Geospatial Data Science | NYU Tandon School of Engineering

Geospatial Data Science

Online with Live Sessions

A silhouette of a person looking at digital display

Register Today

Course begins May 19th

 

Summary

Geospatial Data Science is a comprehensive course designed to enhance your skills in spatial data analysis and visualization. You will explore key topics, including effective map design, storytelling with geospatial data, and using tools like Esri ArcGIS Pro and QGIS. You'll learn how to acquire, clean, and manage geospatial data from various sources, perform spatial analysis, and apply advanced techniques such as spatial statistics, hotspot analysis, and geospatial modeling. The course also covers cutting-edge topics in machine learning for geospatial data, including geospatial AI, spatial machine learning, and deep learning. This course equips you with the tools and knowledge to make data-driven decisions using geospatial data.

 

Key Objectives

Upon completion of this badge, students will be able to:

  1. Create and interpret thematic maps and visualizations:
    • Understand and apply principles of effective map design, including the use of colors and visualizations.
    • Utilize tools like ArcGIS Story Maps and dashboards to communicate geospatial data and use storytelling.
  2. Acquire, manage, and preprocess geospatial data:
    • Source geospatial data from national, regional, and local datasets (e.g., US Census, NYC Open Data).
    • Clean, preprocess, and manage geospatial data using appropriate database management systems.
  3. Perform and quantify spatial analysis using GIS software:
    • Conduct various types of spatial analysis, such as spatial querying, overlay analysis, and proximity analysis.
    • To perform these analyses, you must work proficiently with GIS software tools, including Esri ArcGIS Pro, ArcGIS Online, ArcGIS Storymaps, and QGIS.
  4. Get hands-on experience about how to apply advanced geospatial modeling and machine learning techniques:
    • Implement spatial regression, hotspot analysis, clustering, and network analysis.
    • Utilize machine learning techniques for geospatial data, including supervised and unsupervised learning, and apply geospatial AI and spatial deep learning methods for image analysis.

 

Who Should Attend

This course is designed for:

  • Cities and agencies
  • K-12 teachers, community college instructors
  • Freelancers and working professionals
  • Companies that outsource GIS tasks

 

Technical Requirements and Prerequisites

Prerequisites

  • High school degree
  • Basic computer skills with familiarity with the Windows operating system, file management, zip folders, and general software usage.
  • Basic understanding of mathematics, algebra, and statistics.
  • Comfortable use of Microsoft Office package (Excel, in particular).

GIS tools to be learned/used:

  • Esri ArcGIS Pro software – the main tool ($100 personal use license) includes:
    • Esri ArcGIS Online (it’s a cloud, all files used in the badge could be stored here)
    • Esri ArcGIS Storymaps (the final product could be stored as a link)
  • QGIS – introduction*
  • OpenStreetMap – introduction*

*Free-to-use open-source software

 

Badge Sequence

Visualization and Communication of Spatial Data

  • Intro to colors and visualizations
  • Effective map design principles and visualizations
  • Storytelling with geospatial data (ArcGIS Storymaps, dashboards)
  • Tools for visualization

Introduction to Geospatial Data Science

  • Overview of Geospatial Data Science
  • Importance and applications
  • Key concepts: GIS, remote sensing, spatial data, etc.
  • Introduction to GIS software (ArcGIS Pro, Online, QGIS)

Spatial Data Acquisition and Management

  • Acquiring geospatial data (data portals, Census, satellite, OpenStreetMap etc)
  • Data cleaning and preprocessing
  • Database management systems

Basics of Geographic Information Systems

  • Basics of Geographic Information Systems (GIS)
  • Data types and sources (vector vs. raster)
  • Coordinate systems and map projections
  • Main tools (join, relate, buffer, statistics, etc)

Spatial Analysis

  • Spatial querying and mapping
  • Overlay analysis and spatial joins
  • Proximity analysis

Advanced Spatial Analysis

  • Spatial statistics and interpolation
  • Hotspot analysis and clustering
  • Spatial neighbors and outliers
  • Network analysis and routing

  • Spatial regression
  • Probability of presence
  • Causal inference

  • Introduction to spatial machine learning
  • Supervised vs. unsupervised learning
  • Geospatial AI
  • Use of large language models for geospatial data analysis
  • Spatial deep learning