R Sengupta
Biographic Data
| ID | 48025 |
|---|---|
| NAME | R Sengupta |
| GIVEN NAMES | R |
| FAMILY NAME | Sengupta |
| SIGNATURE | SENGUPTA R |
| AFFILIATIONS | McGill University |
| ORCID | 0000-0003-4914-5844 |
| VERIFIED | Yes |
| TOTAL WORKS | 14 |
| TOTAL CITATIONS | 4 |
| AUTHOR COUNT | 14 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2004 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 1 |
Bridging data and adaptation in agent-based modelling
Agent-based models (ABMs) are powerful tools for simulating complex socioeconomic systems. Reinforcement learning (RL), especially online RL, is increasingly used to model agent behaviour, allowing agents to explore and learn optimal actions from the model environment. However, standard online RL approaches learn from scratch and often fail to incorporate valuable real-world data. Further, while purely offline RL can use this data, it does not ad…
Quantitative and Spatially Explicit Clustering of Urban Grocery Shoppers in Montreal
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 a…
Tracking the state and behavior of people in response to Covid-19 through the fusion of multiple longitudinal data streams
Agent-Based Modeling of Covid-19 Transmission
The differential transmission of COVID-19 depending on the socio-economic status of a neighborhood is well established. For example, several studies have shown that COVID-19 transmission was higher in poorer and denser neighborhoods than in wealthier ones. However, what is less well known is how this varied rate of transmission interacted with established health measures, i.e., face masks and lockdowns, in the context of developing countries to r…
Impacts of Covid-19 on Biodiversity Conservation and Community Networks at Kibale National Park, Uganda
Conservation, like all aspects of society, was severely affected by the COVID-19 pandemic. Although there have been projections and speculations about impacts on conservation plans and actions, data about the extent of these impacts are sparse. We contribute evidence from a research field site in Kibale National Park, Uganda. Our analysis shows that many of the fears concerning the negative conservation impacts of COVID-19 were borne out. Long-te…
A 3D agent-based model for simulating urban densification in Toronto, Canada
The use of land parcel data, 3D visualisation and urban theories offers a significant opportunity for advancing simulations of urban densification. This paper presents a 3D agent-based model (ABM) to explore future urban densification dynamics in Toronto based on stakeholder behaviour and interactions, the impact of zoning regulations, and profit expectations. The ABM establishes residents, developers, landowners, and the local zoning authority a…
Big Data (R)evolution in Geography
The use of data and statistics along with computational systems heralded the beginning of a quantitative revolution in Geography. Use of simulation models (Cellular Automata and Agent-Based Models) followed in the late 1990s, with ontology and epistemology of complexity theory and modelling being defined a little less than two decades ago. We are, however, entering a new era where sensors regularly collect and update large amounts of spatio-tempo…
Evacuation Simulation Implemented by ABM-BIM of Unity in Students’ Dormitory Based on Delay Time
China’s university dormitories have high population densities, which can result in a large number of casualties because of crowding and stampedes during emergency evacuations. It is therefore important to plan properly for evacuations by mitigating the effect of choke points that create backlogs ahead of time. Accurate computer representations of the structure of a building and behavior of the evacuees are two important factors to obtain accurate…
A Sensor Placement Strategy for Comprehensive Urban Heat Island Monitoring
Urban heat islands (UHIs) increase the energy consumption of cities and impact the health of its residents. In light of the correlation between energy consumption and health and UHI variations observed at a local level within the canopy layer, satellite-derived land surface temperatures (LSTs) may be insufficient to provide comprehensive information about these deleterious effects. For both LST and air temperatures to be collected in a spatially …
Montreal's environmental justice problem with respect to the urban heat island phenomenon
Due to climate change, heat events in Canada have become more extreme in intensity and frequency and will continue to do so according to the Intergovernmental Panel on Climate Change's global predictions. Environmental justice research has indicated that extreme heat exposure disproportionally affects socio‐economically disadvantaged populations in cities. The objective of this research was to determine whether such a phenomenon exists in Montrea…
The San Francisco Travel Quality Study
Spatial and temporal patterns in primary school enrolment and exam achievement in Rural Uganda
Using a mixed-methods approach, including qualitative, quantitative and Geographic Information Science methods, we assessed the primary school landscape around a protected area in Western Uganda. Data from a household survey, interviews and standardized school examinations were mapped to visualize spatial patterns in enrolment and academic achievement. We found children on average were starting school at age nine, but started to dropout as early …
Countering elephant raiding with Short Message Service
Key Messages This paper explores whether traditional crisis mapping systems can be used to tackle the perennial livelihood problem of elephant raiding around Kibale National Park, Uganda. The goal of the system described in this paper is to streamline the process of reporting elephant raiding to forest officials so that park services can be effectively deployed. The challenges and considerations of deploying such a system in an environment where …
Development and Comparison of Approaches for Automated Mapping of Stream Channel Networks
Accurate mapping of stream channel networks is important for measuring hydrologic parameters, for site planning in construction projects, and for use in hydrologic models. This article compares five existing and two new methods for extracting stream channel networks for use in topographic mapping. In order of increasing accuracy, these methods are: (1) blue lines on USGS 1:24,000 topographic maps (64.6 percent underrepresentation), (2) placing st…
Montreal's environmental justice problem with respect to the urban heat island phenomenon
Due to climate change, heat events in Canada have become more extreme in intensity and frequency and will continue to do so according to the Intergovernmental Panel on Climate Change's global predictions. Environmental justice research has indicated that extreme heat exposure disproportionally affects socio‐economically disadvantaged populations in cities. The objective of this research was to determine whether such a phenomenon exists in Montrea…
Spatial and temporal patterns in primary school enrolment and exam achievement in Rural Uganda
Using a mixed-methods approach, including qualitative, quantitative and Geographic Information Science methods, we assessed the primary school landscape around a protected area in Western Uganda. Data from a household survey, interviews and standardized school examinations were mapped to visualize spatial patterns in enrolment and academic achievement. We found children on average were starting school at age nine, but started to dropout as early …
Development and Comparison of Approaches for Automated Mapping of Stream Channel Networks
Accurate mapping of stream channel networks is important for measuring hydrologic parameters, for site planning in construction projects, and for use in hydrologic models. This article compares five existing and two new methods for extracting stream channel networks for use in topographic mapping. In order of increasing accuracy, these methods are: (1) blue lines on USGS 1:24,000 topographic maps (64.6 percent underrepresentation), (2) placing st…
Development and Comparison of Approaches for Automated Mapping of Stream Channel Networks
Accurate mapping of stream channel networks is important for measuring hydrologic parameters, for site planning in construction projects, and for use in hydrologic models. This article compares five existing and two new methods for extracting stream channel networks for use in topographic mapping. In order of increasing accuracy, these methods are: (1) blue lines on USGS 1:24,000 topographic maps (64.6 percent underrepresentation), (2) placing st…
Spatial and temporal patterns in primary school enrolment and exam achievement in Rural Uganda
Using a mixed-methods approach, including qualitative, quantitative and Geographic Information Science methods, we assessed the primary school landscape around a protected area in Western Uganda. Data from a household survey, interviews and standardized school examinations were mapped to visualize spatial patterns in enrolment and academic achievement. We found children on average were starting school at age nine, but started to dropout as early …
Countering elephant raiding with Short Message Service
Key Messages This paper explores whether traditional crisis mapping systems can be used to tackle the perennial livelihood problem of elephant raiding around Kibale National Park, Uganda. The goal of the system described in this paper is to streamline the process of reporting elephant raiding to forest officials so that park services can be effectively deployed. The challenges and considerations of deploying such a system in an environment where …
The San Francisco Travel Quality Study
A Sensor Placement Strategy for Comprehensive Urban Heat Island Monitoring
Urban heat islands (UHIs) increase the energy consumption of cities and impact the health of its residents. In light of the correlation between energy consumption and health and UHI variations observed at a local level within the canopy layer, satellite-derived land surface temperatures (LSTs) may be insufficient to provide comprehensive information about these deleterious effects. For both LST and air temperatures to be collected in a spatially …
Montreal's environmental justice problem with respect to the urban heat island phenomenon
Due to climate change, heat events in Canada have become more extreme in intensity and frequency and will continue to do so according to the Intergovernmental Panel on Climate Change's global predictions. Environmental justice research has indicated that extreme heat exposure disproportionally affects socio‐economically disadvantaged populations in cities. The objective of this research was to determine whether such a phenomenon exists in Montrea…
Evacuation Simulation Implemented by ABM-BIM of Unity in Students’ Dormitory Based on Delay Time
China’s university dormitories have high population densities, which can result in a large number of casualties because of crowding and stampedes during emergency evacuations. It is therefore important to plan properly for evacuations by mitigating the effect of choke points that create backlogs ahead of time. Accurate computer representations of the structure of a building and behavior of the evacuees are two important factors to obtain accurate…
Agent-Based Modeling of Covid-19 Transmission
The differential transmission of COVID-19 depending on the socio-economic status of a neighborhood is well established. For example, several studies have shown that COVID-19 transmission was higher in poorer and denser neighborhoods than in wealthier ones. However, what is less well known is how this varied rate of transmission interacted with established health measures, i.e., face masks and lockdowns, in the context of developing countries to r…
Impacts of Covid-19 on Biodiversity Conservation and Community Networks at Kibale National Park, Uganda
Conservation, like all aspects of society, was severely affected by the COVID-19 pandemic. Although there have been projections and speculations about impacts on conservation plans and actions, data about the extent of these impacts are sparse. We contribute evidence from a research field site in Kibale National Park, Uganda. Our analysis shows that many of the fears concerning the negative conservation impacts of COVID-19 were borne out. Long-te…
A 3D agent-based model for simulating urban densification in Toronto, Canada
The use of land parcel data, 3D visualisation and urban theories offers a significant opportunity for advancing simulations of urban densification. This paper presents a 3D agent-based model (ABM) to explore future urban densification dynamics in Toronto based on stakeholder behaviour and interactions, the impact of zoning regulations, and profit expectations. The ABM establishes residents, developers, landowners, and the local zoning authority a…
Big Data (R)evolution in Geography
The use of data and statistics along with computational systems heralded the beginning of a quantitative revolution in Geography. Use of simulation models (Cellular Automata and Agent-Based Models) followed in the late 1990s, with ontology and epistemology of complexity theory and modelling being defined a little less than two decades ago. We are, however, entering a new era where sensors regularly collect and update large amounts of spatio-tempo…
Quantitative and Spatially Explicit Clustering of Urban Grocery Shoppers in Montreal
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 a…
Tracking the state and behavior of people in response to Covid-19 through the fusion of multiple longitudinal data streams
Bridging data and adaptation in agent-based modelling
Agent-based models (ABMs) are powerful tools for simulating complex socioeconomic systems. Reinforcement learning (RL), especially online RL, is increasingly used to model agent behaviour, allowing agents to explore and learn optimal actions from the model environment. However, standard online RL approaches learn from scratch and often fail to incorporate valuable real-world data. Further, while purely offline RL can use this data, it does not ad…
Geography (11 works) · Computer Science (8 works) · Business (3 works) · COVID-19 epidemiological studies (3 works) · Economics (3 works) · Engineering (3 works) · Environmental Science (3 works) · Human Mobility and Location-Based Analysis (3 works) · Marketing (3 works) · Medicine (3 works)