Skip to content

docs: add visualization preview at top of RasterFlow model notebooks #160

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pdarringer wants to merge 5 commits into
base: main
Choose a base branch
from
Open

docs: add visualization preview at top of RasterFlow model notebooks #160

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
63b2493
docs: embed input/output map preview at top of RasterFlow model noteb…
pdarringer May 7, 2026
75728d6
docs: replace RasterFlow preview iframes with a single link
pdarringer May 19, 2026
b255ff0
chore: normalize notebook source format via nbconvert
pdarringer May 19, 2026
3e5da45
Remove mention of vectorized geometries from CHM notebook
pdarringer May 19, 2026
e8bc03b
Remove mention of raster model outputs from SAM3 notebook
pdarringer May 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions Analyzing_Data/RasterFlow_CHM.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,22 @@
"The National Agriculture Imagery Program (NAIP) provides aerial imagery for the United States, capturing high-resolution images during the agricultural growing seasons. The NAIP dataset contains a mixture of resolutions (30cm, 60cm and 1m). See [this map](https://esri.maps.arcgis.com/apps/mapviewer/index.html?webmap=6cc0dcb225de4cb8aaa23c6a9cb59db8) for more details. We will use 60cm imagery to test this model."
]
},
{
"cell_type": "markdown",
"id": "44a7fcf0",
"metadata": {},
"source": [
"## Preview: model inputs and outputs\n",
"\n",
"The interactive map linked below shows the input imagery and model outputs for this notebook's example AOI. Toggle layers in the sidebar to compare the inputs, the raster model output, and the vectorized geometries side-by-side.\n",
Comment thread
pdarringer marked this conversation as resolved.
Outdated
"\n",
"**Layers:**\n",
"- *CHM input mosaic*: RGB NAIP aerial imagery the model runs on\n",
"- *CHM model outputs*: single-band raster where each pixel is the estimated tree canopy height in meters\n",
"\n",
"View the interactive map [here](https://viz.wherobots.com/?l0.id=4a8d3619-291c-4acb-8246-99aea96c3bc4&l0.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fnashua_optimized.zarr&l0.name=CHM+input+mosaic&l0.clim=33.370882202482704%2C201.81320110343603&l0.mode=rgb&l0.rgb=red%2Cgreen%2Cblue%2Cband&l0.ndvi=nir%2Cred%2Cband&l0.var=variables&l1.id=37fe2b6b-2c85-48fa-abd3-60ebfec9ce4b&l1.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fchm_optimized.zarr&l1.name=CHM+model+outputs&l1.clim=0.01848162641420724%2C27.58277035763343&l1.mode=single&l1.var=variables&title=CHM+Nashua+NH)."
]
},
{
"cell_type": "markdown",
"id": "74a65529",
Expand Down
18 changes: 18 additions & 0 deletions Analyzing_Data/RasterFlow_Chesapeake.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,24 @@
"It was trained on high resolution imagery from the [National Agriculture Imagery Program (NAIP)](https://www.usgs.gov/centers/eros/science/usgs-eros-archive-aerial-photography-national-agriculture-imagery-program-naip) and labeled land cover data for the state of Maryland in the United States. "
]
},
{
"cell_type": "markdown",
"id": "227bbdce",
"metadata": {},
"source": [
"## Preview: model inputs and outputs\n",
"\n",
"The interactive map linked below shows the input imagery and model outputs for this notebook's example AOI. Toggle layers in the sidebar to compare the inputs, the raster model output, and the vectorized geometries side-by-side.\n",
"\n",
"**Layers:**\n",
"- *ChesapeakeRSC input mosaic*: RGB high-resolution aerial imagery the model runs on\n",
"- *ChesapeakeRSC model outputs*: single-band raster output from the model (road class)\n",
"- *ChesapeakeRSC vector geometries*: vectorized road polygons derived from the raster output\n",
"- *ChesapeakeRSC PM Tiles*: same vectors delivered as PMTiles for fast rendering at scale\n",
"\n",
"View the interactive map [here](https://viz.wherobots.com/?z=10.75&lat=39.14465&lng=-77.20751&l0.id=ad763026-8281-433a-aad7-d10c9fc709eb&l0.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fmontgomery_optimized.zarr&l0.name=ChesapeakeRSC+input+mosaic&l0.clim=31.23266239424982%2C185.96608315709923&l0.mode=rgb&l0.rgb=r%2Cg%2Cb%2Cband&l0.var=variables&l1.id=ebbf10e8-5d28-4abe-8110-cc48636bb870&l1.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fchesapeakersc_optimized.zarr&l1.name=ChesapeakeRSC+model+outputs&l1.clim=0.0000873437512581339%2C0.6739252251391948&l1.mode=single&l1.var=variables&l1.seli.band=1&l2.id=fc770180-662d-4c9c-b4f5-ffeef3b22bde&l2.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fvectors%2Fchesapeakersc_montgomery.parquet%2F&l2.name=ChesapeakeRSC+vector+geometries&l2.type=geoparquet&l2.fill=%23ef4444&l2.line=%23dc2626&l2.lw=2&l2.cc=%23ef4444&l2.cr=5&l3.id=8c9d2950-0503-40ca-b732-74c6b0bd0a2e&l3.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fchesapeakersc.pmtiles&l3.name=ChesapeakeRSC+PM+Tiles&l3.type=pmtiles&l3.fill=%233b82f6&l3.line=%232563eb&l3.lw=2&l3.cc=%233b82f6&l3.cr=5&title=ChesapeakeRSC+Montgomery+County+MD)."
]
},
{
"cell_type": "markdown",
"id": "74a65529",
Expand Down
19 changes: 19 additions & 0 deletions Analyzing_Data/RasterFlow_FTW.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,25 @@
"Rather than needing to create these mosaics manually, we'll use RasterFlow's registered datasets for Sentinel-2 seasonal mosaics, which are built in to this model recipe."
]
},
{
"cell_type": "markdown",
"id": "99b0dd0d",
"metadata": {},
"source": [
"## Preview: model inputs and outputs\n",
"\n",
"The interactive map linked below shows the input imagery and model outputs for this notebook's example AOI. Toggle layers in the sidebar to compare the inputs, the raster model output, and the vectorized geometries side-by-side.\n",
"\n",
"**Layers:**\n",
"- *FTW input planting mosaic*: RGB Sentinel-2 median-pixel mosaic for the planting season\n",
"- *FTW input harvest mosaic*: RGB Sentinel-2 median-pixel mosaic for the harvest season\n",
"- *FTW model outputs*: raster output from the model, shown using the `field_boundaries` band\n",
"- *FTW vector geometries*: polygons of detected fields, derived from the raster output\n",
"- *FTW PM Tiles*: same field polygons delivered as PMTiles for fast rendering at scale\n",
"\n",
"View the interactive map [here](https://viz.wherobots.com/?z=10.11&lat=37.56246&lng=-100.87099&l0.id=5b4405dc-d603-47dc-ae09-e0faf3a6f445&l0.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fftw_haskell_optimized.zarr&l0.name=FTW+input+planting+mosaic&l0.clim=533.6418968402297%2C4109.013308997522&l0.mode=rgb&l0.rgb=s2med_planting%3AB04%2Cs2med_planting%3AB03%2Cs2med_planting%3AB02%2Cband&l0.var=variables&l1.id=8b1b90e5-7906-4b4e-aa10-57764850aa4f&l1.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fftw_haskell_optimized.zarr&l1.name=FTW+input+harvest+mosaic&l1.clim=297.7345099947093%2C1247.8318047602793&l1.mode=rgb&l1.rgb=s2med_harvest%3AB04%2Cs2med_harvest%3AB03%2Cs2med_harvest%3AB02%2Cband&l1.var=variables&l2.id=19bfda38-982f-4b27-b61f-982f8f00119a&l2.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fftw_optimized.zarr&l2.name=FTW+model+outputs&l2.clim=0.0002047998614793119%2C0.7692958755736328&l2.mode=single&l2.rgb=field_boundaries%2Cfield%2Cfield_boundaries%2Cband&l2.var=variables&l2.seli.band=2&l3.id=aee604ee-f1ea-4fe7-9c7c-1be8b5b2a99e&l3.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fvectors%2Fftw_haskell.parquet%2F&l3.name=FTW+vector+geometries&l3.type=geoparquet&l3.fill=%23ef4444&l3.line=%23dc2626&l3.lw=2&l3.cc=%23ef4444&l3.cr=5&l4.id=1b4a7680-4f0e-4fb0-9b79-a4472908947b&l4.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fvectors%2Fftw_haskell.pmtiles&l4.name=FTW+PM+Tiles&l4.type=pmtiles&l4.fill=%233b82f6&l4.line=%232563eb&l4.lw=2&l4.cc=%233b82f6&l4.cr=5&title=FTW+Haskell+County+KS)."
]
},
{
"cell_type": "markdown",
"id": "74a65529",
Expand Down
17 changes: 17 additions & 0 deletions Analyzing_Data/RasterFlow_SAM3.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,23 @@
"Unlike segmentation models that produce raster outputs, SAM3 directly outputs vector geometries, making it straightforward to integrate results into geospatial workflows. We will demonstrate results using 30cm resolution data from the [National Agriculture Imagery Program (NAIP)](https://www.usgs.gov/centers/eros/science/usgs-eros-archive-aerial-photography-national-agriculture-imagery-program-naip)."
]
},
{
"cell_type": "markdown",
"id": "cbc17581",
"metadata": {},
"source": [
"## Preview: model inputs and outputs\n",
"\n",
"The interactive map linked below shows the input imagery and model outputs for this notebook's example AOI. Toggle layers in the sidebar to compare the inputs, the raster model output, and the vectorized geometries side-by-side.\n",
Comment thread
pdarringer marked this conversation as resolved.
Outdated
"\n",
Comment thread
pdarringer marked this conversation as resolved.
"**Layers:**\n",
"- *SAM3 input mosaic*: RGB NAIP aerial imagery the model runs on\n",
"- *SAM3 vector geometries*: polygons output directly by the text-prompted model (SAM3 is a geometry inference model, so there is no intermediate raster output)\n",
"- *SAM3 PM Tiles*: same geometries delivered as PMTiles for fast rendering at scale\n",
"\n",
"View the interactive map [here](https://viz.wherobots.com/?z=9.61&lat=44.98530&lng=-122.47688&l0.id=3930c361-98e6-4b7a-a534-ef69709881a7&l0.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fmarion_county_optimized.zarr&l0.name=SAM3+input+mosaic&l0.clim=35.23256150636151%2C187.34808753310205&l0.mode=rgb&l0.rgb=red%2Cgreen%2Cblue%2Cband&l0.ndvi=nir%2Cred%2Cband&l0.var=variables&l1.id=8888ae61-90a6-4e8c-b8f3-7bd51c1510e8&l1.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fmarion_county_sam3%2F&l1.name=SAM3+vector+geometries&l1.type=geoparquet&l1.fill=%233b82f6&l1.line=%232563eb&l1.lw=2&l1.cc=%233b82f6&l1.cr=5&l2.id=2882e773-6c93-4d67-8c2d-d0c75e807501&l2.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Fmarion_county_sam3.pmtiles&l2.name=SAM3+PM+Tiles&l2.type=pmtiles&l2.fill=%23ef4444&l2.line=%23dc2626&l2.lw=2&l2.cc=%23ef4444&l2.cr=5&title=SAM3+Marion+County+OR)."
]
},
{
"cell_type": "markdown",
"id": "aoi-description",
Expand Down
18 changes: 18 additions & 0 deletions Analyzing_Data/RasterFlow_Tile2Net.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,24 @@
"It was trained on ~19cm aerial imagery from USGS for Cambridge, Manhattan, Brooklyn, and Washington DC. We will demonstrate results using 30cm resolution data from the [National Agriculture Imagery Program (NAIP)](https://www.usgs.gov/centers/eros/science/usgs-eros-archive-aerial-photography-national-agriculture-imagery-program-naip)."
]
},
{
"cell_type": "markdown",
"id": "dc508144",
"metadata": {},
"source": [
"## Preview: model inputs and outputs\n",
"\n",
"The interactive map linked below shows the input imagery and model outputs for this notebook's example AOI. Toggle layers in the sidebar to compare the inputs, the raster model output, and the vectorized geometries side-by-side.\n",
"\n",
"**Layers:**\n",
"- *Tile2Net input mosaic*: RGB high-resolution aerial imagery the model runs on\n",
"- *Tile2Net model outputs*: raster output from the model, with bands for sidewalk / road / crosswalk classes\n",
"- *Tile2Net vector geometries*: vectorized sidewalk / road / crosswalk polygons derived from the raster output\n",
"- *Tile2Net PM Tiles*: same vectors delivered as PMTiles for fast rendering at scale\n",
"\n",
"View the interactive map [here](https://viz.wherobots.com/?z=14.24&lat=38.99775&lng=-76.93743&l0.id=4b363cf8-20cf-464f-bbaf-820ae32d85de&l0.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmosaics%2Fcollegepark_optimized.zarr&l0.name=Tile2Net+input+mosaic&l0.clim=24.672528253600106%2C200.6443167352033&l0.mode=rgb&l0.rgb=r%2Cg%2Cb%2Cband&l0.var=variables&l1.id=11862f01-e388-4788-bcec-0ade21eec794&l1.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Ftile2net_optimized.zarr&l1.name=Tile2Net+model+outputs&l1.clim=0.00009313203892032774%2C0.8193664079376207&l1.mode=single&l1.rgb=sidewalk%2Croad%2Ccrosswalk%2Cband&l1.var=variables&l2.id=78ecd25a-79c8-49c7-996e-6774a45cc05a&l2.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fvectors%2Ftile2net_collegepark.parquet%2F&l2.name=Tile2Net+vector+geometries&l2.type=geoparquet&l2.fill=%233b82f6&l2.line=%232563eb&l2.lw=2&l2.cc=%233b82f6&l2.cr=5&l3.id=7ba01f8a-40b6-41df-9766-5553491ec152&l3.src=s3%3A%2F%2Fwherobots-examples%2Frasterflow%2Fmodel-outputs%2Ftile2net.pmtiles&l3.name=Tile2Net+PM+Tiles&l3.type=pmtiles&l3.fill=%23ef4444&l3.line=%23dc2626&l3.lw=2&l3.cc=%23ef4444&l3.cr=5&title=Tile2Net+College+Park+MD)."
]
},
{
"cell_type": "markdown",
"id": "74a65529",
Expand Down
Loading