Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Crop Failure Mapping Using Remote Sensing and GEE
Rating: 4.5 out of 5(1 rating)
6 students

Crop Failure Mapping Using Remote Sensing and GEE

Learn how to detect and map crop failure risk using NDVI and rainfall data in Google Earth Engine for agriculture
Created byEarth's AI
Last updated 8/2025
English

What you'll learn

  • Learn to calculate and analyze NDVI from satellite imagery for monitoring vegetation health and detecting stress in crops over time.
  • Process and interpret rainfall data using remote sensing to understand precipitation patterns and their impact on agriculture.
  • Develop comprehensive crop failure risk maps in Google Earth Engine by integrating vegetation and rainfall anomalies for proactive agricultural management.
  • Export and utilize geospatial datasets effectively for informed decision-making, agricultural planning, and risk mitigation strategies.

Course content

1 section • 6 lectures • 59m total length

  • Lecture 1: Fundamentals of Remote Sensing13:19

    This lecture introduces the basic principles of remote sensing, covering electromagnetic radiation, sensor types, and image acquisition. Students will learn how satellite sensors capture data, the importance of spectral bands, and how this data can be used to monitor Earth's surface. The lecture provides a strong foundation for understanding how remote sensing supports environmental and agricultural applications.

  • Lecture 2: Remote Sensing for Risk Mapping10:54

    This session explores how remote sensing data is applied to risk mapping, focusing on environmental hazards like drought, floods, and crop failure. Students will learn how to identify vulnerable areas by analyzing vegetation health, soil moisture, and other critical indicators. Practical examples illustrate the integration of remote sensing datasets to assess and monitor risk effectively.

  • Lecture 3: Sentinel-2 Satellite and Spectral Bands4:51

    Learn about the Sentinel-2 satellite mission, its sensor capabilities, and the significance of its spectral bands for earth observation. This lecture covers band characteristics, spatial and temporal resolutions, and how specific bands are used to calculate vegetation indices such as NDVI. Students will understand how Sentinel-2 supports detailed environmental monitoring.

  • Lecture 4: Introduction to Google Earth Engine (GEE)9:25

    This lecture introduces Google Earth Engine, a powerful cloud-based geospatial analysis platform. Students will learn how to access satellite datasets, perform data processing, and use JavaScript API for large-scale environmental analysis. The session emphasizes GEE’s potential for rapid and scalable remote sensing workflows.

  • Getting Started with the Google Earth Engine Interface3:38

    This section introduces the Google Earth Engine platform, guiding learners through accessing the Code Editor, understanding its interface, and exploring key panels like the script editor, map viewer, inspector, and data catalog. It helps beginners get comfortable navigating GEE before writing any code or performing analysis.

  • Lecture 5: Implementing Crop Failure Mapping in GEE Using Sentinel-217:50

    In this hands-on lecture, students will apply their knowledge to develop crop failure risk maps using Sentinel-2 data in Google Earth Engine. The session guides through calculating NDVI, analyzing rainfall anomalies, and integrating datasets to produce actionable maps. Students will also learn how to visualize results and export data for further use.

Requirements

  • No prior experience with Google Earth Engine is required — the course will guide you step-by-step.

Description

Crop failures due to drought, extreme weather, or land degradation have serious impacts on food security and livelihoods. In this course, you’ll learn how to monitor and map crop failure risks using remote sensing techniques and the cloud-based platform Google Earth Engine (GEE).


We begin with an introduction to vegetation monitoring using NDVI (Normalized Difference Vegetation Index) from Sentinel-2 imagery, and rainfall trends using CHIRPS daily precipitation datasets. You’ll understand how to extract seasonal NDVI and rainfall data, compute long-term averages, and calculate anomalies for the current season.


The course guides you through creating a crop risk index by combining vegetation health and rainfall deviation. You'll learn data normalization, risk index computation, and apply thresholds to identify high-risk agricultural zones. The final outputs include visually intuitive maps that highlight areas with significant crop stress.


Each step is carefully explained with working GEE JavaScript code, so you can follow along—even with little prior coding experience. You'll also learn how to export your maps as GeoTIFFs, making them suitable for GIS integration and policy reports.


Whether you're a student, researcher, or practitioner in agriculture or environmental science, this course equips you with the tools to build real-world risk mapping solutions. By the end, you’ll be confident in building your own crop failure monitoring systems using open data and GEE.

Who this course is for:

  • Students, researchers and professionals in agriculture, environmental science, geography, or remote sensing looking to apply satellite data in real-world scenarios.

Report abuse