Remote Sensing with Google Earth Engine Training Course

Introduction

The field of Remote Sensing has been revolutionized by the advent of cloud-based platforms that democratize access to vast archives of satellite imagery and powerful computational capabilities. Google Earth Engine (GEE) stands at the forefront of this transformation, offering a planetary-scale platform for geospatial analysis that combines a multi-petabyte catalog of Earth observation data with a powerful, parallel processing engine. This revolutionary platform enables users to perform complex analyses on massive datasets – including Landsat, Sentinel, MODIS, and various climate datasets – without the need for specialized hardware or extensive local data storage. GEE is particularly impactful for large-scale environmental monitoring, land change detection, climate change research, and agricultural applications, allowing researchers and practitioners to tackle problems at scales previously unimaginable. It empowers users to analyze decades of satellite imagery in minutes, facilitating time-series analysis, rapid mapping, and machine learning applications that were once the domain of supercomputers. However, effectively harnessing the power of GEE requires proficiency in its JavaScript or Python API, understanding its unique data model, and familiarity with its server-side computational paradigm. Many remote sensing professionals are accustomed to desktop software and traditional data handling, finding the transition to a cloud-native, code-based environment challenging without structured guidance.

Conversely, mastering Remote Sensing with Google Earth Engine empowers professionals to perform cutting-edge geospatial analysis on an unprecedented scale, allowing them to extract critical insights from Earth observation data quickly and efficiently. This specialized skill set is crucial for transforming raw satellite data into actionable geographic intelligence, driving innovative solutions for environmental sustainability, resource management, and climate resilience. Our intensive 5-day "Remote Sensing with Google Earth Engine" training course is meticulously designed to equip GIS professionals, remote sensing analysts, environmental scientists, researchers, and data scientists with the essential theoretical knowledge and practical, hands-on coding skills required to confidently leverage the immense power of Google Earth Engine for advanced Earth observation and analysis.

Duration

5 Days

Target Audience

The "Remote Sensing with Google Earth Engine" training course is ideal for a wide range of professionals and researchers who need to perform large-scale geospatial analysis and work with vast Earth observation datasets. This includes:

  • Remote Sensing Analysts and Specialists: Seeking to transition to cloud-based, large-scale processing.
  • GIS Professionals: Who want to integrate advanced satellite imagery analysis into their workflows.
  • Environmental Scientists and Ecologists: For monitoring land cover, deforestation, water resources, and ecological changes.
  • Climate Change Researchers: Analyzing long-term trends in climate variables and environmental impacts.
  • Agriculturalists and Agronomists: For regional crop monitoring, drought assessment, and yield estimation.
  • Hydrologists and Water Resource Managers: For mapping water bodies, snow cover, and flood extent.
  • Data Scientists and Developers: Interested in applying machine learning and programming to geospatial big data.
  • Researchers and Academics: In Earth sciences, geography, environmental studies, and sustainable development.
  • Anyone involved in projects requiring access to and analysis of vast archives of satellite imagery.

Course Objectives

Upon successful completion of the "Remote Sensing with Google Earth Engine" training course, participants will be able to:

  • Understand the architecture and core concepts of the Google Earth Engine platform.
  • Efficiently access, filter, and manage large collections of satellite imagery and other geospatial data in GEE.
  • Perform essential image pre-processing tasks (e.g., cloud masking, radiometric correction) within GEE.
  • Apply various spectral indices and image enhancement techniques for feature extraction and analysis.
  • Conduct time-series analysis to monitor environmental change and trends over large areas.
  • Perform image classification (supervised and unsupervised) for land cover mapping.
  • Utilize GEE's computational power for advanced analysis, including spatial aggregation and zonal statistics.
  • Export results from GEE for further use and communicate findings effectively through mapping and charting.

 Course Modules

Module 1: Introduction to Google Earth Engine and Cloud-Based Remote Sensing

  • Overview of cloud computing in GIS and remote sensing.
  • Introduction to Google Earth Engine (GEE): History, architecture, advantages (data catalog, computation).
  • Navigating the GEE Code Editor (JavaScript API) and understanding its interface.
  • Basic GEE concepts: Image, ImageCollection, Feature, FeatureCollection.
  • Setting up your GEE account and running your first script.

Module 2: Accessing and Filtering Earth Engine Data Catalog

  • Exploring the GEE Public Data Catalog: Landsat, Sentinel, MODIS, climate data, elevation data.
  • Filtering ImageCollections by date, spatial bounds, and metadata properties.
  • Reducing ImageCollections to single images (e.g., median, mean composites).
  • Visualizing single images and ImageCollections.
  • Understanding and applying different visualization parameters (bands, min/max, palette).

Module 3: Basic Image Pre-processing and Enhancements in GEE

  • Common pre-processing needs: Cloud masking, atmospheric correction (conceptual).
  • Applying built-in cloud masking algorithms (e.g., for Landsat, Sentinel-2).
  • Calculating spectral indices: NDVI, NDWI, EVI, NBR, and custom indices.
  • Image enhancement techniques: Stretching, clipping.
  • Stacking and combining multiple bands for multi-spectral analysis.

Module 4: Time-Series Analysis and Change Detection

  • Working with time-series ImageCollections for long-term monitoring.
  • Creating temporal composites (e.g., monthly, annual medians).
  • Visualizing temporal change using animations and charts.
  • Simple change detection methods: Image differencing, ratioing, change vector analysis (conceptual).
  • Applications: Deforestation monitoring, urban growth, drought assessment.

Module 5: Supervised Image Classification for Land Cover Mapping

  • Principles of image classification: Training data, classifiers, accuracy assessment.
  • Collecting training data points/polygons within GEE.
  • Introduction to common GEE classifiers: Random Forest, Support Vector Machine (SVM), CART.
  • Performing supervised classification and generating land cover maps.
  • Basic accuracy assessment methods for classified images (confusion matrix, overall accuracy).

Module 6: Unsupervised Classification and Zonal Statistics

  • Introduction to unsupervised classification algorithms (e.g., ee.Clusterer.wekaKMeans).
  • Interpreting and assigning classes to unsupervised clusters.
  • Comparing supervised vs. unsupervised approaches in GEE.
  • Zonal Statistics: Calculating statistics (mean, median, sum) of image pixels within defined geographic zones (e.g., administrative boundaries, watersheds).
  • Aggregating data from raster to vector layers.

Module 7: Advanced Spatial Analysis and Vector Operations

  • Working with FeatureCollections: Importing, filtering, and joining tabular data with spatial features.
  • Performing spatial overlays (intersect, union) on vector data.
  • Buffer analysis and proximity calculations.
  • Calculating areas, lengths, and perimeters of geographic features.
  • Converting raster data to vector (e.g., polygonizing classification results).

Module 8: Data Export, Charting, and Advanced Topics

  • Exporting results from GEE to Google Drive, Google Cloud Storage, or as GeoTIFF/Shapefile.
  • Creating interactive charts and plots directly within the GEE Code Editor.
  • Introduction to the Python API for GEE (colab notebook setup).
  • Brief overview of GEE's machine learning capabilities (e.g., for deep learning applications).
  • Performance optimization tips and best practices for large-scale GEE scripts.

CERTIFICATION

  • Upon successful completion of this training, participants will be issued with Macskills Training and Development Institute Certificate

TRAINING VENUE

  • Training will be held at Macskills Training Centre. We also tailor make the training upon request at different locations across the world.

AIRPORT PICK UP AND ACCOMMODATION

  • Airport pick up and accommodation is arranged upon request

TERMS OF PAYMENT

Payment should be made to Macskills Development Institute bank account before the start of the training and receipts sent to info@macskillsdevelopment.com

 

Remote Sensing With Google Earth Engine Training Course in North Macedonia
Dates Fees Location Action