Eagle density function for eco-constrained design setups #168
Conversation
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
This pull request adds eagle density function capabilities for eco-constrained wind farm design optimization. It introduces components for evaluating eagle presence density at turbine locations and computing distances to exclusion zones.
Key changes include:
- New
EagleDensityFunctioncomponent using bivariate spline interpolation to evaluate eagle presence density from SSRS-generated maps - New
FarmExclusionDistancePolygoncomponent for computing turbine distances to polygonal exclusion regions using JAX-based autodifferentiation - Enhanced visualization support for rendering exclusion zones on layout plots
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 17 comments.
Show a summary per file
| File | Description |
|---|---|
ard/eco/eagle_density.py |
New OpenMDAO component implementing eagle presence density evaluation using scipy's RectBivariateSpline |
ard/layout/exclusions.py |
New OpenMDAO component for calculating turbine-to-exclusion distances with JAX-based gradient computation |
ard/viz/layout.py |
Added plotting functionality for polygonal exclusion zones with validation |
test/ard/unit/eco/test_eagle_density.py |
Unit tests for eagle density function with value and gradient validation |
test/ard/unit/eco/inputs/ard_system_eagle_density.yaml |
Test configuration with eagle density map and design variable definitions |
test/ard/unit/layout/test_exclusion.py |
Comprehensive unit tests for exclusion distance calculations (single and multi-polygon) |
test/ard/unit/layout/test_boundary.py |
Cleanup of unused imports and variables |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 8 out of 8 changed files in this pull request and generated 6 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…to feature/eco_eagles_field
jaredthomas68
left a comment
jaredthomas68
left a comment
There was a problem hiding this comment.
Looks great, just a few minor things to get it ready for production
| """ | ||
| OpenMDAO component to evaluate eagle presence density at turbine locations. | ||
| An Ard/OpenMDAO component that evaluates the SRSS-generated eagle presence |
| OpenMDAO component to evaluate eagle presence density at turbine locations. | ||
| An Ard/OpenMDAO component that evaluates the SRSS-generated eagle presence | ||
| density at turbine locations, nominally for analysis of and optimization |
There was a problem hiding this comment.
punctuation: I think you need some parenthetical commas (maybe I used the right term?)
| ------- | ||
| eagle_normalized_density : np.ndarray | ||
| a 1-D numpy array that represents the normalized eagle presence density | ||
| at each of the turbine locations (unitless) |
There was a problem hiding this comment.
Could you give a little more insight into what the eagle density means or how to interpret it?
There was a problem hiding this comment.
could go here or in the intro paragraph of the doc string
|
|
||
| # evaluate the gradients for each variable | ||
| dfdx = self.eagle_density_function.ev(x_turbines, y_turbines, dx=1, dy=0) | ||
| dfdy = self.eagle_density_function.ev(x_turbines, y_turbines, dx=0, dy=1) |
There was a problem hiding this comment.
way to include derivatives!!!!! I do think we may get better computational efficiency if you create separate derivatives splines in setup, but I'm not sure what RectBivariateSpline is doing under the hood with the ev call and dx spec, maybe it has the derivatives splines already.
| y_turbines = inputs["y_turbines"] # m | ||
|
|
||
| # evaluate the density function at each turbine point | ||
| outputs["eagle_normalized_density"] = self.eagle_density_function.ev( |
| # add four-parameter grid farm layout DVs | ||
| self.add_input("spacing_primary", spacing_primary, units="unitless") | ||
| self.add_input("spacing_secondary", spacing_secondary, units="unitless") | ||
| self.add_input("spacing_primary", spacing_primary, units=None) |
There was a problem hiding this comment.
interesting, why the switch to None?
| windIO_plant: | ||
| layout: | ||
| N_turbines: 9 | ||
| ssrs: |
There was a problem hiding this comment.
I think the name ssrs in the modeling options is not clear enough for novice users. Let's spell it out or pick a more human readable name for the input use where users will see it a lot
| windIO_plant: | ||
| layout: | ||
| N_turbines: 9 | ||
| ssrs: |
There was a problem hiding this comment.
This section should probably be in its own file
| R = lambda x, y: np.sqrt(x * x + y * y) | ||
| # if we wanted to add another dimension here | ||
| # we could add `THETA = lambda x, y: np.atan2(x, y)` | ||
| self.F = lambda x, y: -R(x, y) * R(x, y) / (Rmax * Rmax) + 2 * R(x, y) / Rmax |
There was a problem hiding this comment.
this could use a little explanation
There was a problem hiding this comment.
Nice way of testing though
2 participants
Depends on #167.