Information Package / Course Catalogue
Artificial Intelligence in Landscape Architecture
Course Code: PSB131
Course Type: Area Elective
Couse Group: Short Cycle (Associate's Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 1
Prt.: 1
Credit: 2
Lab: 0
ECTS: 2
Objectives of the Course

The aim is to enable students to understand the philosophical foundations of artificial intelligence (AI), its historical development, and its transformative role in the discipline of landscape architecture. The course aims to familiarize students with current AI platforms across a wide range of areas, from large-scale urban ecology and planning to micro-scale plant design and detail modeling. Students will gain practical experience in land modeling, drainage optimization, and planting simulations using generative design and parametric tools.

Course Content

This course examines artificial intelligence (AI) from its historical framework, exploring its philosophical roots and the impact of the "black box" problem on design creativity, focusing on landscape design. It covers the effective use of large language models (LLM) and visual production tools (Midjourney, Stable Diffusion), as well as landscape prompt techniques. AI-powered urban/regional analysis tools are used for feasibility studies and settlement practices. Microclimate and sustainability simulations are conducted using environmental analysis tools. The course also encompasses smart parks, the Internet of Things (IoT), AI-assisted preservation of historical landscape heritage, material selection, drone and AI optimization in construction/implementation processes, ethical discussions, and future visions.

Name of Lecturer(s)
Learning Outcomes
1.Identify and classify AI methods suitable for landscape architecture processes according to the relevant project phase.
2.Analyze large-scale land and environmental data (GIS, satellite imagery, etc.) with AI tools to generate urban green infrastructure and urban morphology strategies.
3.Express projects at contemporary standards using AI-powered visualization, hybrid rendering (img2img), and presentation techniques.
4.Perform AI-based performance simulations (daylight, shadow, wind corridors, urban heat island effect) and evaluate ecological outcomes.
5.Critically evaluate the limitations of AI technologies regarding professional ethics, data privacy, and biodiversity, along with the future projections of landscape architecture.
Recommended or Required Reading
1.Özsel Özger, A., & Çahantimur, A. I. (2023). "Yapay Zeka Destekli Metinden Görüntüye Üretim Araçlarının Tasarım Süreçlerindeki Rolü: Midjourney Örneği." Tasarım Kuramı Dergisi.
2.Bal, M., & Ertaş, Besim. (2024). "Sürdürülebilir Kentsel Peyzaj Tasarımında Yapay Zeka ve Makine Öğrenimi Entegrasyonu." Peyzaj Mimarlığı Akademik Dergisi.
3.Yazar, T., & Çolakoğlu, B. (2018). "Tasarımda Algoritmik Düşünme ve Kodlama Eğitimi." Mimarlık Dergisi, Sayı 402.
Weekly Detailed Course Contents
Week 1 - Theoretical & Practice
Course workflow, resources, and submission criteria. A general overview of the current footprint of AI in landscape architecture.
Week 2 - Theoretical & Practice
Evolution of AI from Alan Turing to the present. Transition from symbolic approaches to machine learning. Neural networks and the relation between human-architect creativity and the "Black Box" problem in landscape design.
Week 3 - Theoretical & Practice
Working principles of models like GPT series, Claude, Gemini, and Deepseek. Meaning for landscape architects: Project scenario writing, spatial program analysis, and concept text generation.
Week 4 - Theoretical & Practice
Effective prompt writing techniques. Production of conceptual open space designs using landscape vocabulary, plant textures, material, and style references.
Week 5 - Theoretical & Practice
Use of tools like Autodesk Forma (Spacemaker), Giraffe, Hypar, and Testfit in landscape architecture. Big data, GIS integration, urban green pattern, and layout optimization under site constraints.
Week 6 - Theoretical & Practice
Use of AI in conceptual mass and surface modeling. Image-to-image (img2img) production techniques. Translating ideas derived from AI into 3D rough forms and landscape plastic elements.
Week 7 - Theoretical & Practice
An introduction to the code structure of basic landscape components in AI using natural language.
Week 8 - Theoretical & Practice
Problem definition for AI to find the most efficient layout under specific constraints (topography, slope, functional zoning) and form diversification with genetic algorithms. Midterm exam.
Week 9 - Theoretical & Practice
Modeling details such as retaining walls, hardscapes, and shade panels using natural language commands.
Week 10 - Theoretical & Practice
Converting data from an Excel table (e.g., plant list, height, quantity, crown diameter data) into code with the help of AI to design automatic plant placement and layout scheme proposals in modeling software.
Week 11 - Theoretical & Practice
Performance analysis of designed open spaces regarding energy, microclimate, daylight, shadow, and acoustics.
Week 12 - Theoretical & Practice
Use of AI in sustainable material and plant selection based on ecological constraints, soil, and climate data. Smart parks, IoT integration, plant growth predictions, and predictive maintenance strategies for landscape areas.
Week 13 - Theoretical & Practice
Schedule optimization, drone-based site inspection applications. Preservation of historical landscape heritage and Digital Twins. Developing final presentation and board techniques by re-feeding raw outputs from the model back into AI (render-to-render).
Week 14 - Theoretical & Practice
Creating a case study in a defined urban landscape area where all AI tools, codes, and analysis methods learned throughout the semester are used together.
Assessment Methods and Criteria
Type of AssessmentCountPercent
Presentation1%10
Assignment1%10
Midterm Examination1%20
Final Examination1%60
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140114
Lecture - Practice140114
Assignment1314
Presentation 1314
Midterm Examination1516
Final Examination1718
TOTAL WORKLOAD (hours)50
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
OÇ-1
4
4
5
OÇ-2
4
4
5
OÇ-3
4
4
5
OÇ-4
4
4
5
OÇ-5
4
4
5
Adnan Menderes University - Information Package / Course Catalogue
2026