Date of Award:

8-2026

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

David Evans

Committee

Phil Fernberg

Abstract

Artificial intelligence (AI) is becoming more common in design fields, including landscape architecture. For example, AI has been used to visually analyze park aesthetics and generate landscape design concepts (Jahani et al., 2022; Senem et al., 2023; Ploennigs & Berger, 2023). This study explores how AI, specifically an image-generation tool called Midjourney, affects the design process for landscape architecture students.

Students completed two design projects—one using AI-generated images and one using traditional, non-AI precedent images. Their final designs were evaluated by professional landscape architects who did not know which designs had been influenced by AI. Students also completed surveys about their experiences using AI in design.

The results showed that AI-integrated designs were rated higher in the category of originality but were not significantly different from traditional methods in other measured descriptors, such as functionality or overall design quality. Additionally, experts could not reliably distinguish between AI-integrated and traditional designs when asked to classify them into one of the two groups. Student opinions toward AI-integrated design processes were generally positive and suggested a perceived increase in design success; evaluations did not always align with these perceptions.

This research suggests that AI can be a useful tool for early-stage design exploration but does not replace human creativity and problem-solving (As et al., 2018; Chen et al., 2023). Future studies should evaluate AI’s role in landscape design more deeply by collecting prompt and image data used in an AI-integrated design process, providing more insight into how AI affects early-stage ideation compared to traditional workflows. Further research could also test how effectively AI tools help generate functional, site-specific design solutions.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Download

Share

COinS

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 .