Skip to content

Crash course

A hands-on, lesson-based introduction to TanagerSpec, Planet's Python toolkit for Tanager hyperspectral data. Each lesson works through a real scene end to end: load, clean, visualize, derive products, and export. You learn by answering an actual remote-sensing question, not by touring the API method by method.

Who this is for

Anyone who wants a guided path from raw HDF5-EOS input to useful analysis outputs, visual products, index maps, and exported files ready for GIS or further work.

You need only very, very basic Python, or even zero Python knowledge. Every lesson walks you through the code line by line, so you can follow along and learn as you go.

Prefer the cloud? Every notebook lesson opens directly in Google Colab, with no local install required. Just click the Open in Colab badge in the lesson table below to launch a lesson and try it yourself.

How to follow along: most lessons are runnable Jupyter notebooks rendered here in the docs. Use the Previous / Next links at the bottom of each page to move through the series in order, open a lesson from the sidebar, or jump straight to any lesson from the table below.

Lessons

Lesson What you'll learn Key tools Run
1. Introduction What TanagerSpec is, the analysis recipe, and how this module fits the end-to-end hyperspectral workflow. None
2. Orientation & Initialization Install TanagerSpec, download a scene from Open STAC, load it, and read scene metadata.
  • download_scene
  • TanagerSpec.from_file
  • .info()
 Open in Colab
3. Preprocessing Mask, clip, drop bands, and denoise reflectance data before analysis.
  • .drop_bands
  • .preprocess
  • .denoise
 Open in Colab
4. Export & Conversion Convert cubes and companion layers to GeoTIFF, ENVI-BIL, and xarray for use outside Python.
  • .convert_to.geotiff
  • .convert_to.envi_bil
  • .convert_to.xarray
 Open in Colab
5. Visualization & Exploration RGB composites, band views, histograms, and spectral signature comparison.
  • .plot.*
 Open in Colab
6. Spectral Indices Search the 200+ index catalog and compute published indices on the scene.
  • IndexCatalog
  • .analysis.calculate_index
 Open in Colab
7. Index Creator Lab Design and test custom band-math formulas on contiguous Tanager bands.
  • .analysis.index_creator_lab
 Open in Colab
8. Machine Learning Dimensionality reduction, clustering, and supervised classification.
  • .analysis.dim_reduction
  • .analysis.clustering
  • .analysis.classify_scene
 Open in Colab

Together, these lessons take you from raw input to interpreted outputs, and from there they open the door to your own creativity: once you know the tools, you can remix them into workflows of your own.

Part of a larger course

This crash course is Module 5 of the broader Tanager Hyperspectral Data Analysis course. These lessons teach you how to drive TanagerSpec; the full course teaches the why behind every step, the physics of reflectance spectra, radiometry, preprocessing, spectral indices, and machine learning. Start here with the hands-on lessons above, then continue into the complete curriculum when you are ready to go deeper.

The full course was designed by Abdelrahman Saleh, who also developed this package.