PRAKRITI SRIMAL
I help planners and designers make sense of complex urban data
SENIOR URBAN DATA SCIENTIST | AEC TECH AUTOMATION SPECIALIST | COMPUTATIONAL DESIGNER | URBAN DESIGNER | ARCHITECT | LEED® GREEN ASSOCIATE™ | TEACHING ENTHUSIAST
IsoChronic City
IsoChronic City is a master's thesis developed at the Bartlett School of Architecture, University College London, as part of the B-Pro program. The project was conceived by a team of four: Prakriti Srimal, Sonali Bordia, Shuyao Li, and Siyang Zheng.
IsoChronic City is an urban response to the recent predicament of what the process of reurbanization in cities will entail in the post-pandemic era. It is based on the 15-minute neighbourhood concept which is derived from historical ideas about proximity and walkability.
CORE COMPETENCIES
Geospatial Intelligence
Urban analysis using satellite imagery, spatial metrics, and clustering models.
Urban Data Visulaisation
Interactive dashboards, maps, and visual storytelling for spatial data insights
Real Time Sensing
Multi-sensor data collection, urban environment monitoring
WRITING
I write about urban systems, spatial analysis, and what data can reveal about the places we live in.
Current focus: applying science based urban analysis methodologies to Bangalore, and documenting the process of building a real time sensing instrument from scratch.
Cities generate more data than ever before. Most of it goes unread.
How far can you go?
5, 10, and 15 minute walk catchments and 20 and 30 minute drive catchments mapped across the city. Which neighbourhoods are truly accessible, and which ones depend entirely on a car.
What is Bangalore actually made up of?
Classifying Bangalore's urban fabric by the shape of its streets, blocks, and buildings. From the organic grain of the old pete area to the sprawling plots of the north, every neighbourhood has a morphological fingerprint.
Real Time Sensing
GPS, temperature, humidity, and audio running on the NVIDIA Jetson Orin Nano Super. The instrument is taking shape.
ABOUT
I am an architect by training, with a specialisation in machine thinking urbanism.
My work sits at the intersection of cities, computation, and data. Over the past few years this has meant building geospatial workflows in Python, applying machine learning to urban systems, and developing Revit API automation tools.
I work across scales, from understanding how a single street performs to how different parts of a city relate to each other. The focus stays the same: turning complex spatial data into something useful for the people who design and plan cities.
I also write about cities. A current series applies professional urban analysis methodologies to Bangalore, the city I live in.
