Normalized Difference Indices
So what can we do with all these bands? One example can be seen in Normalized Difference Vegetation Index (NDVI). This method, which was published in 1974, is calculated by subtracting red from the near-infrared, and dividing it by the sum of near-infrared and red. The near-infrared is strongly reflected by healthy vegetation, while the red band is absorbed for photosynthesis.
With Sentinel-2 specifically this looks like: NDVI = (Band 8 - Band 4) / (Band 8 + Band 4). The result is a raster where photosynthesizing organisms are highlighted!
There are lots of other types of normalized difference indices, for snow, water, and more. One method I focused on for quite some time was NDBI, or Normalized Difference Built-Up Index. This is a similar calculation NDBI = (B11 - B8) / (B11 + B8) where band 11 is the short-wave Infrared and band 8 is the near-infrared. In the SWIR, human-made built up areas have high reflectance, and in NIR they have lower reflectance. NDBI rasters highlight the contrast between natural terrain and human-built structures.
Shapefiles
Shapefiles, simply put, are a geospatial vector data format that stores information such as location, shape, and other attributes. Shapefiles are available for all sorts of information; we are interested in building footprint data. If you take a sat image, and draw a neatly enclosed shape around every building, you’ll get the idea. Shapefiles for all sorts of data are freely available for practically the whole planet.
We can do math between these NDBI rasters.
🔍 Change Detection with ΔNDBI Let us assume for a few minutes that NDBI is a perfect tool for damage detection, it is not, but we will get to that later.
If we take 2 NDBI rasters from 2 consecutive dates, and we subtract the earlier date from the later date, the result is a raster where only changes in human-built infrastructure are highlighted. Better yet, we can take our known-good building footprint shapefile and use it to crop the delta NDBI image we just made. Now we have a raster file that displays only changes to buildings which already exist, between 2 dates.
In the case of Gaza, we can use this technique to theoretically detect the destruction of most individual buildings within Gaza, to a temporal resolution of roughly 5 days, when weather permits.
These damage masks can be used like transparencies and placed atop sat images to better visualize damage between any two revisits, but we can do much more than that using advanced geospatial tools. Precise location data is baked into the shapefiles and this type of raster data. Because of this, it should be theoretically possible to build an automated system which detects if a notable change threshold has been detected within any given building footprint, and if so, record the latitude/longitude coordinates of that damage, to be later cross referenced with other location and address specific data.
Beyond Normalized Differences: Foundation Models
While normalized difference indices like ΔNDBI were foundational to early remote sensing analysis, they are inherently limited by their reliance on simple arithmetic between fixed bands. The future of change detection doesn’t lie in manually crafting indices, but in teaching machines to understand the physics of the Earth’s surface.
Sentinel Bird is currently moving beyond traditional indices by training bridge neural networks that translate data between different satellite modalities—specifically, bridging the gap between Sentinel-1 (Synthetic Aperture Radar) and Sentinel-2 (Optical). By building these cross-modal foundation models, we can leverage the all-weather, day-and-night capabilities of radar to inform and enhance optical analysis.
While this work is still under wraps, the ultimate goal is to fine-tune these foundation models for damage detection tasks on a global scale. Instead of relying on brittle, hand-crafted math to find destroyed buildings, we are training models that inherently understand the structural and spectral signatures of human infrastructure, allowing for vastly more accurate, automated, and scalable documentation of destruction anywhere on the planet.
What’s Next?
You’ve reached the end of the remote sensing primer! Now that you understand the data, the tools, and the methodology behind Sentinel Bird, you are ready to explore the archive.
(Next: Return to the Gaza Strip Overview or Browse Imagery by Date)