Using Machine Learning to Determine Ideal Locations for Urban Agriculture in NYC

May 2023.
Output: Analysis report

This research project was developed as an extension of my work developing the Little Apple. It is meant to offer an additional form of analysis through which ideal locations for urban agriculture can be identified within New York City. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: Python, Pandas, K-means Clustering, Hierarchical Clustering, DBSCAN

Evaluating Amenity Access
Within a Vehicle-less NYC


December 2022.
Output: Research report outlining GIS findings.

The goal of this project was to produce a report exploring and potentially answering a spatial research question. For this, we decided to focus on amenity density within the city, specifically focusing on areas outside walking distance from subway stations. As a result, we were able to conclude what some of the most over and underserved neighborhoods are, as well as which neighborhood(s) are least supportive to individuals with ambulatory disabilities. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: ArcGIS, QGIS, Network Analysis, Tessellation, Metric Normalization, Rasterization of Vector Maps, Raster Addition

Comparison of buffer methods
for assessing street tree density
surrounding McCarren Park


November 2022.
Output: Prospective figure to be included with
a research paper on distance areas.

The goal of this project was to produce one figure suitable for inclusion within an academic paper that describes the analysis and findings when considering street trees surrounding McCarren Park in Brooklyn, NY (including a comparison of the calculations when determined by straight-line distance buffers versus networked distances along the street). Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: ArcGIS, QGIS, Network Analysis

Revisiting John Snow's 1854 Cholera Map

November 2022.
Output: Prospective figure to be included in a
GIS journal.

Project concept included developing a thematic map that revisiting and re-arguing John Snow’s original claim, intended for online viewing by a general, interested-public, audience. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: ArcGIS, QGIS, Getis Ord Gi* Analysis

Mapping the Stream Network and
Basins of the Jordan River Valley


November 2022.
Output: Conceptual map.

Project concept included creating a flow map of the Jordan River Valley using stream network and basins layers developed using ArcGIS Pro geoprocessing tools. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: ArcGIS, QGIS, Fill Sinks, Flow Direction, Flow Accumulation, Stream Threshold, Create Stream Network, Delineate Watersheds

Visualizing Houston-Area
Wetland Loss 1987-2017


November 2022.
Output: Conceptual map.

Project concept included developing three map compositions utilizing Landsat imagery and band combinations to create Natural Color Composite, False Color Infrared, and False Color Urban. It also included composing one map composition showing the wetland change from 1987 to 2017. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: ArcGIS, QGIS, Rendering Composite Images, Creating Training Samples for Automated Image Classification

How Far is _______ from Oakland, CA?

November 2022.
Output: Conceptual map.

Project concept was to develop maps utilizing the Mercator, Peters, Robinson, and one additional CRS visualizing the shortest paths between varios cities and how those paths vary based on the projection used. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: QGIS, Reprojection, Adobe Indesign

Comparing the Population of India's
Five Largest Cities to the Country's
Measurable Light in Space in 2016


November 2022.
Output: Conceptual map.

The goals of this project were to combine raster and vector into a single map, symbolize cities based on their recorded population within the dataset, including labels for the most populated, and focus on a specific region of the world at a scale between 1:15 million and 1:20 million. Completed as part of my work in the MS Computational Design Practices program at Columbia University.

Tools & Techniques Used: QGIS, Symbology Classification