Anwar Akhtar, P.E., F.ASCE

🔹 Why can't we use traditional concrete piles in areas with soil susceptible to chemical attacks such as chlorine and sulfates, like the coasts of the Persian Gulf? Generally, what are the restrictive principles for using traditional methods in producing concrete piles? This article, authored by Mohammad Reza Fani Pakdel briefly mentions these constraints and requirements.

9

The second paper (derived from my dissertation) was accepted for publication in the American Society of Civil Engineers (ASCE). The paper was co-authored with Dr. Jalil Kianfar, PE, PTOE, RSP . Title: Investigating the Role of Dimension-Reduction in Counteracting Machine Learning Performance Bias in TSMO Strategies. Abstract: Machine learning is increasingly utilized to develop predictive models for Transportation Systems Management and Operations (TSMO) applications. These models are often assessed based on a global performance metric that evaluates the model's performance when the entire testing dataset is presented to the model. A TSMO application is expected to perform reliably and consistently in various situations and roadway conditions. The reliability and consistency of the model predictions for various scenarios are critical to the success of transportation agencies’ efforts to address mobility and safety issues. This paper investigates the performance bias that the traffic management center may face when applying machine learning methods to predict incident clearance time. Additionally, dimension-reduction techniques are investigated as performance bias mitigation techniques in the model development process. This paper investigates the impact of two common dimension-reduction methods, important feature selection, and principal component analysis, on performance bias. In a case study, this paper examines the performance bias of RF, BRNN, SVR, KNN, XGB, GP, and NNET in incident clearance time prediction. Incident data from three interstate corridors in Missouri, USA, were utilized to develop and evaluate the models. Repeated k-fold cross-validation was used to prepare twenty training and testing sets to demonstrate and assess the learners' performance variations due to data splits. The results indicated that the seven learners suffered from performance bias. The analysis of the impact of dimension-reduction models revealed that the important feature selection method did not notably mitigate the performance bias. On the other hand, the principal component analysis method substantially mitigated this bias for all learners, with poor-performing learners gaining the most improvements. In addition to reducing the performance bias, the principal component analysis notably reduced the learners' global (i.e., overall) error metrics. #phdjourney #asce #publication #intelligenttransportation

14

5 Comments

The first paper (derived from my dissertation) was accepted for publication in the American Society of Civil Engineers (ASCE). The paper was co-authored with Dr. Jalil Kianfar, PE, PTOE, RSP . Title: Hierarchical Classification-Regression (HiClassR) to Improve Incident Clearance Time Prediction. Abstract: Incident clearance time prediction is a key task in Advanced Transportation Management and Advanced Traveler Information Systems, as it informs mitigation and response strategies adopted by transportation agencies. Incident clearance time prediction is not a trivial task given that the duration of an incident is influenced by various factors, some of which are difficult to measure or not measured at all. Such constraints in the data might limit the accuracy of the models developed for predicting clearance time. Over the past decades, researchers have employed various statistical methods and machine learning approaches to overcome these limitations and improve the accuracy of the incident clearance time prediction models. While these efforts have successfully improved the overall accuracy of models, very few studies have focused on assessing and improving the generalization ability of incident clearance time prediction models. This paper proposes the hierarchical classification-regression (HiClassR) framework to improve the predictive performance of common machine-learning algorithms in predicting incident clearance time. HiClassR is a framework for developing a bi-level model in which the incidents are first assigned to an incident class; then, a class-specific model estimates the incident clearance time. While the HiClassR method is expected to improve error measures such as the RMSE over the entire dataset, it is also expected to improve the model's generalization ability across various incident scenarios. In a case study, the HiClassR method was applied to six conventional predictive methods to develop incident clearance time prediction models for St. Louis, MO, USA. The case study results indicate that the HiClassR model consistently outperforms the conventional base models and effectively generalizes the overall prediction power of the model to various incident categories of different conventional predictive methods. On average, the preferred HiClassR model reduced the RMSE from 22.7 min to 17.6 min for the random forest model, from 22.5 min to 19 min for Bayesian Regularization Neural Networks, from 23.7 min to 16.9 min for Support Vector Machines, from 25.2 min to 21.1 min for K-Nearest Neighbors, from 24.5 min to 19.7 min for XGB, and from 23.9 min to 18.3 min for Neural Networks. #phdjourney #asce #publication

9

2 Comments

🚀 **Just Published!** 🚀 I’m excited to share my latest research paper titled **"Modeling Life Expectancy and Cost Effectiveness for UHPC Bridge Retrofitting Techniques"** published in the journal Advances in Bridge Engineering. In this paper, we explore how Ultra-High-Performance Concrete (UHPC) can be a game-changer for bridge maintenance and rehabilitation. 🌉✨ A major contribution of this paper is the life expectancy model for UHPC concrete. This is a matter of the quandary because life expectancy for concrete structures has been quantified by evaluating the corrosion or predicting the bridge condition index. In the paper, life expectancy modeling was performed based on the corrosion and inherent properties of the concrete. https://lnkd.in/evPaNB8G #engineering #bridgemaintenance #UHPC #construction #infrastructure #innovation #sustainability

28

4 Comments

5th National Geotechnical Conference and 2nd International Conference on Earthquake and Seismic Geotechnical Engineering, Azarbaijan Shahid Madani University, October 2023, Tabriz, "Investigation of the effects of far-field earthquakes on the behavior of downstream tailings dams". Tailings are the residues left over from the extraction of metallic and non-metallic materials from mining operations, which can be toxic and a source of environmental pollution. They are typically stored in the tailings storage facilities (TSFs). A tailings dam is a large embankment constructed to retain mining waste, especially fine tailings (slurry). Obviously, the failure of such a geostructure is directly related not only to public health and safety, but also to the risk it poses to the environment.  Every year at least one or two tailings dam failures occur around the world, causing many injuries, environmental pollution and financial losses to mine owners. This is certainly more pronounced where there is a seismic risk, as confirmed by the report of the International Commission on Large Dams (ICOLD). On the other hand, as the daily production of minerals increases, so does the volume of tailings, making it necessary to increase the height of the dam and thus the capacity of the dam. Therefore, the influence of the dam height on the seismic behavior of tailings dams needs to be evaluated.  Therefore, the effects of dam height and foundation materials on the seismic behavior were investigated in terms of input acceleration, magnification, and permanent displacements. To perform the analysis, the static behavior of the dams was first investigated in eight cases with heights of 20, 50, 80, and 100 meters, two types of bedrock and alluvial foundations, and three loading stages such as end of construction, initial impoundment, and steady seepage. Dynamic analysis was then performed on all cases using seven far-field earthquake acceleration time histories from the literature.

3

On Monday, June 17, at 16:00 Eastern Time (ET), I will be delivering an online presentation on characterization of in situ stress at the 14th ISRM Young Members Seminar. For those interested in learning more about this subject can register for free. #rockmechanics #carma #isrm #youngmembers #insitustress #geotechnicalengineering #characterization #seminar #webinar

25

USACE seismic-related ERs and USSD Webinar on July 9, 2024 The United States Army Corps of Engineers (USACE) has recently updated three seismic-related Engineer Regulations (ER) (available in link below). These policy updates address seismic safety, functionality, operations and maintenance, post-earthquake response and repair, as well as instrumentation aspects of Civil Works (CW) projects including dams and levees. It should be noted that Engineer Manuals (EM) provide detail guidance on different topics, whereas ERs provide policy standards. These three ERs are available at https://lnkd.in/g2rHmqc8 There will be a webinar, hosted by USSD on July 9, 2024 on key updates and rationale for USACE seismic-related Engineer Regulations. Link to USSD webinar is https://lnkd.in/g5PBM2Fb ER 1110-2-103 (Strong-Motion Instruments for Monitoring and Recording Earthquake Ground Motions) provides requirements for strong motion instrumentations for dams and navigation structures. ER 1110-2-1802 (Post-Earthquake Inspections and Reporting for Civil Works Structures) provides regulation concerning verification of post-earthquake project integrity and performance. ER 1110-2-1806 (Earthquake Analysis Evaluation, and Design for Civil Works Projects) establishes minimum standards for serviceability and safety of civil works project features (including dams and levees) for specific earthquake return periods for ground motion and coincident pool elevations. It also provides requirements for aspects of seismic analysis, evaluation, and design.

83

My recent paper in Soil dynamics and earthquake engineering journal.

86

4 Comments

In the newest issue of #StantecERA, our teams reimagine what is possible for our #energy, #resources, and #water infrastructure. Learn more here. #StantecEnergy #StantecResources #StantecWater #EnergyTransition

1