Enhancing Basic Geology Skills with Artificial Intelligence: An Exploration of Automated Reasoning in Field Geology

Perry Ivan Quinto Houser, University of Texas at El Paso

Abstract

This thesis explores the use of Artificial Intelligence, specifically semantics, ontologies, and reasoner techniques, to improve field geology mapping. The thesis focuses on two use cases: 1) identifying a geologic formation based on observed characteristics; and 2) predicting the geologic formation that might be expected next based upon known stratigraphic sequence. The results show that the ontology was able to correctly identify the geologic formation for the majority of rock descriptions, with higher search results for descriptions that provided more detail. Similarly, the units expected next were correctly given and if incorrect, would provide a flag to the field geologist to further investigate the sequence break. However, subjective descriptions and searches can impact the results, and incorrect property assertions can generate undesirable results and require validation and verification of data. Overall, the study demonstrates the potential for using sematic knowledge bases for field studies to improve geologic field observations and measurements.

Subject Area

Geology|Computer science|Information science

Recommended Citation

Houser, Perry Ivan Quinto, "Enhancing Basic Geology Skills with Artificial Intelligence: An Exploration of Automated Reasoning in Field Geology" (2023). ETD Collection for University of Texas, El Paso. AAI30521645.
https://scholarworks.utep.edu/dissertations/AAI30521645

COinS