MLuminance
Instantaneous Daylighting Feedback
Karim Daw | Alexander Jacobson | Ken Takahashi | Peter Ehvert
1
Architects
Annual-based criteria
Daylighting Experts
The unit is too deep!
No, now there is glare!
Ah, we need shading.
The windows aren’t big enough!
2
Can we overlay annual daylighting feedback as we sketch?
3
Process: Overview
4
Solution: Overlay machine learning predictions of daylighting on top of the sketching process in Rhino
5
Process: Timeline
6
Saturday
Sunday
Create Dummy Dataset
Create Real Dataset
Revit Calling ML Model
Train Dummy Dataset
Train Real Dataset
Creating Revit UI
Build Hops Tensorflow link
Build Hops Tensorflow link
Building the dataset: Inputs and variation
Epw weather data from Copenhagen
Orientation is important
UDI is an annual simulation that is notoriously slow to calculate
Collibri iterates over design space
Variables: Orientation, Room width, room depth, Shuffle each corner +/- 1 meter, Room height
7
Building the dataset: Pollination cloud computing
950 runs on pollination (including testing)
Final training dataset is 650 simulations
Parameters for Machine Learning Model, as well as the mask of sensors inside the room were all stored as user Inputs in Pollination
8
Tensorflow: Summary
9
Inputs:
Outputs:
30x31 UDI Mesh
Tensorflow: Summary
10
Tensorflow: Summary
11
Simulated mesh
Predicted mesh
Good Case
1.48% Average Error
Bad Case
12.7% Average Error
Rhino File
Rhino Workflow: Summary
User Modelled Data�
Collect Rhino Data
Input Parameters�
Predicted Daylight
Predicted Daylight
Predicted Daylight
12
Rhino Workflow: Hops and GH
13
Rhino Workflow: Minimal GH canvas
14
Revit Workflow: Summary
User Modelled Data�
Collected Revit Data
Input Parameters�
Predicted Daylight
Predicted Daylight
Predicted Daylight
15
Revit Workflow: User Interface
16
Revit Workflow: Retrieving Indicators by Room
17
Revit Workflow: Calling Trained Model with Room Data
18
Reflections: Lessons for next hackathon
19
Team: 2 time zones
20
Copenhagen
Copenhagen
Copenhagen
Tokyo
Acknowledgements
Thank you to everyone at Thornton Tomasetti and AEC-Tech, we had a blast
Special thank you to Chris and Mostapha for LBT and pollination and generally being very supportive and patient
McNeel for all their opensource API’s
ML community for humbling us
21
Live Demo
22
Process: Creating Dataset (dummy)
23
Rhino Workflow: Hops and GH
24