Divya Natekar | Urban AI & Spatial Data Science

About

Bridging cities, data, and AI.

My work combines computational methods with urban planning questions, focusing on models that are not only predictive but also interpretable and useful for decision-making.

I am pursuing an MS in Urban Data Science at NYU’s Center for Urban Science + Progress. My work focuses on how AI, mobility data, geospatial analytics, and simulation models can help cities understand complex urban systems.

I have worked on retail mobility modeling for Downtown Brooklyn, wildfire risk prediction using satellite and wildfire datasets, and transient object removal from urban LiDAR point clouds.

I am especially interested in explainable urban AI, human mobility modeling, large language models for urban analytics, and applied geospatial machine learning.

Urban Simulation

Agent-based modeling, Huff models, multinomial logit, MCMC/HMC, and retail choice simulation.

Geospatial AI

Remote sensing, GIS, satellite data, wildfire risk prediction, and spatial visualization workflows.

3D Urban Data

LiDAR point-cloud processing, transient object filtering, and 3D urban model improvement.

Research

Selected research experience.

Projects grounded in real urban data, stakeholder problems, and applied AI/ML methods.

Sept 2025 – May 2026

Thinking on the Move: Agent-Based Retail Simulation for Downtown Brooklyn

NYU CUSP · Downtown Brooklyn Partnership

Developed a simulation framework for lunchtime retail mobility and restaurant choice behavior in Downtown Brooklyn, integrating spatial interaction models, LLM-derived restaurant attributes, mobility data, and POI datasets.

Built agent-based retail simulation logic for consumer choice and corridor-level retail analysis.
Integrated gravity-based modeling, multinomial logit thinking, and qualitative preference signals.
Supported stakeholder-oriented planning insights for retail corridors, anchor effects, and intervention scenarios.

Jun 2025 – Aug 2025

Transient Object Removal from Urban LiDAR Point Clouds

NYU CUSP Summer Guided Research · Mentor: Prof. Debra Laefer

Designed point-cloud filtering workflows to remove transient objects such as pedestrians and vehicles from urban LiDAR scans, improving the quality of 3D urban representations.

Worked with LiDAR point clouds, spatial filtering, and 3D urban modeling workflows.
Selected for the NYU Tandon CUSP Experiential Learning Scholarship.
Presented findings at BATWorks Climate Event and NYU CUSP Fall Research Showcase.

2026

Urban Wildfire Risk Prediction using Remote Sensing and Deep Learning

NYU CUSP · Urban AI

Developed an urban wildfire risk pipeline using MODIS satellite imagery, NASA FIRMS wildfire records, machine learning methods, and geospatial visualization outputs.

Built Python and Google Colab workflows for wildfire data processing and modeling.
Explored LoRA and PEFT concepts for parameter-efficient fine-tuning.
Generated spatial outputs for environmental risk assessment and urban AI communication.

Projects

Applied technical work.

A portfolio of modeling, machine learning, geospatial, cloud, and urban analytics projects.

Downtown Brooklyn Retail Mobility Model

Built traditional and simulation-based approaches for understanding restaurant choice behavior, including Huff models, multinomial logit, MCMC/HMC experiments, and agent-based modeling.

Huff ModelMNLMCMCABMMobility Data

Urban Wildfire Risk Prediction

Created a remote sensing and machine learning pipeline using MODIS and FIRMS data to predict and visualize wildfire risk patterns in an urban AI context.

MODISFIRMSRemote SensingPyTorchColab

LiDAR Transient Object Filtering

Designed workflows for cleaning urban point clouds by identifying and removing moving objects to improve the reliability of 3D city models.

LiDARPoint CloudsCloudCompare3D Modeling

Mech-On-Wheels

Built a prototype emergency roadside-assistance application that connects users with nearby mechanics during vehicle breakdowns; recognized with a Google Startup Weekend honorable mention.

Product PrototypeUI WorkflowStartup WeekendMobility Service

Experience

Software engineering foundation.

Industry experience in backend systems, cloud workflows, APIs, and real-time data engineering.

Software Development Intern

L&T Technology Services · Airoli, India · Jan 2023 – Jul 2023

Built backend and consumer components for a proof-of-concept healthcare data platform integrating connected wearable devices with the Philips HSDP cloud ecosystem.

Developed real-time ingestion and processing pipelines using Java Spring Boot and Apache Kafka.
Provisioned cloud infrastructure with Terraform and Microsoft Azure services.
Worked with Azure DevOps, Postman, Swagger, Agile workflows, and Python-based data analysis.

NYUMS Urban Data Science, CUSP

DBPDowntown Brooklyn Partnership capstone sponsor

BATWorksPresented LiDAR research at climate event

Skills

Technical toolkit.

Tools and methods across data science, AI, geospatial computing, cloud, and software engineering.

Programming & Data

PythonJavaCC++SQLJavaScriptPandasNumPy

AI & Machine Learning

Scikit-learnTensorFlowKerasXGBoostDeep LearningLLMsComputer Vision

Urban & Geospatial

GISQGISSpatial AnalyticsABMLiDARRemote SensingMobility Data

Cloud & Engineering

AzureAzure DevOpsTerraformDockerSpring BootKafkaGitPostman

Education & Leadership

Academic background.

New York University, Tandon School of Engineering

MS Urban Data Science · NYU CUSP · GPA 3.58/4.0 · Expected May 2026

Manipal University Jaipur

B.Tech Computer Science & Engineering · Minor in Cloud Computing Applications · 2019–2023

Leadership & Involvement

IEEE Student Branch senior coordinator, Women in Engineering involvement, and Head of Programs for Randomize(); Computing Club.

Contact

Let’s connect.

I am interested in research internships, urban AI projects, geospatial ML roles, data science opportunities, and applied work at the intersection of AI and cities.

Download Resume dyn2009@nyu.edu GitHub