Rajat Verma
Research Subjects
Research Interests
Rajat Verma has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Satish V. Ukkusuri
Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, USA
6 shared publications Ramin Saedi
Department of Civil and Environmental Engineering, Michigan State University, East Lansing, MI
3 shared publicationsAli Zockaie
Department of Civil and Environmental Engineering, Michigan State University, East Lansing, MI
2 shared publicationsSatish V. Ukkusuri
2 shared publications- Zengxiang Lei
Purdue University
2 shared publications - Ali Zockaie
Michigan State University
1 shared publication
Latest Publications
- 1 January 2026
- Published by Purdue University Press
Simulating Current and Future EV Growth Scenarios in Indiana
As Indiana transitions toward electric mobility, data-driven planning is essential to guide electric vehicle (EV) charging infrastructure investment and deployment. This study evaluates the current and future performance of Indiana’s EV charging infrastructure using Multimodal Energy-Efficient Trip Simulation in Real Time (METS-R), a high-resolution simulation platform. Five EV adoption scenarios, ranging from pessimistic to optimistic, are modeled for the years 2024 through 2031, to assess spatial and temporal variations in public charging demand. Results reveal increasing public charging demand under high adoption scenarios, with significant disparities between urban and non-urban areas. Accessibility to public charging is found to be uneven across Indiana, with access to Direct Current Fast Charging (DCFC) more limited than to Level 2 (L2) chargers. Demand-to-supply analysis identifies Zip Code Tabulation Areas (ZCTAs) with high EV demand relative to accessible charging supply, highlighting priority areas for targeted deployment. Temporal variations in charging demand underscore the importance of time-of-day planning, while vehicle miles traveled (VMT) analysis highlights the dominant role of local roads usage in EV travel. Revenue projections indicate substantial market potential but also underscore the importance of strategic siting and accurate forecasting, with a median return on investment (ROI) of approximately 0.90 over an 8-year period. The estimated economic development impacts include approximately 2,000 jobs, $130 million in earnings, and $400 million in gross output. The study concludes with actionable recommendations for the Indiana Department of Transportation (INDOT) and stakeholders to guide EV infrastructure investment and deployment, including scenario-based planning, accessibility-informed location prioritization, and targeted deployment in areas with high demand-to-supply ratio.
- 1 January 2026
- Published by Purdue University Press
Simulating Current and Future EV Growth Scenarios in Indiana
As Indiana transitions toward electric mobility, data-driven planning is essential to guide electric vehicle (EV) charging infrastructure investment and deployment. This study evaluates the current and future performance of Indiana’s EV charging infrastructure using Multimodal Energy-Efficient Trip Simulation in Real Time (METS-R), a high-resolution simulation platform. Five EV adoption scenarios, ranging from pessimistic to optimistic, are modeled for the years 2024 through 2031, to assess spatial and temporal variations in public charging demand. Results reveal increasing public charging demand under high adoption scenarios, with significant disparities between urban and non-urban areas. Accessibility to public charging is found to be uneven across Indiana, with access to Direct Current Fast Charging (DCFC) more limited than to Level 2 (L2) chargers. Demand-to-supply analysis identifies Zip Code Tabulation Areas (ZCTAs) with high EV demand relative to accessible charging supply, highlighting priority areas for targeted deployment. Temporal variations in charging demand underscore the importance of time-of-day planning, while vehicle miles traveled (VMT) analysis highlights the dominant role of local roads usage in EV travel. Revenue projections indicate substantial market potential but also underscore the importance of strategic siting and accurate forecasting, with a median return on investment (ROI) of approximately 0.90 over an 8-year period. The estimated economic development impacts include approximately 2,000 jobs, $130 million in earnings, and $400 million in gross output. The study concludes with actionable recommendations for the Indiana Department of Transportation (INDOT) and stakeholders to guide EV infrastructure investment and deployment, including scenario-based planning, accessibility-informed location prioritization, and targeted deployment in areas with high demand-to-supply ratio.
- Open Access
- 15 July 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-13
Spatial Access of America: Multiple indicators of accessibility to opportunities
Spatial measures of accessibility are widely used in urban and transportation planning to understand the impact of the transportation system on influencing people’s access to places, but publicly available large-scale datasets are rare and limited. This paper presents a highly parametric dataset containing values of spatial accessibility measured by combinations of multiple metrics, travel modes, types of opportunity (including jobs and amenities like schools, hospitals, and electric vehicle charging stations), and travel time thresholds. This includes both cumulative opportunities types of measures as well as competition metrics. A total of 600 accessibility values are computed for each zone at three administrative levels for the 50 most populous urban areas of the United States. Additionally, the dataset also includes the travel time matrix files for each of these urban areas by three travel modes – driving, walking, and bicycling – to facilitate self-validation. Further, comparisons with similar travel time and accessibility datasets show a high degree of similarity with our dataset.
- 15 July 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-13
Open AccessSpatial Access of America: Multiple indicators of accessibility to opportunities
Spatial measures of accessibility are widely used in urban and transportation planning to understand the impact of the transportation system on influencing people’s access to places, but publicly available large-scale datasets are rare and limited. This paper presents a highly parametric dataset containing values of spatial accessibility measured by combinations of multiple metrics, travel modes, types of opportunity (including jobs and amenities like schools, hospitals, and electric vehicle charging stations), and travel time thresholds. This includes both cumulative opportunities types of measures as well as competition metrics. A total of 600 accessibility values are computed for each zone at three administrative levels for the 50 most populous urban areas of the United States. Additionally, the dataset also includes the travel time matrix files for each of these urban areas by three travel modes – driving, walking, and bicycling – to facilitate self-validation. Further, comparisons with similar travel time and accessibility datasets show a high degree of similarity with our dataset.
- 31 October 2024
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 114
Household evacuation decision making during simultaneous events: Hurricane Ida and the COVID-19 pandemic
- 31 October 2024
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 114
Household evacuation decision making during simultaneous events: Hurricane Ida and the COVID-19 pandemic
- Open Access
Long-term forecasts of statewide travel demand patterns using large-scale mobile phone GPS data: A case study of Indiana
The growth in availability of large-scale GPS mobility data from mobile devices has the potential to aid traditional travel demand models (TDMs) such as the four-step planning model, but those processing methods are not commonly used in practice. In this study, we show the application of trip generation and trip distribution modeling using GPS data from smartphones in the state of Indiana. This involves extracting trip segments from the data and inferring the phone users' home locations, adjusting for data representativeness, and using a data-driven travel time-based cost function for the trip distribution model. The trip generation and interchange patterns in the state are modeled for 2025, 2035, and 2045. Employment sectors like industry and retail are observed to influence trip making behavior more than other sectors. The travel growth is predicted to be mostly concentrated in the suburban regions, with a small decline in the urban cores. Further, although the majority of the growth in trip flows over the years is expected to come from the corridors between the major urban centers of the state, relative interzonal trip flow growth will likely be uniformly spread throughout the state. We also validate our results with the forecasts of two travel demand models, finding a difference of 5-15% in overall trip counts. Our GPS data-based demand model will contribute towards augmenting the conventional statewide travel demand model developed by the state and regional planning agencies.
Open AccessLong-term forecasts of statewide travel demand patterns using large-scale mobile phone GPS data: A case study of Indiana
The growth in availability of large-scale GPS mobility data from mobile devices has the potential to aid traditional travel demand models (TDMs) such as the four-step planning model, but those processing methods are not commonly used in practice. In this study, we show the application of trip generation and trip distribution modeling using GPS data from smartphones in the state of Indiana. This involves extracting trip segments from the data and inferring the phone users' home locations, adjusting for data representativeness, and using a data-driven travel time-based cost function for the trip distribution model. The trip generation and interchange patterns in the state are modeled for 2025, 2035, and 2045. Employment sectors like industry and retail are observed to influence trip making behavior more than other sectors. The travel growth is predicted to be mostly concentrated in the suburban regions, with a small decline in the urban cores. Further, although the majority of the growth in trip flows over the years is expected to come from the corridors between the major urban centers of the state, relative interzonal trip flow growth will likely be uniformly spread throughout the state. We also validate our results with the forecasts of two travel demand models, finding a difference of 5-15% in overall trip counts. Our GPS data-based demand model will contribute towards augmenting the conventional statewide travel demand model developed by the state and regional planning agencies.
- Open Access
- 16 January 2024
- Published by Springer Nature in EPJ Data Science
- Vol. 13 (1) , 1-22
Comparison of home detection algorithms using smartphone GPS data
Estimation of people’s home locations using location-based services data from smartphones is a common task in human mobility assessment. However, commonly used home detection algorithms (HDAs) are often arbitrary and unexamined. In this study, we review existing HDAs and examine five HDAs using eight high-quality mobile phone geolocation datasets. These include four commonly used HDAs as well as an HDA proposed in this work. To make quantitative comparisons, we propose three novel metrics to assess the quality of detected home locations and test them on eight datasets across four U.S. cities. We find that all three metrics show a consistent rank of HDAs’ performances, with the proposed HDA outperforming the others. We infer that the temporal and spatial continuity of the geolocation data points matters more than the overall size of the data for accurate home detection. We also find that HDAs with high (and similar) performance metrics tend to create results with better consistency and closer to common expectations. Further, the performance deteriorates with decreasing data quality of the devices, though the patterns of relative performance persist. Finally, we show how the differences in home detection can lead to substantial differences in subsequent inferences using two case studies—(i) hurricane evacuation estimation, and (ii) correlation of mobility patterns with socioeconomic status. Our work contributes to improving the transparency of large-scale human mobility assessment applications.
- 16 January 2024
- Published by Springer Nature in EPJ Data Science
- Vol. 13 (1) , 1-22
Open AccessComparison of home detection algorithms using smartphone GPS data
Estimation of people’s home locations using location-based services data from smartphones is a common task in human mobility assessment. However, commonly used home detection algorithms (HDAs) are often arbitrary and unexamined. In this study, we review existing HDAs and examine five HDAs using eight high-quality mobile phone geolocation datasets. These include four commonly used HDAs as well as an HDA proposed in this work. To make quantitative comparisons, we propose three novel metrics to assess the quality of detected home locations and test them on eight datasets across four U.S. cities. We find that all three metrics show a consistent rank of HDAs’ performances, with the proposed HDA outperforming the others. We infer that the temporal and spatial continuity of the geolocation data points matters more than the overall size of the data for accurate home detection. We also find that HDAs with high (and similar) performance metrics tend to create results with better consistency and closer to common expectations. Further, the performance deteriorates with decreasing data quality of the devices, though the patterns of relative performance persist. Finally, we show how the differences in home detection can lead to substantial differences in subsequent inferences using two case studies—(i) hurricane evacuation estimation, and (ii) correlation of mobility patterns with socioeconomic status. Our work contributes to improving the transparency of large-scale human mobility assessment applications.
- 27 November 2023
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (7) , 845-856
Crosswalk Detection from Satellite Imagery for Pedestrian Network Completion
Pedestrian network creation and completion for various tasks in transportation planning engineering generally requires laborious manual labeling of sidewalks and crosswalks. In this study, we employed the deep learning-based object detection model YOLO v5 for detecting crosswalks using Google Maps satellite imagery data of four North American cities. We also tested for two additional scenarios involving two image-processing techniques to exploit the special properties of crosswalks. Observations showed that the original images performed better than with binary thresholding and nearly the same even when noisy regions outside the right-of-way were removed. We proposed an algorithm to assign the detected crosswalks to intersection legs. We demonstrated the effectiveness of this technique for Washington, D.C. and Los Angeles, CA, showing classification accuracy rates of 71% and 89%, respectively. We also showed the influence of increasing distance threshold, a tolerance radius of prediction accuracy, in degrading the classification performance. This method, when combined with existing methods for sidewalk detection from aerial and street view images, could be reasonably used to help complete urban pedestrian networks in cities where high-resolution satellite images are available.
- 27 November 2023
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (7) , 845-856
Crosswalk Detection from Satellite Imagery for Pedestrian Network Completion
Pedestrian network creation and completion for various tasks in transportation planning engineering generally requires laborious manual labeling of sidewalks and crosswalks. In this study, we employed the deep learning-based object detection model YOLO v5 for detecting crosswalks using Google Maps satellite imagery data of four North American cities. We also tested for two additional scenarios involving two image-processing techniques to exploit the special properties of crosswalks. Observations showed that the original images performed better than with binary thresholding and nearly the same even when noisy regions outside the right-of-way were removed. We proposed an algorithm to assign the detected crosswalks to intersection legs. We demonstrated the effectiveness of this technique for Washington, D.C. and Los Angeles, CA, showing classification accuracy rates of 71% and 89%, respectively. We also showed the influence of increasing distance threshold, a tolerance radius of prediction accuracy, in degrading the classification performance. This method, when combined with existing methods for sidewalk detection from aerial and street view images, could be reasonably used to help complete urban pedestrian networks in cities where high-resolution satellite images are available.
- Open Access
- 19 August 2023
- Published by Springer Nature in npj Urban Sustainability
- Vol. 3 (1) , 1-10
A link criticality approach for pedestrian network design to promote walking
Measures of walkability generally do not provide a detailed quantitative assessment of pedestrian infrastructure development prioritization. In this study, a link-based composite measure of walkability and walking is introduced to overcome this limitation. This measure, called ‘pednet score’, is based on a weighted pedestrian network (‘pednet’) made of sidewalks and crosswalks whose edge weights are descriptive of their popularity. Edge popularity is derived from home-based walk trip assignments derived from simulated pedestrian demand. Properties of the pednet score are studied using three hypothetical variants of the pednet in three North American cities, each involving the addition of candidate sidewalk and/or crosswalk segments. It is shown that a strategic selection of these segments based on pednet score can substantially increase walking trips, in some cases up to 236%, and reduce current mean pedestrian trip distances by up to 340 m. A mixed development approach involving both sidewalks and crosswalks also shows considerably higher improvement than those segments considered alone. Results from marginal benefit curves strongly indicate the utility of the pednet score as a measure of link criticality for segment prioritization in pedestrian network design.
- 19 August 2023
- Published by Springer Nature in npj Urban Sustainability
- Vol. 3 (1) , 1-10
Open AccessA link criticality approach for pedestrian network design to promote walking
Measures of walkability generally do not provide a detailed quantitative assessment of pedestrian infrastructure development prioritization. In this study, a link-based composite measure of walkability and walking is introduced to overcome this limitation. This measure, called ‘pednet score’, is based on a weighted pedestrian network (‘pednet’) made of sidewalks and crosswalks whose edge weights are descriptive of their popularity. Edge popularity is derived from home-based walk trip assignments derived from simulated pedestrian demand. Properties of the pednet score are studied using three hypothetical variants of the pednet in three North American cities, each involving the addition of candidate sidewalk and/or crosswalk segments. It is shown that a strategic selection of these segments based on pednet score can substantially increase walking trips, in some cases up to 236%, and reduce current mean pedestrian trip distances by up to 340 m. A mixed development approach involving both sidewalks and crosswalks also shows considerably higher improvement than those segments considered alone. Results from marginal benefit curves strongly indicate the utility of the pednet score as a measure of link criticality for segment prioritization in pedestrian network design.
- Open Access
- 1 February 2023
- Published by Springer Nature in Research Square
A link criticality approach for pedestrian network design to promote walking
Measures of walkability generally do not provide a detailed quantitative assessment of pedestrian infrastructure development prioritization. In this study, a link-based composite measure of walkability and walking is introduced to overcome this limitation. This measure, called 'pednet score', is based on a weighted pedestrian network ('pednet') made of sidewalks and crosswalks whose edge weights are descriptive of their popularity. Edge popularity is derived from home-based walk trip assignment derived from simulated pedestrian demand. Properties of the pednet score are studied using three hypothetical variants of the pednet in three North American cities, each involving the addition of candidate sidewalk and/or crosswalk segments. It is shown that a strategic selection of these segments based on pednet score can substantially increase walking trips, in some cases up to 236%, and reduce current mean pedestrian trip distances by up to 340 m. A mixed development approach involving both sidewalks and crosswalks also shows considerably higher improvement than those segments considered alone. Results from marginal benefit curves strongly indicate the utility of the pednet score as a measure of link criticality for segment prioritization in pedestrian network design.
- 1 February 2023
- Published by Springer Nature in Research Square
Open AccessA link criticality approach for pedestrian network design to promote walking
Measures of walkability generally do not provide a detailed quantitative assessment of pedestrian infrastructure development prioritization. In this study, a link-based composite measure of walkability and walking is introduced to overcome this limitation. This measure, called 'pednet score', is based on a weighted pedestrian network ('pednet') made of sidewalks and crosswalks whose edge weights are descriptive of their popularity. Edge popularity is derived from home-based walk trip assignment derived from simulated pedestrian demand. Properties of the pednet score are studied using three hypothetical variants of the pednet in three North American cities, each involving the addition of candidate sidewalk and/or crosswalk segments. It is shown that a strategic selection of these segments based on pednet score can substantially increase walking trips, in some cases up to 236%, and reduce current mean pedestrian trip distances by up to 340 m. A mixed development approach involving both sidewalks and crosswalks also shows considerably higher improvement than those segments considered alone. Results from marginal benefit curves strongly indicate the utility of the pednet score as a measure of link criticality for segment prioritization in pedestrian network design.
- 16 April 2020
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2674 (5) , 70-84
Comparison of Support Vector and Non-Linear Regression Models for Estimating Large-Scale Vehicular Emissions, Incorporating Network-Wide Fundamental Diagram for Heterogeneous Vehicles
Estimation of vehicular emissions at network level is a prominent issue in transportation planning and management of urban areas. For large networks, macroscopic emission models are preferred because of their simplicity. However, these models do not consider traffic flow dynamics that significantly affect emissions production. This study proposes a network-level emission modeling framework based on the network-wide fundamental diagram (NFD), via integrating the NFD properties with an existing microscopic emission model. The NFD and microscopic emission models are estimated using microscopic and mesoscopic traffic simulation tools at different scales for various traffic compositions. The major contribution is to consider heterogeneous vehicle types with different emission generation rates in a network-level model. This framework is applied to the large-scale network of Chicago as well as its central business district. Non-linear and support vector regression models are developed using simulated trajectory data of 13 simulated scenarios. The results show a satisfactory calibration and successful validation with acceptable deviations from the underlying microscopic emissions model regardless of the simulation tool that is used to calibrate the network-level emissions model. The microscopic traffic simulation is appropriate for smaller networks, while mesoscopic traffic simulation is a proper means to calibrate models for larger networks. The proposed model is also used to demonstrate the relationship between macroscopic emissions and flow characteristics in the form of a network emissions diagram. The results of this study provide a tool for planners to analyze vehicular emissions in real time and find optimal policies to control the level of emissions in large cities.
- 16 April 2020
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2674 (5) , 70-84
Comparison of Support Vector and Non-Linear Regression Models for Estimating Large-Scale Vehicular Emissions, Incorporating Network-Wide Fundamental Diagram for Heterogeneous Vehicles
Estimation of vehicular emissions at network level is a prominent issue in transportation planning and management of urban areas. For large networks, macroscopic emission models are preferred because of their simplicity. However, these models do not consider traffic flow dynamics that significantly affect emissions production. This study proposes a network-level emission modeling framework based on the network-wide fundamental diagram (NFD), via integrating the NFD properties with an existing microscopic emission model. The NFD and microscopic emission models are estimated using microscopic and mesoscopic traffic simulation tools at different scales for various traffic compositions. The major contribution is to consider heterogeneous vehicle types with different emission generation rates in a network-level model. This framework is applied to the large-scale network of Chicago as well as its central business district. Non-linear and support vector regression models are developed using simulated trajectory data of 13 simulated scenarios. The results show a satisfactory calibration and successful validation with acceptable deviations from the underlying microscopic emissions model regardless of the simulation tool that is used to calibrate the network-level emissions model. The microscopic traffic simulation is appropriate for smaller networks, while mesoscopic traffic simulation is a proper means to calibrate models for larger networks. The proposed model is also used to demonstrate the relationship between macroscopic emissions and flow characteristics in the form of a network emissions diagram. The results of this study provide a tool for planners to analyze vehicular emissions in real time and find optimal policies to control the level of emissions in large cities.
- 20 May 2019
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2673 (10) , 394-404
Behavioral Analysis of Drivers Following Winter Maintenance Trucks Enabled with Collision Avoidance System
Winter maintenance trucks (WMTs) often operate at lower speeds during inclement weather and roadway conditions, creating potential safety issues for motorists following close behind. In this study, a new prototype radar-based rear-end collision avoidance and mitigation system (CAMS) was tested to assess its impact on the behavior of drivers following WMTs. The system is designed to flash an auxiliary rear-facing warning light upon detection of a vehicle encroaching within an unsafe relative headway with the rear of the WMT. A series of field evaluations was performed during actual winter maintenance operations to assess the effectiveness of the system compared with normal operating conditions (i.e., without the CAMS warning light) toward improving driver behavior related to rear-end crash risk. Specifically, two measures were assessed: (a) rate of vehicles encroaching beyond a safe time headway threshold to the rear of the WMT, and (b) the reaction–response time of drivers. Classification and regression tree models were created for identifying the relevant factors influential in determining the change in driver response. The results indicate that this warning light was effective in reducing the likelihood of the subject drivers crossing beyond a relative headway of 4.5 s. It was also effective in reducing the reaction and response times of the drivers by 0.83 and 0.55 s (36% and 20% reduction), respectively. Although the results were encouraging, additional field testing is recommended before conclusions are drawn regarding the traffic safety impacts of the system.
- 20 May 2019
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2673 (10) , 394-404
Behavioral Analysis of Drivers Following Winter Maintenance Trucks Enabled with Collision Avoidance System
Winter maintenance trucks (WMTs) often operate at lower speeds during inclement weather and roadway conditions, creating potential safety issues for motorists following close behind. In this study, a new prototype radar-based rear-end collision avoidance and mitigation system (CAMS) was tested to assess its impact on the behavior of drivers following WMTs. The system is designed to flash an auxiliary rear-facing warning light upon detection of a vehicle encroaching within an unsafe relative headway with the rear of the WMT. A series of field evaluations was performed during actual winter maintenance operations to assess the effectiveness of the system compared with normal operating conditions (i.e., without the CAMS warning light) toward improving driver behavior related to rear-end crash risk. Specifically, two measures were assessed: (a) rate of vehicles encroaching beyond a safe time headway threshold to the rear of the WMT, and (b) the reaction–response time of drivers. Classification and regression tree models were created for identifying the relevant factors influential in determining the change in driver response. The results indicate that this warning light was effective in reducing the likelihood of the subject drivers crossing beyond a relative headway of 4.5 s. It was also effective in reducing the reaction and response times of the drivers by 0.83 and 0.55 s (36% and 20% reduction), respectively. Although the results were encouraging, additional field testing is recommended before conclusions are drawn regarding the traffic safety impacts of the system.