Avipsa Roy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Avipsa Roy has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Mankin Law
3 shared publications- Trisalyn A. Nelson
University of California Santa Barbara
2 shared publications Ahmad A. Tavakoly
Army Research Lab., Adelphi, MD (United States)
1 shared publication- Alexander Stewart Fotheringham
School of Geographical Sciences and Urban Planning, Arizona State University, Tempe, USA
1 shared publication Bandana Kar
Built Environment Characterization Group, Oak Ridge National Laboratory, Oak Ridge, TN, USA
1 shared publication- Cathy Jean Wilson
Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, NM, USA
1 shared publication
Latest Publications
- Open Access
- 17 July 2024
- Published by Elsevier in Applied Geography
- Vol. 169
Understanding the effects of socioeconomic factors on housing price appreciation using explainable AI
- 17 July 2024
- Published by Elsevier in Applied Geography
- Vol. 169
Open AccessUnderstanding the effects of socioeconomic factors on housing price appreciation using explainable AI
- Open Access
- 10 January 2023
- Published by Elsevier in Transportation Research Interdisciplinary Perspectives
- Vol. 17
Functional data analysis approach for mapping change in time series: A case study using bicycle ridership patterns
- 10 January 2023
- Published by Elsevier in Transportation Research Interdisciplinary Perspectives
- Vol. 17
Open AccessFunctional data analysis approach for mapping change in time series: A case study using bicycle ridership patterns
- Top Cited PapersOpen Access
- 1 June 2022
- Published by Elsevier in Sustainable Cities and Society
- Vol. 83
Examining spatial disparities in electric vehicle charging station placements using machine learning
- 1 June 2022
- Published by Elsevier in Sustainable Cities and Society
- Vol. 83
Top Cited PapersOpen AccessExamining spatial disparities in electric vehicle charging station placements using machine learning
- Open Access
- 22 February 2022
- Published by Center for Open Science in SocArXiv
Examining spatial disparities in electric vehicle charging station placements using machine learning
Electric vehicles (EV) are an emerging mode of transportation that has the potential to reshape thetransportation sector by significantly reducing carbon emissions thereby promoting a cleaner environment and pushing the boundaries of climate progress. Nevertheless, there remain significant hurdles to the widespread adoption of electric vehicles in the United States ranging from the high cost of EVs to the inequitable placement of EV charging stations (EVCS). A deeper understanding of the underlying complex interactions of social, economic, and demographic factors which may lead to such emerging disparities in EVCS placements is, therefore, necessary to mitigate accessibility issues and improve EV usage among people of all ages and abilities. In this study, we develop a machine learning framework to examine spatial disparities in EVCS placements by using a predictive approach. We first identify the essential socioeconomic factors that may contribute to spatial disparities in EVCS access. Second, using these factors along with ground truth data from existing EVCS placements we predict future ECVS density at multiple spatial scales using machine learning algorithms and compare their predictive accuracy to identify the most optimal spatial resolution for our predictions. Finally, we compare the most accurately predicted EVCS placement density with a spatial inequity indicator to quantify how equitably these placements would be for Orange County, California. Our method achieved the highest predictive accuracy (94.9%) of EVCS placement density at a spatial resolution of 3 km using Random Forests. Our results indicate that a total of 74.18% of predicted EVCS placements in Orange County will lie within a low spatial equity zone – indicating populations with the lowest accessibility may require the highest investments in EVCS placements. Within the low spatial equity areas, 14.86% of the area will have a low density of predicted EVCS placements, 50.32% will have a medium density of predicted EVCS placement, and only 9% tend to have high EVCS placements. The findings from this study highlight a generalizable framework to quantify inequities in EVCS placements that will enable policymakers to identify underserved communities and facilitate targeted infrastructure investments for widespread EV usage and adoption for all.
- 22 February 2022
- Published by Center for Open Science in SocArXiv
Open AccessExamining spatial disparities in electric vehicle charging station placements using machine learning
Electric vehicles (EV) are an emerging mode of transportation that has the potential to reshape thetransportation sector by significantly reducing carbon emissions thereby promoting a cleaner environment and pushing the boundaries of climate progress. Nevertheless, there remain significant hurdles to the widespread adoption of electric vehicles in the United States ranging from the high cost of EVs to the inequitable placement of EV charging stations (EVCS). A deeper understanding of the underlying complex interactions of social, economic, and demographic factors which may lead to such emerging disparities in EVCS placements is, therefore, necessary to mitigate accessibility issues and improve EV usage among people of all ages and abilities. In this study, we develop a machine learning framework to examine spatial disparities in EVCS placements by using a predictive approach. We first identify the essential socioeconomic factors that may contribute to spatial disparities in EVCS access. Second, using these factors along with ground truth data from existing EVCS placements we predict future ECVS density at multiple spatial scales using machine learning algorithms and compare their predictive accuracy to identify the most optimal spatial resolution for our predictions. Finally, we compare the most accurately predicted EVCS placement density with a spatial inequity indicator to quantify how equitably these placements would be for Orange County, California. Our method achieved the highest predictive accuracy (94.9%) of EVCS placement density at a spatial resolution of 3 km using Random Forests. Our results indicate that a total of 74.18% of predicted EVCS placements in Orange County will lie within a low spatial equity zone – indicating populations with the lowest accessibility may require the highest investments in EVCS placements. Within the low spatial equity areas, 14.86% of the area will have a low density of predicted EVCS placements, 50.32% will have a medium density of predicted EVCS placement, and only 9% tend to have high EVCS placements. The findings from this study highlight a generalizable framework to quantify inequities in EVCS placements that will enable policymakers to identify underserved communities and facilitate targeted infrastructure investments for widespread EV usage and adoption for all.
- Open Access
- 24 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Joint segmentation of aerial UAV and LiDAR images using Bayesian Non-Parametric clustering
Recent advances in high resolution geographic data collection platforms such as Unmanned Aerial Vehicles (UAVs) have rapidly changed the way we visualize spatial information. Integrating different modalities collected by UAV can be used to indicate the state of facility operations by providing environmental context about the surroundings. However, performing image segmentation combining features from multiple sensors situated on a UAV is challenging owing to the huge volume of data, lack of co-orientation among sensors and variability in their spatial and temporal resolution. In this study, we provide a novel framework to perform image segmentation on fused LiDAR and aerial imagery data from unlabeled images using a Bayesian non-parametric clustering approach.
- 24 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessJoint segmentation of aerial UAV and LiDAR images using Bayesian Non-Parametric clustering
Recent advances in high resolution geographic data collection platforms such as Unmanned Aerial Vehicles (UAVs) have rapidly changed the way we visualize spatial information. Integrating different modalities collected by UAV can be used to indicate the state of facility operations by providing environmental context about the surroundings. However, performing image segmentation combining features from multiple sensors situated on a UAV is challenging owing to the huge volume of data, lack of co-orientation among sensors and variability in their spatial and temporal resolution. In this study, we provide a novel framework to perform image segmentation on fused LiDAR and aerial imagery data from unlabeled images using a Bayesian non-parametric clustering approach.
- Open Access
- 10 January 2022
- Published by Elsevier in Journal of Transport & Health
- Vol. 24, 101331
A multicriteria decision analysis framework to measure equitable healthcare access during COVID-19
- 10 January 2022
- Published by Elsevier in Journal of Transport & Health
- Vol. 24, 101331
Open AccessA multicriteria decision analysis framework to measure equitable healthcare access during COVID-19
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Examining Spatial Disparities in Electric Vehicle Charging Station Placements Using Machine Learning
Electric vehicles (EV) are an emerging mode of transportation that has the potential to reshape the transportation sector by significantly reducing carbon emissions thereby promoting a cleaner environment and pushing the boundaries of climate progress. A deeper understanding of the underlying complex interactions of socioeconomic factors which may lead to such emerging disparities in EVCS access among people of all ages and abilities. In this study, we develop a machine learning framework to examine spatial disparities in EVCS placements by using a predictive approach and use decision analysis to generate an equity indicator to compare placement coverage in Orange County, California. Our method achieved the highest predictive accuracy (94.9%) of EVCS placement density at a spatial resolution of 3 km using Random Forests. with a total of 74.18% of predicted EVCS placements within areas of high spatial inequality– and 50.32% with a medium density of future EVCS placements. Our framework is generalizable and can help policymakers to identify underserved communities to facilitate targeted infrastructure investments for widespread EV usage and adoption for all.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessExamining Spatial Disparities in Electric Vehicle Charging Station Placements Using Machine Learning
Electric vehicles (EV) are an emerging mode of transportation that has the potential to reshape the transportation sector by significantly reducing carbon emissions thereby promoting a cleaner environment and pushing the boundaries of climate progress. A deeper understanding of the underlying complex interactions of socioeconomic factors which may lead to such emerging disparities in EVCS access among people of all ages and abilities. In this study, we develop a machine learning framework to examine spatial disparities in EVCS placements by using a predictive approach and use decision analysis to generate an equity indicator to compare placement coverage in Orange County, California. Our method achieved the highest predictive accuracy (94.9%) of EVCS placement density at a spatial resolution of 3 km using Random Forests. with a total of 74.18% of predicted EVCS placements within areas of high spatial inequality– and 50.32% with a medium density of future EVCS placements. Our framework is generalizable and can help policymakers to identify underserved communities to facilitate targeted infrastructure investments for widespread EV usage and adoption for all.
- Open Access
- 1 September 2020
- Published by Network Design Lab - Transport Findings in Findings
- p. 14520
Classifying Transport Mode from Global Positioning Systems and Accelerometer Data: A Machine Learning Approach
Smartphones and wearable devices are driving a boom in mobility data. We use data-driven tools for classifying movement data into five different travel modes (bicycle, walk, bus, motor vehicle and SkyTrain) in Vancouver and St. John’s, Canada. Using data from a GPS-enabled smartphone app (Itinerum) combined with a wrist-worn accelerometer (GENEActiv) collected over a period of 67 days, we classified modes using Support Vector Machines from 4071 trips. Pre-labelled data were used to classify modes with 90.9% accuracy when data from both devices were combined in comparison to a single data source with accuracy ranging between 55.5% and 79.4%.
- 1 September 2020
- Published by Network Design Lab - Transport Findings in Findings
- p. 14520
Open AccessClassifying Transport Mode from Global Positioning Systems and Accelerometer Data: A Machine Learning Approach
Smartphones and wearable devices are driving a boom in mobility data. We use data-driven tools for classifying movement data into five different travel modes (bicycle, walk, bus, motor vehicle and SkyTrain) in Vancouver and St. John’s, Canada. Using data from a GPS-enabled smartphone app (Itinerum) combined with a wrist-worn accelerometer (GENEActiv) collected over a period of 67 days, we classified modes using Support Vector Machines from 4071 trips. Pre-labelled data were used to classify modes with 90.9% accuracy when data from both devices were combined in comparison to a single data source with accuracy ranging between 55.5% and 79.4%.
- 21 August 2019
- Published by Office of Scientific and Technical Information (OSTI)
Climate variability and fill rate impacts on downstream flows from the Grand Ethiopian Renaissance Dam [Sheets]
The U.S. Department of Energy's Office of Scientific and Technical Information
- 21 August 2019
- Published by Office of Scientific and Technical Information (OSTI)
Climate variability and fill rate impacts on downstream flows from the Grand Ethiopian Renaissance Dam [Sheets]
The U.S. Department of Energy's Office of Scientific and Technical Information
- Open Access
- 4 June 2019
- Published by MDPI AG in Urban Science
- Vol. 3 (2) , 62
Correcting Bias in Crowdsourced Data to Map Bicycle Ridership of All Bicyclists
Traditional methods of counting bicyclists are resource-intensive and generate data with sparse spatial and temporal detail. Previous research suggests big data from crowdsourced fitness apps offer a new source of bicycling data with high spatial and temporal resolution. However, crowdsourced bicycling data are biased as they oversample recreational riders. Our goals are to quantify geographical variables, which can help in correcting bias in crowdsourced, data and to develop a generalized method to correct bias in big crowdsourced data on bicycle ridership in different settings in order to generate maps for cities representative of all bicyclists at a street-level spatial resolution. We used street-level ridership data for 2016 from a crowdsourced fitness app (Strava), geographical covariate data, and official counts from 44 locations across Maricopa County, Arizona, USA (training data); and 60 locations from the city of Tempe, within Maricopa (test data). First, we quantified the relationship between Strava and official ridership data volumes. Second, we used a multi-step approach with variable selection using LASSO followed by Poisson regression to integrate geographical covariates, Strava, and training data to correct bias. Finally, we predicted bias-corrected average annual daily bicyclist counts for Tempe and evaluated the model’s accuracy using the test data. We found a correlation between the annual ridership data from Strava and official counts (R2 = 0.76) in Maricopa County for 2016. The significant variables for correcting bias were: The proportion of white population, median household income, traffic speed, distance to residential areas, and distance to green spaces. The model could correct bias in crowdsourced data from Strava in Tempe with 86% of road segments being predicted within a margin of ±100 average annual bicyclists. Our results indicate that it is possible to map ridership for cities at the street-level by correcting bias in crowdsourced bicycle ridership data, with access to adequate data from official count programs and geographical covariates at a comparable spatial and temporal resolution.
- 4 June 2019
- Published by MDPI AG in Urban Science
- Vol. 3 (2) , 62
Open AccessCorrecting Bias in Crowdsourced Data to Map Bicycle Ridership of All Bicyclists
Traditional methods of counting bicyclists are resource-intensive and generate data with sparse spatial and temporal detail. Previous research suggests big data from crowdsourced fitness apps offer a new source of bicycling data with high spatial and temporal resolution. However, crowdsourced bicycling data are biased as they oversample recreational riders. Our goals are to quantify geographical variables, which can help in correcting bias in crowdsourced, data and to develop a generalized method to correct bias in big crowdsourced data on bicycle ridership in different settings in order to generate maps for cities representative of all bicyclists at a street-level spatial resolution. We used street-level ridership data for 2016 from a crowdsourced fitness app (Strava), geographical covariate data, and official counts from 44 locations across Maricopa County, Arizona, USA (training data); and 60 locations from the city of Tempe, within Maricopa (test data). First, we quantified the relationship between Strava and official ridership data volumes. Second, we used a multi-step approach with variable selection using LASSO followed by Poisson regression to integrate geographical covariates, Strava, and training data to correct bias. Finally, we predicted bias-corrected average annual daily bicyclist counts for Tempe and evaluated the model’s accuracy using the test data. We found a correlation between the annual ridership data from Strava and official counts (R2 = 0.76) in Maricopa County for 2016. The significant variables for correcting bias were: The proportion of white population, median household income, traffic speed, distance to residential areas, and distance to green spaces. The model could correct bias in crowdsourced data from Strava in Tempe with 86% of road segments being predicted within a margin of ±100 average annual bicyclists. Our results indicate that it is possible to map ridership for cities at the street-level by correcting bias in crowdsourced bicycle ridership data, with access to adequate data from official count programs and geographical covariates at a comparable spatial and temporal resolution.