GeoAI Risks: exercises and data

Companion to the textbook. Fifteen exercises, the code that runs them, and the frozen data they run on.

Everything here runs without a license. Python with pandas, numpy, scipy and matplotlib. No geographic information system, no account, no application programming interface key. Every chart and map published here was computed by the programs published here.

Exercises

0-A. Spatial Dependence Before Anything Else

Part 0. Fundamentals and Their Failure Modes

0-B. The Variogram and What Its Parameters Do

Part 0. Fundamentals and Their Failure Modes

0-C. Regression Kriging and What a Covariate Buys

Part 0. Fundamentals and Their Failure Modes

I-A. Where Uncertainty Enters, and the Fallacy That Follows

Part I. Foundations of GeoAI Risks

I-B. Signal, or a Change in What Was Watching

Part I. Foundations of GeoAI Risks

II-A. Measuring Aggregation Sensitivity

Part II. Representational Risk: Aggregation and Boundary Distortion

II-B. The Analysis That Was Already Wrong

Part II. Representational Risk: Aggregation and Boundary Distortion

III-A. The Spatial Exploitability Assessment

Part III. Behavioral and Institutional Risk: Fragility

III-B. Blind-Spot Mapping and the Reliability Screen

Part III. Behavioral and Institutional Risk: Fragility

IV-A. The Uncertainty Cascade Assessment

Part IV. Systemic Risk and Uncertainty: Feedback Loops

IV-B. The GeoAI Feedback Reflex Assessment

Part IV. Systemic Risk and Uncertainty: Feedback Loops

V-A. The Proxy Integrity Assessment

Part V. Adversarial and Emerging Risks

V-B. Adversarial Stress Testing

Part V. Adversarial and Emerging Risks

VI-A. The Practical Uncertainty Stress Test

Part VI. Governing GeoAI Risks

VI-B. The Assurance Case and the Person Across the Table

Part VI. Governing GeoAI Risks

Where to begin

Read Start here for the conventions, the technical tiers and what a submission contains. Instructors should read it as well, since it explains how the student workbook and the instructor material separate.