About

Raja Sengupta is a Professor in the Systems Engineering Program, Civil & Environmental Engineering at UC Berkeley. He holds a Ph.D. in Systems Engineering from the University of Michigan, earned in 1995, and a Master's degree in Systems Engineering from the same institution, obtained in 1991. His undergraduate degree is in Electrical Engineering from Jadavpur University, India, completed in 1988. His research spans a broad range of topics including transportation, wireless communications, inertial navigation for vehicle systems, automated cars, drones, connected cars, smartphone applications for economics and transportation, wireless networking, and control theory. Professor Sengupta has made significant contributions to the development of vehicle-to-road and vehicle-to-vehicle networking technologies, holding patents with Toyota and BAE Aerospace, and contributing to standards by the SAE. His work includes research on sensor networks for forest fire monitoring, vehicle neighborhood mapping, and autonomous navigation of unmanned aerial and ground vehicles for applications such as firefighting, border patrol, search and rescue, and environmental monitoring. He has been recognized with awards such as the USDOT's Connected Vehicle Technology award in 2011 and UC Berkeley's Energy and Climate Lectures Innovation Award in 2014. Additionally, he has served as an advisor to the World Bank and has authored over a hundred papers in his fields of expertise.

Research topics

• Geography
• Computer Science
• Economics
• Medicine
• Biology
• Transport engineering
• Environmental science
• Mathematics
• Statistics
• Demographic economics
• Engineering
• Ecology
• Data science
• Environmental resource management
• Environmental economics
• Environmental health
• Psychology
• Advertising
• Meteorology
• Toxicology
• Agroforestry
• Business

Selected publications

• Joint Supply-Demand Control of Urban Air Mobility Operations with Variable Pricing: A Case Study of Airport Access Market at JFK

  SSRN Electronic Journal · 2026-01-01

  preprintOpen access
  PublisherDOI

• DRBO—A Regional Scale Simulator Calibration Framework Based on Day-to-Day Dynamic Routing and Bayesian Optimization

  Smart Cities · 2025-03-13 · 1 citations

  articleOpen accessSenior author

  Traffic simulation, a tool for recreating real-life traffic scenarios, acts as an important platform in transportation research. Considering the growing complexity of urban mobility, various large-scale regional simulators are designed and used for research and applications. Calibration is a key issue in the traffic simulation: it finds the optimal system pattern to decrease the gap between the simulator output and the real data, making the system much more reliable. This paper proposes DRBO, a calibration framework for large-scale traffic simulators. This framework combines the travel behavior adjustment with black box optimization, better exploring the structure of the regional scale mobility. The motivation of the framework is based on the decomposition of the regional scale mobility dynamic. We decompose the mobility dynamic into the car-following dynamic and the routing dynamic. The prior dynamic imitates how vehicles propagate as time flows while the latter one reveals how vehicles choose their route according to their own information. Based on the decomposition, the DRBO framework uses iterative algorithms to find the best dynamic combinations. It utilizes the Bayesian optimization and day-to-day routing update to separately calibrate the dynamic, then combine them sequentially in an iterative way. Compared to the prior arts, the DRBO framework is efficient for capturing multiple perspectives of traffic conditions. We further tested our simulator on SFCTA demand to further validate the speed distribution from our simulation and observed data.

  PublisherOA PDFDOI

• From Patchwork to Network: A Comprehensive Framework for Demand Analysis and Fleet Optimization of Urban Air Mobility

  ArXiv.org · 2025-10-05

  preprintOpen accessSenior author

  Urban Air Mobility (UAM) presents a transformative vision for metropolitan transportation, but its practical implementation is hindered by substantial infrastructure costs and operational complexities. We address these challenges by modeling a UAM network that leverages existing regional airports and operates with an optimized, heterogeneous fleet of aircraft. We introduce LPSim, a Large-Scale Parallel Simulation framework that utilizes multi-GPU computing to co-optimize UAM demand, fleet operations, and ground transportation interactions simultaneously. Our equilibrium search algorithm is extended to accurately forecast demand and determine the most efficient fleet composition. Applied to a case study of the San Francisco Bay Area, our results demonstrate that this UAM model can yield over 20 minutes' travel time savings for 230,000 selected trips. However, the analysis also reveals that system-wide success is critically dependent on seamless integration with ground access and dynamic scheduling.

  PublisherOA PDFDOI

• Quantitative and Spatially Explicit Clustering of Urban Grocery Shoppers in Montreal: Integrating Loyalty Data with a Synthetic Population

  Preprints.org · 2025-03-17 · 1 citations

  preprintOpen accessSenior author

  This study integrates customer loyalty program data with a synthetic population to analyze grocery shopping behaviours in Montreal. Using clustering techniques, we classify 295,631 loyalty program members into seven distinct consumer segments based on behavioural and sociodemographic attributes. The findings reveal significant heterogeneity in consumer behaviour, emphasizing the impact of urban geography on shopping decisions. This segmentation also provides valuable insights for retailers optimizing store locations and marketing strategies, and for policymakers aiming to enhance urban accessibility. Additionally, our approach strengthens Agent-Based Model (ABM) simulations by incorporating demographic and behavioural diversity, leading to more realistic consumer representations. While integrating loyalty data with synthetic populations mitigates privacy concerns, challenges remain regarding data sparsity and demographic inconsistencies. Future research should explore multi-source data integration and advanced clustering techniques. Overall, this study contributes to geographically explicit modelling, demonstrating the effectiveness of combining behavioural and synthetic demographic data in urban retail analysis.

  PublisherOA PDFDOI

• A Novel Voronoi-Driven Optimization Approach for Point-Based Sensor Network Deployment

  IEEE Access · 2025-01-01 · 1 citations

  articleOpen access

  Sensor Networks (SNs) are gaining more attention in applications such as urban microclimate monitoring, which is a critical input for building energy simulation. Despite extensive research on SN placement, there remains a shortage of studies on efficient solutions that account for realistic sensing models without oversimplifying the environment or search spaces, making current approaches inadequate for large-scale real-world problems. This study relies on a realistic coverage model for point-based sensor networks (e.g., air temperature sensors) and introduces a novel and efficient heuristic Voronoi-based Optimal Sensor Deployment Algorithm (VOSDA). The algorithm estimates the minimum number of sensors needed and their optimal placement. Its performance is evaluated using the root mean square error (RMSE), calculated via an interpolation process that reconstructs the field from sensor positions. VOSDA leverages Voronoi diagram characteristics to manage the sensor network, assess error distribution, and enhance coverage quality through integrated sensor insertion and movement strategies. Several experiments were conducted to evaluate the effectiveness and efficiency of the proposed approach, comparing the results with the Genetic Algorithm (GA) as a reference by calculating the RMSE using Kriging, Thin Plate Spline, and Inverse Distance Weighting methods. In all cases, VOSDA was first used to estimate the required number of sensors, and RMSE was then calculated for both algorithms at that sensor count. Furthermore, in six out of nine different scenarios conducted across different benchmark heatmaps, VOSDA outperformed GA in achieving lower RMSE values. Both algorithms performed significantly better with Kriging and TPS than with IDW.

  PublisherDOI

• Pathogen Control System for Buildings

  medRxiv · 2025-12-04

  articleOpen accessSenior author

  Abstract Background Environmental control systems in buildings are typically designed to maintain occupant comfort while minimizing energy use. However, the significant role of airborne pathogens in respiratory illness transmission has highlighted the imperative to address how these control systems can mitigate infection risk. Traditional CO 2 -based ventilation control does not necessarily correlate with infectious aerosol presence, limiting its effectiveness for pathogen mitigation. Objective To develop and evaluate a pathogen control system (PCS) that combines real-time pathogen sensing with in-duct germicidal ultraviolet (GUV) irradiation to reduce infection risk while maintaining energy efficiency and occupant comfort. Methods We developed a closed-loop control system using pathogen air quality (PAQ) sensors with hysteretic threshold control (7-20 copies/m 3 ) to dynamically activate GUV systems achieving 99% single-pass inactivation efficiency. System performance was evaluated across four activity scenarios (1.33-750 copies/s generation rates) in a simulated 70 m 3 office environment using eight complementary metrics: peak concentration ( C peak ), steady-state concentration ( C ss ), clearance time improvement (Δ t clear ), time to safety ( t safe ), cumulative inhaled dose ( D inh ), infection risk probability ( P risk ), equivalent clean air rate (ECAi), and energy consumption. Results In talking scenarios, the PCS reduced peak concentration from 40 to 22 copies/m 3 (45% reduction), time to safety from 75 to 25 min (67% improvement), cumulative inhaled dose from 1.1×10 −2 to 4.4×10 −3 copies (60% reduction), and infection risk from 56.07% to 28.88%. In high activity scenarios, peaks decreased from 90 to 45 copies/m 3 , time to safety from 90 to 30 min, dose from 2.4×10 −2 to 8.4×10 −3 copies (65% reduction), and risk from 83.93% to 47.83% (43% relative reduction). Baseline active control increased ECAi from 108 to 191 m 3 /h, with geometric scaling enabling pathways to full ASHRAE 241 compliance (920-3,680 m 3 /h). System performance was robust across sampling intervals (30-300 s) while achieving 37-52% energy savings through duty-cycle operation. Significance This study provides the first comprehensive quantitative framework for sensor-based pathogen control in building environments. The demonstrated ability to achieve substantial infection risk reduction while maintaining energy efficiency supports the viability of pathogen-responsive building control as an effective intervention for indoor air quality management. Results establish fundamental design principles and performance benchmarks that can inform regulatory guidelines, building codes, and public health recommendations for pathogen control system deployment in the era of healthy buildings. Impact Statement This research addresses a critical gap in building environmental control by demonstrating how real-time pathogen sensing can enable targeted, energy-efficient disinfection strategies that traditional CO 2 -based systems cannot achieve. By providing quantitative evidence that sensor-based pathogen control systems can reduce infection risk by 43-67% across realistic occupancy scenarios while maintaining operational efficiency, this work establishes a scientific foundation for next-generation healthy building technologies. The systematic evaluation framework and performance benchmarks developed herein directly support evidence-ng based implementation of pathogen-responsive building control systems, contributing to improved occupant health outcomes and enhanced pandemic preparedness in built environments. These findings are particularly relevant for the Journal of Exposure Science and Environmental Epidemiology’s focus on environmental health and exposure assessment, as they provide quantitative tools for evaluating and optimizing indoor air quality interventions that reduce infectious disease transmission risk.

  PublisherOA PDFDOI

• Quantitative and Spatially Explicit Clustering of Urban Grocery Shoppers in Montreal: Integrating Loyalty Data with Synthetic Population

  ISPRS International Journal of Geo-Information · 2025-04-06

  articleOpen accessSenior authorCorresponding

  This study integrates customer loyalty program data with a synthetic population to analyze grocery shopping behaviours in Montreal. Using clustering algorithms, we classify 295,631 loyalty program members into seven distinct consumer segments based on behavioural and sociodemographic attributes. The findings reveal significant heterogeneity in consumer behaviour, emphasizing the impact of urban geography on shopping decisions. This segmentation also provides valuable insights for retailers optimizing store locations and marketing strategies and for policymakers aiming to enhance urban accessibility. Additionally, our approach strengthens agent-based model (ABM) simulations by incorporating demographic and behavioural diversity, leading to more realistic consumer representations. While integrating loyalty data with synthetic populations mitigates privacy concerns, challenges remain regarding data sparsity and demographic inconsistencies. Future research should explore multi-source data integration and advanced clustering methods. Overall, this study contributes to geographically explicit modelling, demonstrating the effectiveness of combining behavioural and synthetic demographic data in urban retail analysis.

  PublisherOA PDFDOI

• Urban Air Mobility Research Challenges and Opportunities

  Annual Review of Control Robotics and Autonomous Systems · 2025-01-02 · 21 citations

  articleOpen access1st authorCorresponding

  This article reviews the literature on urban air mobility (UAM), examining both the research challenges it presents and the transformative opportunities that make these challenges worth addressing. While UAM has historical precedents, the current iteration is born of novel aircraft technology, primarily electric vertical takeoff and landing (eVTOL) and electric short takeoff and landing (eSTOL) aircraft. These advances raise new questions in aerodynamics, control, and integration with urban infrastructure. We explore several key research areas, including aircraft design, vertiport development, network planning, and air traffic management. We also address the scalability challenges in air traffic management for high-density UAM operations and the potential of autonomous and remotely piloted systems. If new aircraft are to birth a new urbanism, they will do so by integrating aircraft engineering and computational intelligence in control, systems, robotics, and human factors.

  PublisherDOI

• Spatial bias in placement of citizen and conventional weather stations and their impact on urban climate research: A case study of the Urban Heat Island effect in Canada

  Urban Climate · 2025-01-07 · 9 citations

  articleOpen accessSenior authorCorresponding

  Citizen Weather Stations (CWS) are a source of Crowdsourced Geographic Information for urban climate research, which can provide extensive datasets in areas where data are scarce or unavailable. In this article, we explore the efficacy of using meteorological data from CWS in studying the Urban Heat Island (UHI) effect across Canada during late spring and summer of 2022. In particular, we evaluate the distribution of CWS before relying on them for UHI intensity estimates, since potential spatial biases in placement of these sensors can greatly affect canopy-level measurements. We compared the spatial distribution of Netatmo CWS with conventional weather stations from Environment and Climate Change Canada (ECCC), and found that ECCC sensors are more numerous in rural areas, while Netatmo sensors are present in greater numbers in urban areas. We then computed UHI intensity using urban temperature from Netatmo sensors and peri-urban temperature from ECCC sensors. The resulting intensity values were higher than those estimated using either the Netatmo or the ECCC sensors individually, thus highlighting the influence of sensor distribution in estimating UHI magnitude. Overall, our research explores the distribution of both ECCC and CWS sensors, and highlights their potential complementarity in urban climate research. • Citizen weather stations (CWS) are located largely in Census Metropolitan Areas (CMAs), surrounded mostly by built-up areas • Conventional weather stations are more distributed in rural areas, and are mostly surrounded by vegetation and water • Overall quantity of CWS increases with population • Spatial distribution of CWS and conventional sensors is complementary

  PublisherDOI

• SynthEco: An open-source Python application for the generation of a multi-scale digital ecosystem anchored in synthetic populations

  2025-07-18

  articleOpen access

  Synthetic populations (SPs) are a special kind of synthetic datasets that are statistical representations of a population at a given geo-spatial granularity, created using individual/household and aggregated census data. The SynthEco project aims to provide a platform for researchers to create a basic SP using an open-source Python package. The basic SP is then enriched by combination with (1) other datasets that capture the many dimensions of individual/household characteristics and real-world behaviors (creating what we call mosaic agents) and (2) with real-world behavioral data for spatially and/or temporally explicit characterization of the environment in which agents evolve for analytics and/or simulations combining individual and environmental characteristics. This package allows for SP creation from any census data and on different geographic granularities and jurisdictions through a simple plug-in system enabling enrichment into multiscale digital ecosystems. The use of SynthEco is illustrated in two use cases.

  PublisherDOI

Recent grants

• CPS: Medium: Making Cloud Computing Sense, Act, and Move (SAM)

  NSF · $1.1M · 2011–2016

Frequent coauthors

• Colin A. Chapman

  George Washington University

  40 shared

• Sivakumar Rathinam

  Texas A&M University

  31 shared

• A Zaroliagis

  Cornell University

  25 shared

• Monika Verma

  Indian Institute of Technology Bhilai

  25 shared

• U Ramos

  Indian Institute of Science Bangalore

  25 shared

• Ramani Kannan

  Universiti Teknologi Petronas

  25 shared

• R. Balasubramanian

  25 shared

• Jean-Pierre Jouannaud

  25 shared

Education

• Ph.D., EECS

  University of Michigan

Awards & honors

• USDOT's Connected Vehicle Technology award 2011
• UC Berkeley's Energy and Climate Lectures Innovation Award 2…