Portfolio
A collection of my professional and research work in AI, machine learning, geospatial analysis, and infrastructure analytics.
Current Work
GeoTasker.ai
AI-powered geospatial storytelling platform. Describe any topic and get a narrated video with maps, animations, data visualizations, and background music. Built with Claude AI, Next.js, FastAPI, and GPU-accelerated rendering.
GeoManim
Python library for creating animated geospatial visualizations using Manim. One-line API for animated maps, choropleths, route animations, and more. Install from GitHub: pip install git+https://github.com/Kamol-Roy/geomanim
Professional Work
Infrastructure Analytics & AI
Geospatial analytics and AI solutions for transportation and infrastructure projects across North America, Saudi Arabia, Central Asia, and Africa. Freight network analysis, travel time reliability, and infrastructure monitoring using large-scale GPS datasets (NPMRDS, INRIX, ATRI).
Built custom Python and Plotly Dash tools for spatial visualization and routing. Led AI-assisted mapping workflows for power and transport infrastructure. Now serving as technical lead for AI and automation initiatives.
Funded Research Projects
Disruption Identification and Dynamic Mapping During Disasters
2020Developed document classification and deep learning models to identify infrastructure disruptions during disasters using streaming Twitter data. Funded by the National Science Foundation (NSF) ORDER-CRISP project.
Modeling the Dynamics of Hurricane Evacuation
2019Built Hidden Markov Models and activity classification systems to understand evacuation behavior patterns using Twitter data, demographic information, and hurricane data. Funded by the Southeast Transportation Center.
Quantifying Human Mobility Resilience
2019Developed a novel approach to detect events and measure resilience using geo-tagged Twitter data. Published in EPJ Data Science.
Real-Time Traffic Information Sharing via Twitter
2019Analyzed the effectiveness and information content of FDOT Twitter accounts for sharing traffic information. Applied topic modeling and logit models. Funded by Florida DOT.
Social Media Crisis Communication During Hurricane Sandy
2020Analyzed the efficiency of social media-based crisis communication using entropy analysis, logit models, and regression analysis. Published in the International Journal of Information Management.
Hurricane Evacuation Traffic Demand Prediction
2017Integrated multiple data sources (geo-tagged Twitter, traffic sensors, socio-demographic data) to predict evacuation traffic using LSTM models.
Agent-Based Modeling for Human Behavior and Infrastructure Disruption
2020Developed agent-based simulations to understand the interaction between human behavior and infrastructure during disasters. Funded by NSF ORDER-CRISP.
Risk Perception and Evacuation Decision Modeling
2020Built agent-based models to understand how multiple information sources influence risk perception and evacuation decisions during disasters.
COVID-19 Projects
COVID-19 Spatio-temporal Comparison Visualization
2020Built a live interactive map to visualize and compare COVID-19 cases and deaths across regions using Johns Hopkins University data.
COVID-19 Temporal Visualization by County
2020Created temporal visualizations showing the spread of COVID-19 across US counties using New York Times data and county shapefiles.
COVID-19 ABM for Los Angeles Reopening
2020Developed high fidelity location-based risk estimates using agent-based modeling for the LA COVID-19 Data Science Challenge.
Data Challenge Competition Platform
2020Built a web platform for hosting data science competitions with submission and scoring capabilities.
Collaboration Projects
Dynamics of Social Media Communication in Major Hurricanes
2019Applied dynamic topic modeling to understand how social media communication evolves during major hurricanes. Collaboration with N-HIRS at Florida International University.
Information Diffusion and Evacuation Decision Modeling
2019Developed contagion models (SIS/SIR) to understand how information spreads and influences evacuation decisions during disasters.
Individual & Challenge Projects
Traffic Intersection Simulation with VISSIM
2015Modeled traffic operations at complex intersections using PTV VISSIM microsimulation to analyze feasible traffic operation alternatives.
Climate Stress Impact on Human Mobility
2017Analyzed mobile phone data to understand the impact of climate stress on human mobility and resilience. Honorable Mention at UN Global Pulse Data for Climate Action Challenge.
Bicycle Crash Prediction with Machine Learning
2017Built machine learning models to predict bicycle crashes using Capital Bikeshare and climate data. First Prize at NSF Big Data Innovation Hub Transportation Data Challenge.