Skip to content

Dataset

Satellite Crop Type Mapping


This tutorial provides guidance on creating a machine learning model to identify crop types from satellite imagery and other earth observation data. It follows a process refined by Atlas AI which leverages satellite imagery of land cover, satellite-derived terrain characteristics, and weather data as inputs to the model. Users will be guided through obtaining and analyzing these data sources individually before combining them with known crop locations to train the model. For users with a sample of known crop locations, the tutorial provides a complete guide to the prediction of crop locations for an area of interest.

Data and Resources

Tags

Additional Info

Field Value
Author(s) Natalie Ayers, with contributing authors Shruti Jain and the Atlas AI team
Last Updated April 6, 2022, 23:59 (UTC)
Created September 12, 2021, 04:56 (UTC)
Stable Link https://learn.geo4.dev/Satellite%20Crop%20Mapping.html
Date 2021-09-13
Content Type Training Materials
Primary Category Land Use & Land Cover
Sub Category Automatic Crop Mapping/AG
Country Name Global, Malawi
Associated Datasets Sentinel-2 Level-2A Imagery (https://sentinel.esa.int/web/sentinel/user-guides/sentinel-2-msi/product-types/level-2a); Shuttle Radar Topography Mission (https://www2.jpl.nasa.gov/srtm/); aWhere Observed Weather (https://docs.awhere.com/knowledge-base-docs/daily-observed-weather/)
Publishing Organization Center for Effective Global Action