Mehak Sachdeva
Urban Science Faculty Fellow
Center for Urban Science and Progress, Tandon School of Engineering, New York University
I am an Urban Science Faculty Fellow at the Center for Urban Science and Progress at New York University. I recently completed a PostDoc and PhD in Geographic Information Science at the Spatial Analysis Research Center (ASU) with a focus on computational methods and local regression models to analyze urban processes with applications in crime, housing markets and urban health outcomes amongst others. I have prior experience as a geospatial data scientist at Carto (a SaaS web-mapping platform) and have a graduate degree in urban planning and analytics from Columbia University and an undergraduate degree and professional background in architecture. As a passionate researcher and an urban enthusiast, everything I have engaged in so far has been driven by a keen interest in the coexistence of urbanity and ecology and the impact of human footprint on the environment. In my spare time I run, hike, paint and read.
Representative research on a geographical perspective on Simpson’s Paradox and the scale of processes between local and global models:
Education
PhD in Geographic Information Science, 2022
Arizona State University
Master of Science in Urban Planning, 2016
Columbia University
Bachelor of Architecture, 2013
The Maharaja Sayajirao University of Baroda, India
Publications
Quickly discover relevant content by filtering publications.
(2022).
Local Modeling in a Regression Framework.
Spatial Analysis in the Social Sciences Handbook, eds. S. Rey and R. Franklin..
(2022).
Are We Measuring Spatial Nonstationarity or Nonlinearity.
Geographical Analysis..
(2022).
The Geographically Weighted Regression Framework..
The Geographic Information Science & Technology Body of Knowledge (4th Quarter 2020 Edition).
(2022).
Analyzing the distribution of researchers in China: An approach using multiscale geographically weighted regression..
Growth and Change..
(2022).
Using the specification curve to teach spatial data analysis and explore geographic uncertainties.
Journal of Geography in Higher Education.
(2022).
Modelling spatial processes in quantitative human geography.
Annals of GIS.
(2022).
A Replication of DiMaggio et al. (2020) in Phoenix, AZ.
Annals of Epidemiology.
(2022).
A scoping review on the multiplicity of scale in spatial analysis.
Journal of Geographical Systems.
(2022).
On the importance of thinking locally for statistics and society..
Spatial Statistics.
(2022).
Scale and Local Modeling: New perspectives on the modifiable areal unit problem and Simpson’s paradox.
Journal of Geographical Systems.
(2022).
Do places have value? Quantifying the intrinsic value of housing neighborhoods using MGWR.
Journal of Housing Research 0(0):1–29.
Select presentations and workshops
Projects
*
A recent addition to the local statistical modeling framework is the implementation of the Multiscale Geographically Weighted Regression (MGWR) model, a multiscale extension to the widely used approach for modeling process spatial heterogeneity, Geographically Weighted Regression (GWR).
The concept of ‘spatial scale’, or simply ‘scale’ is implicit in any discussion of global versus local models. The raison d’etre of local models is that a global scale (where here ‘global’ simply refers to all locations within a predefined area of interest) might be the incorrect scale at which to undertake any analysis of spatial processes; the alternative being a local scale (where here ‘local’ refers to individual locations).
Studies of spatially varying parameter estimates obtained in the calibration of various types of local statistical models are commonplace. The variation in such estimates is typically explained in terms of spatially varying processes.
Real estate market analysis has long been an active area of inquiry and one that reveals much about people’s preferences regarding housing attributes. It is well-known that house prices tend to exhibit strong spatial dependency and that they vary across space due to differences in structural and neighborhood characteristics.
City Studio is an Arizona State University (ASU) course developed to allow ASU and the City of Tempe to collaborate on Tempe’s 20-Minute City project. ASU worked with Tempe staff to develop the City Studio class.
Space-time Autocorrelation using NYC taxi data (2015) This project explores spatial and temporal autocorrelation. Open-source yellow taxi trip data for the year 2015 was aggregated to a 50m * 50m grid across NYC.
My first contribution to the CARTO environment was to develop materials for the Carto Academy depicting how to implement and interpret spatial tools on the web GIS platform. This has since been deprecated to accommodate for changes in the version of the current software.
The Resilient Island Culture Studio was tasked to address housing and resiliency issues on Staten Island in the aftermath of Hurricane Sandy. With Make the Road New York as the studio client, emphasis was placed on serving lower-income communities that have not fully recovered from the storm.
As wealth gaps increase in American Cities certain lower income populations in cities will grow more vulnerable if their transportation
needs are not met. We can use GIS to spatially research where the
highly dense areas are that may be currently underserved by existing
Subway infrastructure in cities.
Concerned with environmental injustice and the many ill-impacts it has on the residents of affected neighborhoods, I realized through existing literature that there were sources of toxic air pollutants existing within close proximity to our daily land-uses.
In 2013, deeply concerned about rampant mining in some parts of India and their subsequent abandoning I came across some abandoned asbestos mines, south of the city of Udaipur that had left a toxic trail for the community dwellers to deal with.
In this urban theory studio during my undergraduate studies in architecture, the aim was to study and implement a plan for the resurgence of the center of the city of Vadodara, India, long known for its Colonial architectural style.
Teaching Experience
Co-Instructor
GIS-563 - Local Statistical Modeling
Description:
- Concepts on local statistical modeling
- Teaching how to implementing related software and understand inference
Graduate Course - Assistant Developer
GIS-471 - Spatial Statistics
Responsibilities include:
- Contributing to construction of course material
Graduate Teaching Assistant
Advanced GIS
Description:
- Advanced concepts in GIS (Medium - ESRI software and Python)
- Syllabus
Graduate Teaching Assistant
Sustainable Urban Development - International Perspectives
Responsibilities include:
- Assisting with course development
- Updating outdated lectures and circulating relevant course content
Professional Experience
Geospatial Data Scientist
Responsibilities include:
- Analysing
- Modeling
- Deploying new tools within the Carto environment
- Contributing to Carto Academy
Education and Data Intern
Responsibilities include:
- Contributing to Carto Academy
- Held workshops to promote use of geospatial technologies
Urban Planner
GWW Planning and Consultancy
Responsibilities include:
- Drafting planning ideas for neighborhood projects
Development Intern
Responsibilities include:
- Analysis for neighborhood planning projects
- Community engagement and meetings
Data Analyst and Developer
SHoP Architects and Center for Spatial Design
Responsibilities include:
- Creating clean network data for node analysis
Resiliency Planning Intern
New York City Department of City Planning
Responsibilities include:
- Planning for the resilient neighborhoods projects
- Contributed to drafting resilient neighborhoods report
Architect
Responsibilities include:
- Designing for institutional projects
- Drafting ideas for design competitions
- Working drawings for on-site construction