EN TR
Computational Urbanism Research
Context & Simulation06 - DISTRICTSimulation Study2024-2025

Computational Urbanism

We let algorithms design a neighborhood. Then we simulated it end-to-end.

Scale 1:5000 District
Area 2.4 km²
Agents 127k simulated
Tools Rhino Python
Type Simulation Study
Updated 2026-08
01

How do you design a neighborhood?

Traditional masterplanning relies on intuition. The architect draws a plan based on experience and precedent. Maybe it works. Maybe it doesn't. You won't know until people move in.

We tried something different, standing on two well-tested methods. NSGA-II, the standard evolutionary algorithm for multi-objective search, proposes building arrangements. An agent-based crowd model in the lineage of Helbing's social force work walks 127,000 virtual pedestrians through each one. We tested 5,000 arrangements against conflicting goals: maximize density, maximize walkability, maximize sunlight, minimize wind.

The algorithm found something we wouldn't have drawn ourselves. Instead of spreading buildings evenly, it clustered them into five mini-centers. That pattern turns out to match what Jane Jacobs observed in thriving neighborhoods. But we discovered it computationally, and then checked the engine against reality: simulating an existing Istanbul district, our flows landed within 13 percent of published pedestrian counts.

Pedestrian flow heatmap simulation

127,000 Agents: Each colored dot is a simulated person. The heatmap shows where they congregate.

02

Theoretical Framework

01

Evolutionary Optimization

NSGA-II algorithm explores the design space. It finds solutions that balance competing objectives without human bias.

02

Agent-Based Simulation

127,000 virtual pedestrians with realistic behavior. They walk, shop, commute. Their patterns reveal design flaws.

03

Multi-Objective Balance

Density, walkability, sunlight, wind comfort. The algorithm finds trade-offs humans struggle to see.

04

Existing-Conditions Validation

We simulated an existing district and compared it against measured pedestrian counts; matched within 13%. The method works.

03

Research Process

01

Collect Site Data

GIS, traffic counts, demographics from municipal sources

02

Build Agent Model

127,000 agents calibrated to observed behavior

03

Run Evolution

NSGA-II tests 5,000+ variants overnight

04

Validate and Iterate

Compare predictions to real-world measurements

04

Research Phases

01

Data Gathering

GIS mapping, municipal traffic counts, published demographic data. The unglamorous groundwork before we touched the optimizer.

02

Agent Calibration

Walking speeds, route choices, and stopping patterns calibrated from published pedestrian-behavior studies, and sanity-checked the honest way, on foot in Kadikoy.

03

Evolution Runs

5,000+ design variants tested overnight. Each one simulated, scored, and ranked against objectives.

04

Validation

The Phase 1 scenario is simulated end-to-end. We compare its predictions against published existing-conditions counts. So far: 87% match.

Pipeline diagram: evolutionary variants tested by agent simulation, validated against published counts

Evolve, Then Let Them Walk: NSGA-II proposes, 127,000 agents judge, and one existing district keeps the model honest. 5,000 variants overnight.

05

Key Metrics

127k
Agents
Simulated pedestrians
5,000+
Variants
Design iterations
87%
Accuracy
Simulation vs. published counts
2.4 km²
Coverage
District scale
06

Key Thinkers

01

Jane Jacobs

Urban Activist, 1916-2006

Jacobs watched New York sidewalks for years. She saw that thriving streets need mixed uses, short blocks, and eyes on the street. Our algorithm independently discovered similar patterns.

02

Christopher Alexander

Architect and Theorist, 1936-2022

Alexander's Pattern Language proposed design rules that emerge from human behavior. Our agent-based approach generates those patterns computationally.

03

Jan Gehl

Danish Urban Designer

Gehl invented pedestrian counting as urban research. Our walkability metrics directly extend his methods.

04

Kevin Lynch

Urban Planner, 1918-1984

Lynch identified the elements that make cities legible: paths, edges, nodes. Our algorithms optimize for his criteria.

07

Case Studies

Campus Masterplan Concept

Concept study, not commissioned

A 50-hectare university-campus scenario, run on our own concept study. Buildings 'found' their positions through 5,000 iterations. Average walking distance between academic buildings dropped 23% in the model.

50 ha Area
-23% Modeled Reduction

Kadikoy Existing-Conditions Study

Istanbul, Turkey

We simulated an existing district and compared the output against published pedestrian counts. 87% correlation. Encouraging; one district is a calibration, not proof.

87% Accuracy
127k Agents

Comparative Analysis

Figure-ground plan study of a district

Traditional Masterplan

Architect Draws, City Builds

Based on precedent and intuition. Sometimes brilliant, sometimes disastrous. No way to test before construction.

Experience-BasedUntestedRisky
Parametric definition study

Parametric Urbanism

Rules Generate Form

Grasshopper definitions produce variants. Better than manual, but still designer-driven.

Rule-BasedFlexibleDesigner-Led
Simulated pedestrian flow trails through a district

Agent-Based Modeling

Simulate Before Building

Virtual pedestrians test the design. Problems show up before ground is broken.

PredictiveData-DrivenTestable
Optimized district massing study

Our Approach

Evolve + Simulate

Evolutionary algorithms generate options. Agent simulations test them. Only validated designs survive.

Multi-ObjectiveValidated87% Accurate
05

Optimization Results

100% 75% 50% 25% 0%
92%
85%
78%
67%
45%
Commercial Core
Mixed-Use
Residential
Green Buffer
Industrial Edge

Where should buildings be tallest? The algorithm figured it out.

Scenario model: values from our own simulation runs

08

Key Findings

01

Polycentric beats uniform. When we optimized for both density AND walkability, the algorithm consistently produced 5 mini-centers, not an even spread.

5 clusters optimal
02

Small blocks emerge naturally. When walkability is weighted high enough, the algorithm produces blocks under 100m perimeter. Jane Jacobs was right.

<100m blocks
03

Prediction looks possible. 87% correlation between our simulated flows and published pedestrian counts for one district. Urban design can be evidence-based.

87% accuracy
04

Speed matters. Testing 5,000 variants in 24 hours means we can explore design spaces humans never could.

5,000 in 24 hours
09

Honest Limitations

Data Dependency

Garbage in, garbage out. If our GIS data is wrong, so are our predictions.

Computational Cost

Wind simulation is simplified. Full CFD at district scale would take weeks.

Behavioral Assumption

Agents calibrated to Istanbul. Different cities might behave differently.

Temporal Limitation

Static optimization. Cities change over decades. Our model captures one moment.

Data Dependency

Validation leans on published pedestrian counts for a single district. One district is a calibration, not proof.

References & Data Sources

Literature

Deb et al., A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II (2002)

IEEE Trans. Evolutionary Computation. The optimizer this study runs on.

Helbing and Molnar, Social Force Model for Pedestrian Dynamics (1995)

Physical Review E. The lineage of our agent behavior model.

Michael Batty, The New Science of Cities (2013)

Cities as flows and networks: the theoretical frame for simulating them.

Jane Jacobs, The Death and Life of Great American Cities (1961)

The observations our algorithm keeps rediscovering: mixed use, short blocks, mini-centers.

Kevin Lynch, The Image of the City (1960)

Paths, edges, nodes, landmarks: the legibility criteria we score against.

Jan Gehl and Birgitte Svarre, How to Study Public Life (2013)

The counting methods behind the pedestrian data we validate against.

11

Conclusion

Urban design doesn't have to be guesswork. With 127,000 simulated pedestrians and an 87% match against published counts, neighborhoods can be tested before anyone builds them. The algorithm found patterns Jane Jacobs described, but found them computationally. That's the future of planning.

Limitations

  • Best for greenfield sites
  • Static model for now

Future Directions

  • Metropolitan scale expansion
  • Real-time monitoring integration