Abstract
dc:description.abstractArchaeological Predictive Modeling stands firmly as an important tool for Archaeologists to predict undiscovered sites from civilizations all across the globe. While powerful, this methodology is not without its own set of qualms. Striking a balance between pure a data-driven approach while also observing leading expert theories can be a complicated task. Going further, deciding on the specific domain of features to emphasize or overlook can be a challenge within itself, as one misstep can drastically change the output of model, sometimes for the worst. In addition, creating models that can expose their reasoning process can be rather difficult to develop, a roadblock that can prevent non-technical professionals from fully understanding numerical results. We created a model that solves all three of these problems, a succinct meta-model that utilizes features derived from both geographical data points and quantitative representations of abstract theoretical criteria, which can compare the importance of various domains of features, and incorporate eXaplainable AI features for more transparent decision making. In the end, its result can be further extrapolated to predict the locations of undiscovered archaeological sites in the historically underrepresented region of Mexico. JEL— C45, C51, C52, Q01, R14, R15
Degree
thesis:*- Name thesis:degree_name
- M.S. in Computer Science
- Level thesis:degree_level
- Masters Thesis
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Stamm, Peter
- Contributors dc:contributor
-
- Stephen Hutt
- Kerstin Haring
- Kara Nance
- Guiming Zhang
Subjects
dc:subject × 10Rights
dc:rights- Statement dc:rights
-
- <p>Copyright is held by the author. User is responsible for all copyright compliance.</p>
- Peter Stamm
- Language dc:language
- English (eng)