UGA Bulletin Logo

Introduction to Geospatial Artificial Intelligence


Course Description

Artificial intelligence (AI) and machine learning (ML) methods and their applications on geospatial problems. Topics include GIS data preparation for machine learning models, ML foundations, regression, clustering, decision tree and random forest, neural network, embedding, and location representation learning.

Additional Requirements for Graduate Students:
Graduate students will be assigned additional reading and discussion activities, more complex analytical and writing assignments, and additional questions on tests.


Athena Title

Introduction to Geo AI


Undergraduate Prerequisite

CSCI 1301-1301L or CSCI 1301E or CSCI 1360 or CSCI 1360E or GEOG 4590/6590-4590L/6590L or GEOG 4590E/6590E or permission of department


Graduate Prerequisite

CSCI 1301-1301L or CSCI 1301E or CSCI 1360 or CSCI 1360E or GEOG 4590/6590-4590L/6590L or GEOG 4590E/6590E or permission of department


Semester Course Offered

Offered fall


Grading System

A - F (Traditional)


Course Objectives

1) Students will develop an integrated understanding of various machine learning and artificial intelligence techniques and their pros and cons when applying them to different geospatial data. 2) Students will gain practical experience by using a collection of artificial intelligence and machine learning libraries on different geospatial datasets. 3) Students will be able to choose appropriate GeoAI techniques and apply them to real-world geospatial problems and analyze the results.


Topical Outline

1) Python, Jupyter Notebook, and Google Colab 2) Python fundamentals 3) Spatial data models and formats 4) Vector data analysis 5) Raster data analysis 6) Machine learning fundamentals: gradient decent, classification of machine learning, bias-variance tradeoff 7) Integrating GIS and ML in geospatial projects 8) Regression: linear regression, ridge regression, logistic regression; Geographically weighted regression 9) Decision tree and random forest 10) Geospatial clustering: K-Means, K-Medoid, hierarchical clustering, DBSCAN 11) Neural Network 12) Embedding and Location Representation Learning


Syllabus