Tutorials

Looking to improve your data skills using tools like R or Python? Want to learn more about working with a specific NEON data product? NEON develops online tutorials to help you improve your research. These self-paced tutorials are designed for you to used as standalone help on a single topic or as a series to learn new techniques.

Code for all script based tutorials can be downloaded at the end of the tutorial. Original files can also be found on GitHub.

All materials are freely available for you to use and reuse. We suggest the following citation for tutorials:  [AUTHOR(S), NEON (National Ecological Observatory Network)]. Data Tutorial: [TUTORIAL NAME]. [URL] (accessed [DATE OF ACCESS]). See Citation Guidelines for examples, and for guidance in citing data and code.

Tutorials

About Hyperspectral Remote Sensing Data

0.25 - 0.5 Hours

Learn about the fundamental principles of hyperspectral remote sensing data.

Access and Work with NEON Geolocation Data

30 minutes

Use files available on the NEON data portal, NEON API, and neonUtilities R package to access the locations of NEON sampling events and infrastructure. Calculate more precise locations for certain sampling types and reference ground sampling to airborne data.

Assessing Spectrometer Accuracy using Validation Tarps with Python

0.5 hour

Learn to analyze the difference between rasters taken a few days apart to assess the uncertainty between days.

Assignment: Reproducible Workflows with Jupyter Notebooks

1 hour

This page details how to complete the assignment for pre-Institute week 3 on documenting your code with Jupyter Notebooks.

Assignment: Version Control with GitHub

1 hour

Data Institute Assignment: The page lists the requirements for the week 2 assignment on version control and GitHub.

Band Stacking, RGB & False Color Images, and Interactive Widgets in Python - Flightline Data

0.5 hours

Learn to efficiently work with flightline NEON AOP spectral data using functions.

Band Stacking, RGB & False Color Images, and Interactive Widgets in Python - Tiled Data

0.5 hours

Learn to efficiently work with tiled NEON AOP spectral data using functions.

Basic R Skills

This series provides tutorials and references on key skills needed to complete more complex tasks in R. It is not intended as an guide for the introduction to or initial learning of how to use R.

Series

4 part series

Build & Work With Functions in R

30 minutes

This tutorial teaches the basics of creating a function in R.

Calculate NDVI & Extract Spectra Using Masks in Python - Tiled Data

0.5 hours

Learn to calculate Normalized Difference Vegetation Index (NDVI) and extract spectral using masks with Python and NEON tiled hyperspectral data products.

Calculate Vegetation Biomass from LiDAR Data in Python

1 hour

Learn to calculate the biomass of standing vegetation using a canopy height model data product.

Calculating Forest Structural Diversity Metrics from NEON LiDAR Data

30 minutes

Read in a NEON LiDAR file (.laz) and calculate several forest structural diversity

Classification of Hyperspectral Data with Ordinary Least Squares in Python

1 hour

Learn to classify spectral data using the Ordinary Least Squares method.

Classification of Hyperspectral Data with Principal Components Analysis (PCA) in Python

1 hour

Learn to classify spectral data using the Principal Components Analysis (PCA) method.

Classification of Hyperspectral Data with Support Vector Machine (SVM) Using SciKit in Python

1 hour

Learn to classify spectral data using the Support Vector Machine (SVM) method.

Classify a Raster Using Threshold Values in Python - 2017

1 hour

Learn how to read NEON lidar raster GeoTIFFs (e.g., CHM, slope, aspect) into Python numpy arrays with gdal and create a classified raster object.

Compare tree height measured from the ground to a Lidar-based Canopy Height Model

1 hour

Investigate the relationship between two methods for measuring canopy height

Convert to Julian Day

20 minutes

This tutorial explains why Julian days are useful and teaches how to create a Julian day variable from a Date or Data/Time class variable.

Create a Canopy Height Model from lidar-derived Rasters in R

0.5 Hours

In this tutorial, you will bring lidar-derived raster data (DSM and DTM) into R to create a canopy height model (CHM).

Create a Hillshade from a Terrain Raster in Python

0.5 hour

Learn how to create a hillshade from a terrain raster in Python.

Create A Square Buffer Around a Plot Centroid in R

1.0 - 1.5 Hours

This tutorial walks you through creating square polygons from a plot centroid (x,y format) in R.

Create HDF5 Files in R Using Loops

1.0 - 1.5 Hours

Create a HDF5 in R from scratch! Add groups and datasets. View the files with HDFView.

Creating a Raster Stack from Hyperspectral Imagery in HDF5 Format in R

1.0 - 1.5 Hours

Open up and explore hyperspectral imagery in HDF format R. Combine multiple bands to create a raster stack. Use these steps to create various band combinations such as RGB, Color-Infrared and False color images.

Data Activity: Visualize Elevation Change using LiDAR in R to Better Understand

1 hour

This tutorial teaches how to use Digital Terrain Models derived from

Data Activity: Visualize Palmer Drought Severity Index Data in R to Better

1 hour

This tutorial walks through how to download and visualize Palmer Drought

Data Activity: Visualize Precipitation Data in R to Better Understand the

1 hour

This lesson walks through the steps need to download and visualize precipitation

Data Activity: Visualize Stream Discharge Data in R to Better Understand the 2013 Colorado Floods

1 hour

This lesson walks through the steps needed to download and visualize USGS

Data Institute Activity: Calculate Index of Interest

30 mins

This page details the remote sensing hyperspectral imaging indices activity used during Data Institutes.

Data Institute: Install Required R Packages

1.0 - 1.5 Hours

This tutorial covers the R packages that you will need to have installed for the Institute.

Data Management using National Ecological Observatory Network’s (NEON) Small Mammal Data with Accompanying Lesson on Mark Recapture Analysis