Geospatial Data Science Course

Lesson 1 • Coordinate Systems and Projections

Covers geographic vs. projected coordinate systems, datums, and projection distortion. Establishes the spatial reference foundation required for all subsequent data work.

Lesson 2 • Spatial Data Formats and Standards

Surveys widely used file formats and open standards for storing and exchanging geospatial data. Prepares students to ingest and export data across diverse platforms.

Lesson 3 • Spatial Scale and Resolution Concepts

Explains map scale, spatial resolution, and their effects on analysis accuracy. Links scale decisions to real-world data collection and interpretation outcomes.

Lesson 4 • Vector and Raster Data Models

Introduces the two primary spatial data models and their trade-offs. Understanding both models is essential for selecting appropriate formats in analysis workflows.

Lesson 1 • Data Integration and Schema Harmonization

Addresses merging datasets with differing projections, schemas, and resolutions into a unified analysis-ready layer. Directly supports multi-source analytical projects.

Lesson 2 • Data Quality Assessment and Cleaning

Identifies common spatial data quality issues including positional error, attribute gaps, and topology faults. Equips students with systematic cleaning and validation workflows.

Lesson 3 • APIs and Web Services for Spatial Data

Teaches programmatic access to spatial data via REST APIs, WMS, WFS, and tile services. Enables automated, repeatable data retrieval within analysis pipelines.

Lesson 4 • Primary and Secondary Data Sources

Distinguishes field-collected primary data from secondary sources such as open portals and satellite archives. Guides source selection based on accuracy, coverage, and licensing.

Lesson 1 • Raster-Based Spatial Operations

Explores map algebra, reclassification, zonal statistics, and cost-surface analysis on raster data. Raster operations enable continuous-surface modeling across large extents.

Lesson 2 • Network Analysis Fundamentals

Covers graph-based routing, service area modeling, and origin-destination matrix computation. Network analysis is critical for logistics, urban planning, and emergency response.

Lesson 3 • Proximity and Distance Analysis

Covers buffer generation, distance matrices, and nearest-neighbor calculations. These operations underpin site selection, service area delineation, and accessibility studies.

Lesson 4 • Terrain and Surface Analysis

Introduces DEM-based operations including slope, aspect, hillshade, and viewshed analysis. Connects surface modeling to environmental, infrastructure, and planning applications.

Lesson 1 • Python Geospatial Environment Setup

Configures conda and pip environments with core geospatial libraries and Jupyter notebooks. A stable environment is the prerequisite for all subsequent Python-based work.

Lesson 2 • Raster Processing with Rasterio and NumPy

Reads, writes, and processes raster datasets using Rasterio and NumPy array operations. Enables scalable raster analysis without reliance on desktop GIS software.

Lesson 3 • Workflow Automation and Scripting

Designs modular, reusable geospatial processing scripts with logging, error handling, and CLI interfaces. Automation skills are essential for production-grade data pipelines.

Lesson 4 • Vector Analysis with GeoPandas and Shapely

Applies GeoPandas GeoDataFrames and Shapely geometry objects to perform spatial operations programmatically. Bridges tabular data science skills to spatial analysis.

Lesson 1 • Spatial Autocorrelation Analysis

Measures spatial dependence using Moran's I, Geary's C, and local indicators of spatial association. Autocorrelation analysis reveals clustering and dispersion patterns in attribute data.

Lesson 2 • Descriptive Spatial Statistics

Computes spatial mean, median center, standard deviational ellipse, and directional distribution. These measures summarize the central tendency and dispersion of spatial point sets.

Lesson 3 • Geographically Weighted Regression

Fits spatially varying regression models to capture local relationships between variables. GWR reveals how predictor effects change across geographic space.

Lesson 4 • Point Pattern Analysis

Analyzes the distribution of point events using kernel density estimation, quadrat analysis, and Ripley's K. Identifies whether point patterns are random, clustered, or dispersed.

Lesson 1 • Spectral Indices and Band Math

Computes vegetation, water, built-up, and soil indices from multispectral bands. Spectral indices provide rapid, quantitative proxies for land surface conditions.

Lesson 2 • Remote Sensing Principles

Explains electromagnetic spectrum, sensor types, and image acquisition geometry. Foundational physics knowledge is required for correct interpretation of satellite imagery.

Lesson 3 • Change Detection and Time-Series Analysis

Detects land cover and surface change using image differencing, post-classification comparison, and time-series methods. Change detection supports environmental monitoring and urban growth analysis.

Lesson 4 • Image Preprocessing and Correction

Covers radiometric calibration, atmospheric correction, and geometric orthorectification. Preprocessing ensures that imagery is analysis-ready and comparable across dates.

Lesson 1 • Spatial Feature Engineering

Creates location-aware features including spatial lags, distance features, and terrain derivatives for ML models. Feature engineering bridges raw geodata and model-ready input matrices.

Lesson 2 • Spatially Aware Model Validation

Addresses spatial autocorrelation in training data through spatial cross-validation and block holdout strategies. Proper validation prevents overly optimistic performance estimates.

Lesson 3 • Regression and Classification on Spatial Data

Trains gradient boosting, random forest, and linear models on spatial tabular datasets for prediction tasks. Covers model tuning, interpretation, and spatial residual diagnostics.

Lesson 4 • Clustering and Regionalization Methods

Applies spatially constrained clustering and regionalization algorithms to delineate homogeneous zones. Clustering supports market segmentation, ecological zoning, and urban analysis.

Lesson 1 • Static Map Production in Python

Creates publication-quality static maps using Matplotlib, GeoPandas plot, and Cartopy. Python-based map production integrates seamlessly into reproducible analysis workflows.

Lesson 2 • Cartographic Design Principles

Covers visual hierarchy, color theory, typography, and map element placement for effective cartography. Sound design principles ensure maps communicate accurately and without bias.

Lesson 3 • Storytelling with Spatial Data

Structures spatial narratives using scrollytelling, annotated maps, and data-driven reports for non-technical audiences. Effective storytelling translates analytical findings into actionable insights.

Lesson 4 • Interactive Web Mapping

Builds interactive web maps using Folium, Leaflet, and Mapbox GL JS with dynamic layers and popups. Interactive maps increase audience engagement and enable exploratory data discovery.