Date of Award:
12-2025
Document Type:
Thesis
Degree Name:
Master of Landscape Architecture (MLA)
Department:
Landscape Architecture and Environmental Planning
Committee Chair(s)
Benjamin George
Committee
Benjamin George
Committee
Dave Anderson
Committee
Lance Stott
Abstract
Artificial intelligence (AI) is rapidly transforming many industries, but its role in landscape architecture remains relatively unexplored. This study examines how AI, specifically GPT-4, can assist landscape architects in selecting plants for projects. By comparing AI-generated plant lists to those that human experts created, the research evaluates Accuracy, Suitability, Availability, Aesthetics, and Professional Usability.
The results show that AI-generated plant lists were highly efficient, accurately matching site conditions and improving plant availability while significantly reducing selection time. However, human expertise was essential for ensuring aesthetic quality and design intent. While AI can serve as a powerful tool for streamlining plant selection, it is most effective when used alongside human judgment rather than as a replacement.
These findings highlight AI’s potential to support landscape architects by automating research and expanding plant selection options. Future research should explore AI’s adaptability across different climates and its integration with plant databases to improve accuracy. By combining AI’s adaptability across different climates and its integration with plant databases, there is great potential to improve accuracy. By combining AI’s efficiency with human creativity, landscape architects can enhance the design process while maintaining ecological and aesthetic integrity.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Gardner, Paul, "Practical Effectiveness of Large Language Models in Assisting Landscape Architects in Plant Selection" (2025). All Graduate Theses and Dissertations, Fall 2023 to Present. 675.
https://digitalcommons.usu.edu/etd2023/675
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .