Nowadays, the availability of remote sensing and geospatial data as big data poses a challenge concerning how we can process this data, and for what purpose.

 

To learn more about how to conveniently and efficiently deal with big data in the field of remote sensing, this online course will teach you some of the steps that are needed to start your own remote sensing imagery supported project for your research and interests – ranging from the very basic to rather advanced concepts.

 

By following these courses, you can improve your remote sensing data analysis skills and gain valuable proficiency that can be easily transferred to any related field of environmental earth sciences.

 

For these courses, we will be using the Google Earth Engine, a cloud-based computing and analysis tool for spatial data, powered by the Google Cloud Platform. Since the tool is web-based, there is no need for installing any software to your computer and you can take your work wherever you have internet access.

This course will provide useful lectures to get started with the Google Earth Engine and is split into 3 main topics. 

 

1. Introduction to the Google Earth Engine

1.1 Big Data for earth monitoring and documentation of basic software

     - Available data in Google Cloud Platform

     - Webbased programming environment

     - Integration of the GEE in RStudio, QGIS and Python

1.2 Getting started with the Google Earth Engine

     - GEE and its processing Infrastructure

     - Basic JavaScript in GEE

     - Raster and Vector Code: Access and Filters

     - Visualization of data

     - Raster and Vector Code: Clip and Reduce

     - Visualization of data

     - Charts in the GEE

     - Assetts

     - Summary and Best Practice

1.3 Self Assessment

 

 

2. Monitoring the Normalized Difference Vegetation Index and Normalized Burn Ratio (Landsat 8, Sentinel 2 and MODIS)

2.1 Basic Methodology and Literature

     - Spectral Indices

     - Normalized Difference Vegetation Index (NDVI)

     - Normalized Burn Ratio

2.2 Calculating Spectral Indices in the Google Earth Engine

     - NDVI - Sentinel 2

     - NDVI - Landsat 8

     - NDVI - MODIS

     - NBR - Sentinel 2

     - NBR - Landsat 8

     - NBR - MODIS

2.3 Monitoring the NDVI and NBR in the GEE

     - NDVI - Preparation of Base Data

     - NDVI - Difference Image

     - NDVI - Charts

     - NDVI - Classification and Area Calculation

     - NBR - Preparation of Base Data

     - NBR - Difference Image

     - NBR - Charts

     - NBR - Classification and Area Calculation

2.4 Comparison and Analysis of the Results

2.5 Self Assessment

 

3. Classification of Satellite data

3.1 Methodical Background

     - Classification and Regression Trees (CART)-Classifier

     - Random Forest-Classifier

     - Linear Regression Time Series Trend Analysis

3.2 Classification in the Google Earth Engine

     - Data Preparation

     - Creating Training Samples

     - Classification and Validation

     - Interpretation and Thoughts of Improvement

     - Improved Classification

3.3 Linear Regression in the Google Earth Engine

3.4 Self Assessment

 

 

Important note: To use the Google Earth Engine, you will need to register a Google-Account and verify it for the Google Earth Engine. In this process, you will be asked about what you will be using the GEE for, if you are working for any kind of institution and if you are planning to use it for commercial matters. The process of verification can take up to weeks, so you better set your account off before you run into important deadlines. You will get a verification email as soon as your account is approved to use the GEE.