Related Concept Videos
Light Acquisition
Methods of Obtaining Topography
Levels of Use of a GIS
Topographic Surveying and Contours
Thematic Layering in GIS
GIS Software, Hardware, and Sources of GIS Data
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Unraveling volcanic impacts in semi-arid climates: machine learning and CMIP6 insights from Krakatau and Santa Maria.
Unsupervised mapping of urban tree diversity using spatially-aware visual clustering.
Bat2Web: A Framework for Real-Time Classification of Bat Species Echolocation Signals Using Audio Sensor Data.
Related Experiment Video
Updated: Jul 19, 2025

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
Published on: October 16, 2018
A Light-Weight Cropland Mapping Model Using Satellite Imagery.
Maya Haj Hussain1, Diaa Addeen Abuhani1, Jowaria Khan1
1Department of Computer Science and Engineering, American University of Sharjah, Sharjah P.O. Box 26666, United Arab Emirates.
This study introduces a fast, cost-effective machine learning model for creating accurate cropland maps using satellite imagery. The approach enhances global crop production and food security assessments by providing reliable data efficiently.
More Related Videos
12:26Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
Published on: October 11, 2016
08:47Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
Area of Science:
- Agricultural Science
- Remote Sensing
- Environmental Monitoring
Background:
- Reliable cropland maps are essential for agriculture, natural resources, environment, health, and sustainability.
- Manual cropland mapping is labor-intensive, costly, and time-consuming, hindering global food security studies.
- Satellite imagery offers a potential solution for efficient cropland assessment.
Purpose of the Study:
- To develop a cost-effective, fast, and accurate machine learning-based approach for cropland mapping.
- To create a reliable model for assessing cropland extent and intensity using satellite data.
- To address the limitations of manual data collection for agricultural monitoring.
Main Methods:
- Utilized Sentinel-2 satellite imagery for four diverse test regions: Iran, Mozambique, Sri-Lanka, and Sudan.
- Implemented a complete pipeline involving data collection and time series reconstruction.
- Applied machine learning models for cropland extent and crop intensity mapping, incorporating NDVI (Normalized Difference Vegetation Index) scores.
Main Results:
- Achieved high accuracy in cropland mapping across all four test regions.
- Reported accuracy scores ranging from 0.92 to 0.98.
- Demonstrated the effectiveness of the machine learning approach in diverse geographical contexts.
Conclusions:
- The proposed machine learning approach provides a reliable and efficient method for cropland mapping.
- This technique offers a cost-effective alternative to traditional manual mapping methods.
- The model's high accuracy supports improved agricultural monitoring and food security assessments globally.