Graduate Student Research

Niraj Adhikari

Concentration: Construction and Infrastructure Management
Overview: Adhikari’s research develops large language model (LLM)-based agentic systems for construction, addressing both their capabilities and their risks. He builds self-correcting LLM agents that automate BIM workflows and multimodal systems for construction safety compliance. His dissertation investigates the inverse problem: how generative AI threatens the integrity of highway construction quality assurance (QA) data, developing adversarial simulation methodologies to expose and mitigate these vulnerabilities. The overarching goal is enabling trustworthy adoption of AI across the construction project lifecycle.

Advisor: Rayan H. Assaad
Smart Construction and Intelligent Infrastructure Systems (SCIIS) Laboratory

Ghadi Charbel 

Concentration: Construction and Infrastructure Management
Overview: Charbel’s research integrates simulation modeling and deep learning to advance infrastructure resilience. His dissertation develops novel models for optimizing maintenance decisions and extending bridge lifecycles. Beyond civil infrastructure, he contributes to environmental research, examining lithium-ion battery lifecycle management and recycling, as well as litter management and policy improvements in the U.S. These efforts aim to enhance decision-making, sustainability, and long-term outcomes across both infrastructure and environmental systems. 

Advisor: Rayan H. Assaad
Smart Construction and Intelligent Infrastructure Systems (SCIIS) Laboratory

Prabhakar Khadka

Concentration: Geotechnical Engineering
Overview: Khadka’s research focuses on coastal slopes, aiming to understand their behavior, failure mechanisms, and long-term stability within dynamic coastal environments. To achieve this, I combine laboratory experimentation, finite element method (FEM)-based numerical analyses, and machine learning frameworks to study how coastal slopes respond and fail under real-world conditions. This work contributes to more reliable hazard mapping, better risk management, and the development of bio-based intervention strategies as sustainable solutions for slope reinforcement, supporting safer and more resilient coastal infrastructure. 

Advisor: Oladoyin Kolawole
Geomechanics for Geo-Engineering & Sustainability (GGES) Laboratory

Cyril Mendelek

Concentration: Construction and Infrastructure Management
Overview: Mendelek’s research advances artificial intelligence, machine learning, and data analytics for smarter infrastructure construction management. His dissertation develops a data-driven, expert-informed framework for production-rate estimation in transportation infrastructure projects by synthesizing daily work report analytics, multistate benchmarking, statistical production-rate analysis, and scheduling practice. By linking productivity assumptions to contract time determination, schedule reliability, delays, claims, and disputes, his work supports enhanced construction scheduling manuals, proactive risk governance, and more reliable, defensible decisions throughout the project delivery lifecycle.

Advisor: Rayan H. Assaad
Smart Construction and Intelligent Infrastructure Systems (SCIIS) Laboratory

Carol Mgiba 

Concentration: Geotechnical Engineering, Rock Mechanics
Overview: Mgiba’s research focuses on investigating mechanisms influencing rock collapse in underground excavations, both on Earth and in extraterrestrial environments. Underground engineering is essential to modern civilization, but the surrounding rock can collapse, posing serious safety and investment risk. By understanding rock mass response under varying stress conditions, she aims to support the development of stable, sustainable and resilient subsurface excavations here and beyond our planet. 

Advisor: Oladoyin Kolawole
Geomechanics for Geo-Engineering & Sustainability (GGES) Laboratory

Oscar Poudel

Concentration: Construction and Infrastructure Management
Overview: Poudel’s research focuses on developing AI-driven frameworks for next-generation construction automation, integrating human–robot interaction, intelligent sensing, and generative systems. The work spans over multimodal perception and control using deep learning, with ongoing research studies like audio-based monitoring, noise-robust voice control systems, wearable-based hand pose estimation for precision tasks etc. The ultimate goal is to enable context-aware, adaptive, and safe robotic systems that enhance productivity, safety, and real-time decision-making in dynamic construction environments. 

Advisor: Rayan H. Assaad
Smart Construction and Intelligent Infrastructure Systems (SCIIS) Laboratory

Matthew Sonibare

Concentration: Geotechnical Engineering
Overview: Sonibare’s research focuses on understanding the mechanical behavior of weak rock masses under different loading, environmental, and failure conditions to enhance their stability and performance in underground and geotechnical engineering applications. In particular, his research work investigates the effectiveness of grouting techniques in improving the strength, deformability, and resilience of fractured rocks. By integrating experimental testing, and numerical simulations, his research aims to optimize rock improvement strategies for challenging ground conditions. 

Advisor: Oladoyin Kolawole
Geomechanics for Geo-Engineering & Sustainability (GGES) Laboratory

Ravindu L. Senevirathna 

Concentration: Geotechnical Engineering; PFAS remediation; Acoustic cavitation and Nanobubble nucleation modeling
Overview: Senevirathna’s research focuses on the implosion of ultrasound-generated nanobubbles to destroy PFAS in contaminated water. The project investigates how acoustic parameters, water chemistry, and interfacial effects influence nanobubble generation, stability, and collapse. A key component of his work is developing a predictive model for nanobubble generation under ultrasound, with the goal of linking controllable operating conditions to improved PFAS degradation efficiency in water treatment applications. 

Advisor: Jay Meegoda
Co-advisor: Linda Cummings

Ronit Sthapit 

Concentration: Structural Engineering
Overview: Sthapit’s research focuses on understanding the behavior of reinforced high-performance fiber-reinforced cementitious composites (R/HPFRCC) columns through extensive experimental testing and numerical simulations. The effects of key parameters such as axial load ratio, longitudinal reinforcement, and material mechanical properties are investigated by subjecting R/HPFRCC columns to axial and reversed cyclic loadings. Based on the experimental and simulation results, plastic hinge expressions suitable for use in frame analysis are developed.

Advisor: Matthew J. Bandelt
Materials and Structures Laboratory (MatSLab)

Sowmya Atukuri

Concentration: Nanobubble Technology for Environmental Remediation
Overview: Atukuri's research focuses on understanding the physicochemical properties of nanobubbles and their interactions with oil-water systems for environmental remediation applications. The work investigates nanobubble stability, partitioning behavior, interfacial interactions, electrocoalescence, foam fractionation, and soil washing processes. Experimental studies are combined with modeling approaches to elucidate contaminant transport and removal mechanisms. The ultimate goal is to develop sustainable and efficient technologies for remediation of oil-contaminated water systems. 

Advisor: Wen Zhang
Sustainable Environmental Nanotechnology and Nanointerfaces Laboratory

Ebenezer Etsiwah

Concentration: Treatment Solutions for Emerging Contaminants in Water and Wastewater; PFAS
Overview: Per- and polyfluoroalkyl substances (PFAS) continue to be a major water treatment hurdle that needs to be addressed. Etsiwah’s research focuses on developing novel treatment approaches and technologies to address PFAS and other emerging contaminants in various environmental media.  

Advisor: Arjun Venkatesan
Emerging Contaminants Research Laboratory (ECRL)

Bishnu Pandey

Overview: Pandey’s research focuses on addressing PFAS (“forever chemicals”) contamination in water. These persistent, potentially carcinogenic compounds are widespread across soil, air, and water. His work explores sustainable and practical methods to remove PFAS from water, aiming to protect both public health and the environment. Specifically, he investigates treatment strategies involving coagulation-flocculation and foam fractionation to improve PFAS removal efficiency.

Advisor: Arjun Venkatesan
Emerging Contaminants Research Laboratory (ECRL)

Tamjidul Islam Illin

Concentration: Soil and Groundwater Transportation, Contaminant Hydrogeology
Overview: Illin's research proposes an electrokinetic remediation (EKR) system to remove PFAS and metals from contaminated soil and groundwater under replicable field-relevant conditions. The study will evaluate contaminant transport, treatment efficiency, energy consumption, and permeable reactive barrier performance. The project aims to enhance the understanding of PFAS mobilization mechanisms and develop guidelines for full-scale implementation of EKR technology. 

Advisor: Michel Boufadel
Center for Natural Resources (CNR)

Md Azmain Rahman

Concentration: Flood Modeling, Hydrology, Hydraulics, Stormwater Management, and Mitigation
Overview: Rahman’s research focuses on urban and riverine flooding, flood risk assessment, stormwater management, and flood mitigation through 2D hydrodynamic modeling. As part of state funded research conducted in coordination with the New Jersey Office of Emergency Management (NJOEM), Rahman uses HEC-RAS 2D, GIS-based watershed analysis, high-resolution terrain data, and field observations to simulate flood behavior and evaluate mitigation alternatives such as levees, floodwalls, reservoirs, detention basins, green infrastructure, erosion control measures, and drainage improvements. His research aims to support informed decision-making and provide practical recommendations for water resource management and community flood resilience in New Jersey.

Advisor: Michel Boufadel
Center for Natural Resources (CNR)

Jiahe Zhang

Concentration: Electrochemistry, Advanced Surface Analysis (AFM), Water Treatment & Resource Recovery
Overview: Zhang’s research focuses on novel electrochemical separation and resource recovery by valorizing conventional wastewater into useful chemical products. Specifically, he designs and tests gas-permeable electrodes that convert/capture nutrients with minimal chemical inputs and energy, leveraging interfacial acid–base microenvironments to drive selectivity. He also employs cutting-edge characterization tools such as atomic force microscopy (AFM) in combination with IR, KPFM, and electrochemical scanning microscope to perform nanoscale characterization for catalysts and acquire reactivity mapping and quantification, essential for understanding of nanoscale transport, fouling, and wetting.

Advisor: Wen Zhang
Sustainable Environmental Nanotechnology and Nanointerfaces Laboratory

Yining Zhang 

Concentration: Sustainable Agriculture and Advanced Water/Soil Treatment Technologies
Overview: Zhang’s research focuses on developing advanced methods for quantifying plant growth and health using 3D scanning technologies integrated with AI-based data analysis. By creating more accurate and efficient approaches to monitoring plant development, his work supports sustainable agricultural practices. He also explores the use of nanobubble-enriched hydrogels for improved water retention and nutrient delivery in soils. Together, these technologies aim to address key environmental challenges and promote resilient, sustainable food systems.

Advisor: Wen Zhang
Sustainable Environmental Nanotechnology and Nanointerfaces Laboratory

Abolfazl Afshari

Concentration: Intelligent Transportation Systems (ITS), Artificial Intelligence for Transportation, Transportation Data Analytics, Digital Twins, Autonomous AI Agents, Large Language Models (LLMs), Vision-Language Models (VLMs), and Smart Mobility Systems
Overview: Abolfazl Afshari’s research focuses on advancing intelligent transportation systems through the integration of artificial intelligence, generative AI, large language models (LLMs), vision-language models (VLMs), autonomous AI agents, computer vision, LiDAR sensing, digital twins, connected vehicle technologies, and traffic simulation. His work centers on developing intelligent and interpretable transportation systems for traffic operations, safety, mobility, and infrastructure management. By combining real-time sensing, data analytics, and AI-driven decision-making, his research aims to create safer, more efficient, and more adaptive transportation networks capable of responding to complex real-world conditions. 

Advisor: Joyoung Lee
Intelligent Transportation Systems Resource Center (ITSRC)

Mohammadjavad Bazdar

Concentration: AI-Driven Transportation Systems, Transportation Data Analytics, Agentic AI/LLM-Based Decision Support, Autonomous Mobility Simulation, and AI-Enabled Multimodal Travel Demand Modeling
Overview: Bazdar’s research focuses on AI-enabled transportation systems. He developed IRIS (Incident Response Intelligence System), a next-generation traffic incident management framework that uses agentic AI to orchestrate predictive modeling, LLM, and retrieval-based reasoning (RAG) for smarter incident response. His work features a novel tour-based travel demand model that integrates OpenPaths AGENT/CUBE applications, generative-AI-assisted synthetic population modeling, and AI-assisted calibration to move travel demand modeling toward a more realistic era. His broader work includes autonomous vehicle simulation and AI-based safety analytics.

Advisor: Branislav Dimitrijevic
Intelligent Transportation Systems Resource Center (ITSRC)

Emmanuel Obeng Danquah

Concentration: Intelligent Transportation Systems
Overview: Danquah’s research focuses on improving the continuity and reliability of vehicle trajectories using roadside LiDAR data for intelligent transportation systems. LiDAR sensors can capture detailed vehicle movement in real traffic environments, but the resulting trajectories may sometimes become fragmented when tracking is interrupted or when vehicles pass through areas with limited detection. His work develops data-driven methods to reconnect and reconstruct these broken vehicle movement paths so they can provide more reliable information for traffic analysis, travel-time estimation, roadway operations, vehicle behavior understanding, and safety-related applications.

Advisor: Joyoung Lee
Intelligent Transportation Systems Research Center (ITSRC)

Md Tufajjal Hossain

Concentration: Traffic Flow Modeling, Intelligent Transportation Systems, Physics-Informed Neural Network (PINN), and AI-Driven Traffic Safety Analysis
Overview: Hossain’s research focuses on advancing intelligent and data-driven traffic management by integrating connected-vehicle (CV) telemetry, crowdsourced sensing, and artificial intelligence. His work includes traffic count estimation from high-resolution trajectories, real-time incident detection using Waze data, optimal Safety Service Patrol routing from historical crash data, and crash-risk modeling through harsh-braking telematics. He was also involved in applying large language models (LLM) for crash severity prediction. By combining statistical modeling, GIS, and AI, his research enables proactive, cost-efficient, and real-time decision-making for safer and smarter transportation infrastructure.

Advisor: Joyoung Lee
Intelligent Transportation Systems Resource Center (ITSRC)

Aimee Jefferson 

Overview: Jefferson’s research uses nearly 35,000 crashes in New York City (2020-2024) to create binary logistic regression models that identify significant crash characteristics for e-scooters and e-bikes and key differences between the two devices and bicycles. Key findings indicate that rider signal non-compliance and unsafe vehicular passing significantly increase the likelihood of fatal or severe injury (FSI) crash. Additionally, the dissertation establishes a framework for understanding common crash configurations and explores targeted safety countermeasures.

Advisor: Janice Daniel

Hyun Kim

Concentration: Travel Demand Modeling, Reinforcement Learning for Multi-agent Route Optimization
Overview: Kim’s research focuses on applying artificial intelligence to improve on-demand public transportation services. Using deep reinforcement learning, he develops autonomous shuttle systems that learn how to make real-time routing and passenger service decisions in dynamic environments. His work explores how fleets of vehicles can coordinate efficiently to reduce passenger wait times, improve service reliability, and enhance overall transportation system performance, helping advance the future of smart and sustainable mobility.

Advisor: Branislav Dimitrijevic

Md Wazkuruni

Concentration: Intelligent Transportation Systems (ITS), Connected and Autonomous Vehicles (CAVs), Autonomous Vehicle Safety, Robotics and ROS2, Digital Twins, Traffic Simulation, Artificial Intelligence for Transportation, and Transportation Data Analytics
Overview: Md Wazkuruni's research focuses on improving the safety, reliability, and operational performance of intelligent transportation and autonomous vehicle systems. His work integrates robotics, ROS2 based autonomous platforms, traffic simulation, artificial intelligence, and digital twin technologies to evaluate vehicle behavior and transportation system performance. His research includes autonomous vehicle safety assessment, surrogate safety analysis, sensor based perception, connected vehicle applications, and transportation modeling using microscopic traffic simulation tools such as Vissim. By combining real time sensing, simulation, and data driven decision making, his research aims to support the development of safer, smarter, and more efficient transportation systems.

Advisor: Joyoung Lee
Intelligent Transportation Systems Resource Center (ITSRC)

Yuyue Zhang

Concentration: Intelligent Transportation Systems and Transportation Safety Analytics
Overview: Zhang’s research focuses on intelligent transportation systems and transportation safety, with an emphasis on applying artificial intelligence, large language models (LLMs), and data analytics to transportation problems. Her current work includes wildlife-related crash analysis, information extraction from crash narratives, and the integration of structured and unstructured data for safety modeling. She is also interested in leveraging emerging traffic data sources to support data-driven decision-making and improve roadway safety.

Advisor: Joyoung Lee
Intelligent Transportation Systems Resource Center (ITSRC)