were (one, two, and three) and their orientation; horizontal (perpendiculat to applied load), vertical (parallel to applied load), and a combination of both. The results showed that the incorporation of EMM improved the overall flexural performance significantly. This improvement became more pronounced with the increase in the number of EMM layers. Mixes reinforced with vertically aligned EMM layers exhibited greater improvements than those with horizontal alignment. The percentages of increase in flexural strength, toughness, and first crack-load for mix reinforced with three layers of horizontally alignend mesh were 80% , 595% , and 156 %, respectively. While for mixes reinforced with three layers of vertically aligned mesh, the corresponding values were 127%, 1474%, and 242%. The deflection results exhibited two different trends; under the same applied load, mixes reinforced with EMM showed lower deflection than the plain unreinforced mix, whereas at ultimate load, reinforced mixes recorded higher deflection. The mix reinforced with a combined orientation layers demonstrated the most significant improvements for all flexural performance tests, and the percentages of increase in flexural strength, toughness, and first crack load were 140%, 2063%, and 2875% relative to reference mix, repectively.https://ajce.aut.ac.ir/article_5924_d5fcc35c94879a4afad61cacca56192c.pdf