IEEE GRSS Washington DC & Northern VA Chapter Virtual Seminar: Advancing Large-area Crop Mapping with Satellite Data
Advancing Large-area Crop Mapping with Satellite Data
Satellite remote sensing is transforming global agricultural monitoring. Crop maps from satellite data are essential for crop monitoring systems and crop modeling projects. Generating high-resolution crop maps is a research area of significant potential. The Landsat and Sentinel series of satellites, with 10-30 m spatial resolution, sub-weekly revisit frequency, free data policy, and standardized pre-processing, represent the best available datasets for crop mapping over large areas. This talk presents a multi-scale mapping approach with satellite Analysis Ready Data (ARD) generation, machine learning, probability sampling and in situ data collection as critical components. The approach can simultaneously produce crop area estimates with uncertainty estimates and crop classification maps with validation accuracy. Crop mapping results at national and continental scales over the United States, Canada, China and South America are illustrated.
Date and Time
Location
Hosts
Registration
- Date: 21 Dec 2023
- Time: 12:00 PM to 01:00 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
-
Add Event to Calendar
- Starts 18 December 2023 09:20 AM
- Ends 21 December 2023 12:20 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
- No Admission Charge
Speakers
Xiaopeng Song of University of Maryland
Advancing Large-area Crop Mapping with Satellite Data
Satellite remote sensing is transforming global agricultural monitoring. Crop maps from satellite data are essential for crop monitoring systems and crop modeling projects. Generating high-resolution crop maps is a research area of significant potential. The Landsat and Sentinel series of satellites, with 10-30 m spatial resolution, sub-weekly revisit frequency, free data policy, and standardized pre-processing, represent the best available datasets for crop mapping over large areas. This talk presents a multi-scale mapping approach with satellite Analysis Ready Data (ARD) generation, machine learning, probability sampling and in situ data collection as critical components. The approach can simultaneously produce crop area estimates with uncertainty estimates and crop classification maps with validation accuracy. Crop mapping results at national and continental scales over the United States, Canada, China and South America are illustrated.
Biography:
Xiao-Peng Song is an Assistant Professor in the Department of Geographical Sciences at the University of Maryland, College Park. His current research focuses on crop mapping and crop production forecasting using satellite remote sensing. He has published in a number of leading academic journals including Nature, Nature Food and Nature Sustainability. Xiao-Peng received his Ph.D. in Geographical Sciences from the University of Maryland in 2015, and his B.S. in GIS and Economics from Peking University in 2008.
Email: